Aperture fusion using separate devices

Abstract

Systems and techniques for combining images captured by two or more image sensors are disclosed. For example, a method may include obtaining a first image of a scene from a first image sensor of a first device. The method may include obtaining a second image including at least a portion of the scene from a second image sensor of a second device. The second image is transmitted via the communication link. The method may include determining a location between the first device and the second device based on a relative pose between the first device and the second device. The method may include normalizing one or more image attributes between the first image and the second image. The method may include generating a third image based on the first image and the second image based on locating and normalizing the one or more image attributes.

Description

Technical Field

[0001] The present disclosure relates generally to image processing. For example, aspects of the present disclosure relate to systems and techniques for fusing images captured by two or more cameras (eg, in two or more different electronic devices). Background Art

[0002] Many devices and systems allow for capturing a scene by generating images (also referred to as frames or photographs) and / or video data (comprising multiple frames) of the scene. For example, a camera or a device incorporating a camera can capture a single image or a sequence of frames (e.g., a video) of a scene. In some cases, the image or sequence of frames can be processed to perform one or more functions, output for display, output for processing and / or consumption by another device, and for other uses.

[0003] In some cases, multiple cameras can simultaneously capture images and / or video frames of a scene with different fields of view, poses, depths of field, resolutions, focus, etc. In some cases, viewing images from multiple cameras can provide a wider perspective of the scene. For example, an image from a first camera can capture details of individual athletes at a sporting event, while an image from a second camera can capture multiple athletes from a team spread out on the field, the crowd, and / or other details not captured by the image from the first camera.

[0004] Extended reality (XR) devices are another example of devices that may include one or more cameras. XR devices can include augmented reality (AR) devices, virtual reality (VR) devices, mixed reality (MR) devices, and so on. Examples of AR devices include smart glasses and head-mounted displays (HMDs). Typically, AR devices may implement cameras and various sensors to track the position of the AR device and other objects within the physical environment. AR devices use tracking information to provide users of the AR devices with realistic AR experiences. For example, AR devices may allow users to experience or interact with immersive virtual environments or content. To provide a realistic AR experience, AR technology generally aims to integrate virtual content with the physical world. In some examples, AR technology can match the relative position and movement of objects and devices. For example, an AR device may use tracking information to calculate the relative position of the device, objects, and / or a map of the real-world environment to match the relative position and movement of the device, objects, and / or the real-world environment. Using the position and movement of one or more devices, objects, and / or the real-world environment, the AR device can convincingly anchor content to the real-world environment. Relative pose information can be used to match virtual content to the user's perceived motion and the spatiotemporal state of the device, objects, and the real-world environment. Summary of the Invention

[0005] Systems and techniques for processing images are described herein. According to at least one example, a method for processing an image is provided. The method includes obtaining a first image of a scene from a first image sensor of a first device; obtaining a second image including at least a portion of the scene from a second image sensor of a second device, wherein the second image is transmitted via a communication link between the first device and the second device; determining a position between the first device and the second device based on a relative pose between the first device and the second device; normalizing one or more image attributes between the first image and the second image; and generating a third image based on the first image and the second image based on the position between the first device and the second device and the normalized one or more image attributes between the first image and the second image.

[0006] In another example, an apparatus for processing an image is provided, comprising at least one memory and at least one processor coupled to the at least one memory. The at least one processor is configured to: obtain a first image of a scene from a first image sensor of a first device; obtain a second image including at least a portion of the scene from a second image sensor of a second device, wherein the second image is sent via a communication link between the first device and the second device; determine a position between the first device and the second device based on a relative position between the first device and the second device; normalize one or more image attributes between the first image and the second image; and generate a third image based on the first image and the second image based on the position between the first device and the second device and the normalized one or more image attributes between the first image and the second image.

[0007] In another example, a non-transitory computer-readable medium having instructions stored thereon is provided, wherein the instructions, when executed by one or more processors, cause the one or more processors to: obtain a first image of a scene from a first image sensor of a first device; obtain a second image including at least a portion of the scene from a second image sensor of a second device, wherein the second image is sent via a communication link between the first device and the second device; determine a positioning between the first device and the second device based on a relative pose between the first device and the second device; normalize one or more image attributes between the first image and the second image; and generate a third image based on the first image and the second image based on the positioning between the first device and the second device and the normalized one or more image attributes between the first image and the second image.

[0008] In another example, an apparatus for processing an image is provided. The apparatus includes: a component for obtaining a first image of a scene from a first image sensor of a first device; a component for obtaining a second image including at least a portion of the scene from a second image sensor of a second device, wherein the second image is sent via a communication link between the first device and the second device; a component for determining a position between the first device and the second device based on a relative pose between the first device and the second device; a component for normalizing one or more image attributes between the first image and the second image; and a component for generating a third image based on the first image based on the position between the first device and the second device and the normalized one or more image attributes between the first image and the second image.

[0009] In some aspects, one or more of the devices described herein is a camera, a mobile device (e.g., a mobile phone or so-called "smartphone" or other mobile device), a wireless communication device, an extended reality device (e.g., a virtual reality (VR) device, an augmented reality (AR) device, or a mixed reality (MR) device), a wearable device, a personal computer, a laptop computer, a server computer, or other device, or a portion thereof. In some aspects, one or more processors include an image signal processor (ISP). In some aspects, the device includes a camera or multiple cameras for capturing one or more images. In some aspects, the device includes an image sensor for capturing image data. In some aspects, the device also includes a display for displaying the image, one or more notifications (e.g., associated with the processing of the image), and / or other displayable data.

[0010] This summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to be used alone to determine the scope of the claimed subject matter. The subject matter should be understood by reference to appropriate portions of the entire specification of this patent, any or all of the drawings, and each claim.

[0011] The foregoing and other features and aspects will become more apparent by reference to the following description, claims, and accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Illustrative aspects of the present application are described in detail below with reference to the following drawings:

[0013] Figure 1 is a block diagram illustrating the architecture of an image capture and processing device according to some examples of the present disclosure;

[0014] Figure 2 is a block diagram illustrating the architecture of an example extended reality (XR) system according to some examples of the present disclosure;

[0015] Figure 3is a block diagram illustrating the architecture of a Simultaneous Localization And Mapping (SLAM) device according to some examples of the present disclosure;

[0016] Figure 4A and Figure 4B An example of spatial alignment and transformation (SAT) of an image according to some examples of the present disclosure is shown;

[0017] Figure 4C shows perspective views of Fields Of View (FOV) captured by different image sensors according to some examples of the present disclosure;

[0018] Figure 4D and Figure 4E illustrates perspective views of FOVs captured by image sensors of different electronic devices according to some examples of the present disclosure;

[0019] Figure 5 is a block diagram illustrating an example aperture fusion system according to some examples of the present disclosure;

[0020] Figure 6 is a block diagram illustrating an example aperture fusion engine according to some examples of the present disclosure;

[0021] Figure 7 is a diagram illustrating an example user interface for an aperture fusion system according to some examples of the present disclosure;

[0022] Figure 8A and Figure 8B is a diagram illustrating an example alignment indicator for an aperture fusion system including a head mounted display (HMD) and a mobile device according to some examples of the present disclosure;

[0023] Figure 9A is a perspective diagram illustrating an unmanned ground vehicle (UGV) performing feature tracking and / or visual simultaneous localization and mapping (VSLAM) according to some examples;

[0024] Figure 9B is a perspective diagram illustrating an unmanned aerial vehicle (UAV) performing feature tracking and / or VSLAM according to some examples;

[0025] Figure 10Ais a perspective view illustrating a head-mounted display (HMD) performing feature tracking and / or VSLAM according to some examples;

[0026] Figure 10B is shown being worn by a user according to some examples Figure 9A Perspective view of the HMD;

[0027] Figure 11A is a perspective view illustrating a front surface of a mobile handset using one or more front-facing cameras to perform feature tracking and / or VSLAM according to some examples;

[0028] Figure 11B is a perspective view illustrating a rear surface of a mobile handset using one or more rear-facing cameras to perform feature tracking and / or VSLAM according to some examples;

[0029] Figure 12 is a flow chart illustrating an example of an image processing technique according to some examples;

[0030] Figure 13 is a diagram illustrating an example of a system for implementing certain aspects of the present technology. DETAILED DESCRIPTION

[0031] Provided below are certain aspects of the present disclosure. Some of these aspects can be applied independently, and some of them can be applied in combination, which will be apparent to those skilled in the art. In the following description, for the purpose of explanation, specific details are set forth in order to provide a thorough understanding of various aspects of the application. However, it will be apparent that various aspects can be practiced without these specific details. The accompanying drawings and description are not intended to be restrictive.

[0032] The following description provides only exemplary aspects and is not intended to limit the scope, applicability, or configuration of the present disclosure. Rather, the following description of the exemplary aspects will provide those skilled in the art with an enabling description for implementing the exemplary aspects. It should be understood that various changes may be made to the function and arrangement of elements without departing from the spirit and scope of the present application as set forth in the appended claims.

[0033] An image capture device (e.g., a camera) is a device that receives light and uses an image sensor to capture image frames, such as still images or video frames (or sequences of still images or video frames). The terms "image," "image frame," "video frame," and "frame" are used interchangeably herein. An image capture device typically includes at least one lens that receives light from a scene and bends the light toward the image sensor of the image capture device. The light received by the lens passes through an aperture controlled by one or more control mechanisms and is received by the image sensor. In some cases, the one or more control mechanisms can control exposure, focus, and / or zoom based on information from the image sensor and / or based on information from an image processor (e.g., a host or application process and / or an image signal processor). In some cases, the images or frame sequences can be processed to perform one or more functions, output for display, output for processing and / or consumption by other devices, and for other uses.

[0034] Degrees of Freedom (DoF) refers to the number of fundamental ways a rigid object can move in three-dimensional (3D) space. In some cases, six different DoFs can be tracked. The six DoFs include three translational DoFs corresponding to translational movement along three orthogonal axes. These three axes can be referred to as the x, y, and z axes. The six DoFs include three rotational DoFs corresponding to rotational movement about three axes, which can be referred to as pitch, yaw, and roll.

[0035] Extended reality (XR) devices are another example of devices that may include one or more cameras. XR devices can include augmented reality (AR) devices, virtual reality (VR) devices, mixed reality (MR) devices, and so on. Examples of AR devices include smart glasses and head-mounted displays (HMDs). Typically, AR devices may implement cameras and various sensors to track the position of the AR device and other objects within the physical environment. AR devices use tracking information to provide users of the AR devices with realistic AR experiences. For example, AR devices may allow users to experience or interact with immersive virtual environments or content. To provide a realistic AR experience, AR technology generally aims to integrate virtual content with the physical world. In some examples, AR technology can match the relative position and movement of objects and devices. For example, an AR device may use tracking information to calculate the relative position of the device, objects, and / or a map of the real-world environment to match the relative position and movement of the device, objects, and / or the real-world environment. Using the position and movement of one or more devices, objects, and / or the real-world environment, the AR device can convincingly anchor content to the real-world environment. Relative pose information can be used to match virtual content to the user's perceived motion and the spatiotemporal state of the device, objects, and the real-world environment.

[0036] XR systems or devices can provide users with virtual content and / or can combine a real-world or physical environment with a virtual environment (composed of virtual content) to provide users with an XR experience. The real-world environment can include real-world objects (also known as physical objects) such as people, vehicles, buildings, tables, chairs, and / or other real-world or physical objects. XR systems or devices can facilitate interaction with different types of XR environments (e.g., a user can interact with an XR environment using an XR system or device). XR systems can include virtual reality (VR) systems that facilitate interaction with VR environments, augmented reality (AR) systems that facilitate interaction with AR environments, mixed reality (MR) systems that facilitate interaction with MR environments, and / or other XR systems. As used herein, the terms XR system and XR device are used interchangeably. Examples of XR systems or devices include head-mounted displays (HMDs), smart glasses, and the like. In some cases, the XR system can track parts of the user (e.g., the user's hands and / or fingertips) to allow the user to interact with virtual content items.

[0037] Visual Simultaneous Localization and Mapping (VSLAM) is a computational geometry technique used in devices with cameras, such as robots, head-mounted displays (HMDs), mobile handsets, and autonomous vehicles. In VSLAM, a device can build and update a map of an unknown environment based on images captured by the device's camera. As the device updates the map, it can track the device's pose (e.g., position and / or orientation) within the environment. For example, a device can be activated in a specific room of a building and can move throughout the interior of the building, capturing images. The device can build a map of the environment and track its position within the environment by tracking where different objects in the environment appear in different images.

[0038] In some embodiments, the output of one or more sensors (e.g., accelerometers, gyroscopes, one or more inertial measurement units (IMUs), and / or other sensors) can be used to determine the pose of a device (e.g., an HMD, a mobile device, etc.). An IMU is an electronic device that uses a combination of one or more accelerometers, one or more gyroscopes, and / or one or more magnetometers to measure the specific force, angular rate, and / or orientation of an electronic device. In some examples, the one or more sensors can output measurement information associated with the capture of images captured by a camera of the device (e.g., an HMD, a mobile device, etc.) and / or depth information obtained using one or more depth sensors of the device.

[0039] In the context of systems that track movement in an environment (such as XR systems and / or VSLAM systems), degrees of freedom can refer to which of the six degrees of freedom the system is able to track. 3DoF systems typically track three rotational DoFs—pitch, yaw, and roll. For example, a 3DoF headset can track whether the user of the headset turns their head left or right, tilts their head up or down, and / or tilts their head left or right. A 6DoF system can track three translational DoFs as well as three rotational DoFs. So, for example, in addition to tracking three rotational DoFs, a 6DoF headset can also track a user moving forward, backward, laterally, and / or vertically.

[0040] Systems that track movement within an environment, such as XR systems and / or VSLAM systems, typically include powerful processors. These powerful processors can be used to perform complex operations quickly enough to display up-to-date output based on these operations to the user of these systems. Such complex operations may involve feature tracking, 6DoF tracking, VSLAM, rendering virtual objects in XR overlaid on the user's environment, animating virtual objects, and / or other operations discussed herein. Powerful processors typically draw power at a high rate. Sending large amounts of data to powerful processors typically draws power at a high rate, and such systems typically capture large amounts of sensor data (e.g., images, positional data, and / or other sensor data) per second. Head-mounted devices and other portable devices typically have small batteries so as not to be uncomfortably heavy for the user. As a result, typical XR headsets either must be powered by an external power source, are uncomfortably heavy due to the large batteries they contain, or have very short battery life.

[0041] In some cases, cameras included in separate devices may concurrently capture images of the same scene. As used herein, separate devices that may concurrently capture a scene may include, but are not limited to, mobile or fixed telephone handsets (e.g., smartphones, cellular phones, etc.), desktop computers, laptop or notebook computers, tablet computers, set-top boxes, televisions, cameras, display devices, digital media players, video game consoles, video streaming devices, Internet Protocol (IP) cameras, or any other suitable electronic device.

[0042] For example, a first camera included in a first device (e.g., a head-mounted XR device) can concurrently capture images of a scene with a second camera included in a separate second device (e.g., a mobile device) (e.g., as part of a VSLAM operation). In some examples, the first and second devices can move relative to each other while capturing images of the scene. For example, a user can turn their head to focus on a particular object in the scene. As another example, a user can reposition the mobile device in 6DoF to maintain and / or adjust the position of an object or event of interest within the scene. In some cases, the different positions of the first and second cameras can result in different perspectives (e.g., depth of field, field of view (FOV)), etc.) of the captured scene. Additionally, the first and second cameras can have different camera sensor characteristics (e.g., resolution, sensor design, sensor technology, etc.), different lens characteristics, and / or other differences that may affect the image of the scene. In some cases, the resulting images from the different cameras can have different image properties, including, but not limited to, resolution, brightness, white balance, color balance, focus, depth of field, FOV, distortion, and / or any other image properties. In some cases, it can be beneficial to combine the images of the scene captured by the first and second cameras into a combined image that provides a unique perspective of the scene.

[0043] In some cases, it may be preferable for a combined image captured by two (or more) cameras (e.g., cameras in separate devices) to have the appearance of being captured by a single camera. For example, the combined image may have the appearance of being captured entirely from the position of a camera in a head-mounted device (HMD). In another example, the combined image may have the appearance of being captured from the position of a mobile device (e.g., held in a user's hand). In some examples, the combined image may have the appearance of being captured from a novel viewpoint that is different from the viewpoint of each of the separate devices contributing to the combined image.

[0044] In some cases, combining images captured by two different cameras may include one or more steps for creating a combined image. In some cases, combining the images may include coordinating the different perspectives of the camera systems. For example, a camera on an HMD may be positioned higher and further away from the scene than a camera included in a mobile device (e.g., when the mobile device is held in front of the HMD wearer at below head height). In some cases, the two devices may move relative to each other. In some cases, this change in position may be dynamic. For example, during scene capture, the HMD, the mobile device, and / or both may change pose as the user's head and / or hands move. In some cases, the HMD and / or mobile device may perform 6DoF tracking (e.g., using a camera, accelerometer, gyroscope, IMU, and / or any combination thereof). As used herein, view synthesis refers to the process of combining images originally captured from different perspectives to generate a combined image that appears to be captured from a single perspective. In some cases, view synthesis can generate a combined image that appears to be captured from the original perspective of one of the original images. In some examples, view synthesis can generate a combined image that differs from the original perspective of any of the original images.

[0045] In some cases, the HMD and the mobile device can exchange (e.g., via wired or wireless communication) positioning information. The positioning information can include, but is not limited to, SLAM maps, sensor measurements (e.g., from a LIDAR sensor, a RADAR sensor, a SODAR sensor, a SONAR sensor, an audio sensor, an inertial sensor, and / or any other sensor), images, feature vectors, and the like. In some examples, the HMD, the mobile device, and / or both can determine relative pose information based on positioning information from only one of the devices. In some examples, the HMD, the mobile device, and / or both can determine relative pose information based on a combination of positioning information captured by both devices.

[0046] In one illustrative example, the HMD may determine the positioning (e.g., relative position, relative pose, etc.) between the HMD and the mobile device based on images captured by the HMD's camera (and / or other sensors) (e.g., determining relative position and relative pose information of the HMD and the mobile device). In another illustrative example, the HMD may send the images (and / or other sensor measurements) to the mobile device (e.g., via wired or wireless communication), and the mobile device may determine the positioning between the HMD and the mobile device.

[0047] In some cases, the relative position (or relative pose) of the HMD and the mobile device can change dynamically during the capture of the image sequence. In some cases, view synthesis can include updating the positioning (e.g., relative pose) between the HMD and the mobile device and dynamically adapting to the change in positioning as part of view synthesis.

[0048] In some aspects, an image of a scene captured by a camera of an HMD may be obstructed by a mobile device, a human body part (e.g., an arm, a hand, etc.), or a mechanical fixture (e.g., a tripod, a telescopic mounting structure, a gimbal system, etc.). In some cases, generating a combined image may include identifying and / or removing obstructions (also referred to herein as occlusions) from one or both images. In some cases, identifying and / or removing obstructions may include at least one or more of segmentation, feature extraction, inpainting, alpha blending, and the like.

[0049] In some examples, generating the combined image may include image normalization (e.g., to account for differences in properties of images captured by different cameras, such as resolution, brightness, white balance, color balance, focus, depth of field, FOV, distortion, and / or any other image properties). In some cases, generating the combined image may include additional image fusion techniques to generate the combined image.

[0050] As described in greater detail herein, systems, apparatuses, methods (also referred to as processes), and computer-readable media (collectively referred to herein as the "systems and techniques") are described for generating a combined image based on two or more input images captured by image sensors of separate devices (e.g., a camera included in an HMD and a camera included in a mobile device). In some cases, the systems and techniques can remove one or more obstructions (e.g., a mobile device, a user's hand, a mechanical fixture) from one or more of the input images. In some cases, the image capture devices providing the input images can be housed in separate housings. In some examples, the image capture devices may not be rigidly physically attached, such that their relative positions (or poses) vary between images captured at different times. For example, the relative positions (or poses) can vary between snapshots captured at different times. In another illustrative example, the relative positions (or poses) can change dynamically during an image capture sequence (e.g., capturing a video). In some examples, the systems and techniques can obtain positioning information from one or more of the devices. In some cases, the systems and techniques can generate an image with a novel viewpoint based on the input images and the positioning image. In some cases, the novel viewpoint can correspond to the viewpoint of one of the input devices. In one illustrative example, systems and techniques can combine images from an HMD with images from a mobile device and generate an image from the mobile device's viewpoint. In one illustrative example, systems and techniques can combine images from an HMD with images from a mobile device and generate an image from the HMD's viewpoint.

[0051] In some cases, systems and techniques for generating a combined image based on two or more input images may employ one or more machine learning (ML) systems.

[0052] ML is a subset of artificial intelligence (AI). ML systems include algorithms and statistical models that computer systems can use to perform various tasks without explicit instructions by relying on patterns and inferences. An example of an ML system is a neural network (also known as an artificial neural network), which can be composed of a set of interconnected artificial neurons (e.g., a neuron model). Neural networks can be used in a variety of applications and / or devices, such as image analysis and / or computer vision applications, Internet Protocol (IP) cameras, Internet of Things (IoT) devices, autonomous vehicles, service robots, and more.

[0053] Individual nodes in a neural network can simulate biological neurons by taking input data and performing simple operations on the data. The results of the simple operations performed on the input data are selectively passed to other neurons. Weight values ​​are associated with each vector and node in the network, and these values ​​constrain how the input data is related to the output data. For example, the input data for each node can be multiplied by the corresponding weight value, and the products can be summed. The sum of products can be adjusted by an optional bias, and an activation function can be applied to the result, resulting in the node's output signal or "output activation" (sometimes called an activation map or feature map). The weight values ​​can initially be determined by iteratively flowing training data through the network (for example, weight values ​​are established during a training phase in which the network learns how to identify specific categories by their typical input data characteristics).

[0054] There are different types of neural networks, such as deep generative neural network models (e.g., generative adversarial networks (GANs), recurrent neural network (RNN) models, multilayer perceptrons (MLPs), and deep neural network models. Perceptron (MLP) neural network models, convolutional neural network (CNN) models, and so on. A GAN is a form of generative neural network that can learn patterns in input data, enabling the neural network model to generate new, synthetic outputs that are reasonably likely to have come from the original dataset. A GAN can consist of two neural networks operating together. One of the neural networks (called the generative neural network or generator, denoted G(z)) generates the synthesized output, while the other (called the discriminative neural network or discriminator, denoted D(x)) evaluates the authenticity of the output (whether it comes from the original dataset, such as the training dataset, or is generated by the generator). As an illustrative example, the training input and output can include images. The generator is trained to try and trick the discriminator into determining that the synthesized images generated by the generator are real images from the dataset. As the training process continues, the generator becomes better at generating synthesized images that look like real images. The discriminator continues to discover flaws in the synthesized images, and the generator figures out what the discriminator is looking at to determine the flaws. Once the network is trained, the generator is able to produce realistic-looking images that the discriminator cannot distinguish from real images.

[0055] RNNs work by saving the output of a layer and feeding that output back into the input to help predict the layer's outcome. In an MLP neural network, data can be fed into the input layer, and one or more hidden layers provide levels of abstraction for the data. Predictions can then be made at the output layer based on the abstracted data. MLPs may be particularly well-suited for classification prediction problems where inputs are assigned categories or labels. A convolutional neural network (CNN) is a type of feedforward artificial neural network. A CNN can include a collection of artificial neurons, each with a receptive field (e.g., a spatially local region of the input space) that collectively tile the input space. CNNs have many applications, including pattern recognition and classification.

[0056] In a layered neural network architecture (called a deep neural network when there are multiple hidden layers), the output of the first artificial neuron layer becomes the input to the second artificial neuron layer, the output of the second artificial neuron layer becomes the input to the third artificial neuron layer, and so on. Convolutional neural networks can be trained to recognize hierarchies of features. Computation in a convolutional neural network architecture can be distributed across a cluster of processing nodes, which can be configured in one or more computational chains. These multi-layer architectures can be trained one layer at a time and can be fine-tuned using backpropagation.

[0057] Various aspects of the application will be described with respect to the accompanying drawings. Figure 1 is a block diagram illustrating the architecture of image capture and processing system 100. Image capture and processing system 100 includes various components for capturing and processing images of a scene (e.g., images of scene 110). Image capture and processing system 100 can capture individual images (or photographs) and / or can capture videos comprising multiple images (or video frames) in a particular sequence. In some cases, lens 115 and image sensor 130 may be associated with an optical axis. In one illustrative example, the photosensitive area (e.g., photodiode) of image sensor 130 and lens 115 may both be aligned centered about the optical axis. Lens 115 of image capture and processing system 100 faces scene 110 and receives light from scene 110. Lens 115 deflects incident light from the scene toward image sensor 130. Light received by lens 115 passes through an aperture. In some cases, the aperture (e.g., aperture size) is controlled by one or more control mechanisms 120 and received by image sensor 130. In some cases, the aperture may have a fixed size.

[0058] The one or more control mechanisms 120 may control exposure, focus, and / or zoom based on information from the image sensor 130 and / or based on information from the image processor 150. The one or more control mechanisms 120 may include a plurality of mechanisms and components; for example, the one or more control mechanisms 120 may include one or more exposure control mechanisms 125A, one or more focus control mechanisms 125B, and / or one or more zoom control mechanisms 125C. The one or more control mechanisms 120 may also include additional control mechanisms in addition to those shown, such as controls for analog gain, flash, HDR, depth of field, and / or other image capture properties.

[0059] Focus control mechanism 125B of control mechanism 120 can obtain a focus setting. In some examples, focus control mechanism 125B stores the focus setting in a memory register. Based on the focus setting, focus control mechanism 125B can adjust the position of lens 115 relative to the position of image sensor 130. For example, based on the focus setting, focus control mechanism 125B can move lens 115 closer to or further away from image sensor 130 by actuating a motor or servo (or other lens mechanism), thereby adjusting the focus. In some cases, additional lenses can be included in image capture and processing system 100, such as one or more microlenses on each photodiode of image sensor 130, each of the one or more microlenses deflecting light received from lens 115 toward the corresponding photodiode before the light reaches the photodiode. The focus setting may be determined via contrast detection autofocus (CDAF), phase detection autofocus (PDAF), hybrid autofocus (HAF), or some combination thereof. The focus setting may be determined using control mechanism 120, image sensor 130, and / or image processor 150. The focus setting may be referred to as an image capture setting and / or an image processing setting. In some cases, lens 115 may be fixed relative to the image sensor, and focus control mechanism 125B may be omitted without departing from the scope of the present disclosure.

[0060] Exposure control mechanism 125A of control mechanism 120 may obtain an exposure setting. In some cases, exposure control mechanism 125A stores the exposure setting in a memory register. Based on the exposure setting, exposure control mechanism 125A may control the size of the aperture (e.g., aperture size or f-number (f / stop)), the duration that the aperture is open (e.g., exposure time or shutter speed), the duration that the sensor collects light (e.g., exposure time or electronic shutter speed), the sensitivity of image sensor 130 (e.g., ISO speed or film speed), the analog gain applied by image sensor 130, or any combination thereof. The exposure setting may be referred to as an image capture setting and / or an image processing setting.

[0061] Zoom control mechanism 125C of control mechanism 120 can obtain a zoom setting. In some examples, zoom control mechanism 125C stores the zoom setting in a memory register. Based on the zoom setting, zoom control mechanism 125C can control the focal length of an assembly of lens elements (lens assembly) including lens 115 and one or more additional lenses. For example, zoom control mechanism 125C can control the focal length of the lens assembly by actuating one or more motors or servo mechanisms (or other lens mechanisms) to move one or more of the lenses relative to each other. The zoom setting can be referred to as an image capture setting and / or an image processing setting. In some examples, the lens assembly can include a parfocal zoom lens or a varifocal zoom lens. In some examples, the lens assembly may include a focus lens (which in some cases may be lens 115) that first receives light from scene 110. The light then passes through an afocal zoom system between the focus lens (e.g., lens 115) and image sensor 130 before reaching image sensor 130. In some cases, the afocal zoom system may include two positive (e.g., converging, convex) lenses with equal or similar focal lengths (e.g., within a threshold difference of each other), with a negative (e.g., diverging, concave) lens between them. In some cases, zoom control mechanism 125C moves one or more lenses in the afocal zoom system, such as a negative lens and one or two positive lenses. In some cases, zoom control mechanism 125C may control zoom by capturing images from an image sensor in a plurality of image sensors (e.g., including image sensor 130) at a zoom corresponding to a zoom setting. For example, image processing system 100 may include a wide-angle image sensor with relatively low zoom and a telephoto image sensor with greater zoom. In some cases, based on the selected zoom setting, zoom control mechanism 125C may capture an image from the corresponding sensor.

[0062] Image sensor 130 includes one or more arrays of photodiodes or other photosensitive elements. Each photodiode measures the amount of light that ultimately corresponds to a specific pixel in the image generated by image sensor 130. In some cases, different photodiodes may be covered with different filters. In some cases, different photodiodes may be covered with color filters and, therefore, may measure light that matches the color of the filter covering the photodiode. Various color filter arrays may be used, including a Bayer color filter array, a quad color filter array (also known as a quad Bayer color filter array or QCFA), and / or any other color filter array. For example, a Bayer color filter includes a red filter, a blue filter, and a green filter, where each pixel of the image is generated based on red light data from at least one photodiode covered with a red filter, blue light data from at least one photodiode covered with a blue filter, and green light data from at least one photodiode covered with a green filter.

[0063] Return to Figure 1 Other types of color filters may include yellow, magenta, and / or cyan (also known as "emerald") filters, instead of or in addition to red, blue, and / or green filters. In some cases, some photodiodes may be configured to measure infrared (IR) light. In some embodiments, the photodiodes measuring IR light may not be covered by any filters, thereby allowing the IR photodiodes to measure both visible (e.g., color) and IR light. In some examples, the IR photodiodes may be covered by IR filters, allowing IR light to pass through while blocking light from other parts of the spectrum (e.g., visible, color). Some image sensors (e.g., image sensor 130) may lack filters entirely (e.g., color, IR, or any other part of the spectrum) and may instead use different photodiodes (in some cases stacked vertically) throughout the pixel array. Different photodiodes throughout the pixel array may have different spectral sensitivity curves and therefore respond to different wavelengths of light. Monochrome image sensors may also lack filters and, therefore, lack color depth.

[0064] In some cases, image sensor 130 may alternatively or additionally include an opaque and / or reflective mask that blocks light from reaching certain photodiodes or portions of certain photodiodes at certain times and / or from certain angles. In some cases, the opaque and / or reflective mask may be used for phase detection autofocus (PDAF). In some cases, the opaque and / or reflective mask may be used to block portions of the electromagnetic spectrum from reaching the image sensor's photodiodes (e.g., an IR cut filter, a UV cut filter, a bandpass filter, a low-pass filter, a high-pass filter, etc.). Image sensor 130 may also include an analog gain amplifier for amplifying the analog signal output by the photodiode and / or an analog-to-digital converter (ADC) for converting the analog signal output by the photodiode (and / or amplified by the analog gain amplifier) ​​into a digital signal. In some cases, certain components or functionality discussed with respect to one or more of control mechanism 120 may alternatively or additionally be included in image sensor 130. The image sensor 130 may be a charge-coupled device (CCD) sensor, an electron-multiplying CCD (EMCCD) sensor, an active pixel sensor (APS), a complementary metal-oxide semiconductor (CMOS), an N-type metal-oxide semiconductor (NMOS), a hybrid CCD / CMOS sensor (e.g., sCMOS), or some other combination thereof.

[0065] The image processor 150 may include one or more processors, such as one or more image signal processors (ISPs) (including ISP 154), one or more host processors (including host processor 152), and / or related Figure 13Host processor 152 may be a digital signal processor (DSP) and / or other types of processors discussed above. In some embodiments, image processor 150 is a single integrated circuit or chip (e.g., referred to as a system on a chip or SoC) that includes host processor 152 and ISP 154. In some cases, the chip may also include one or more input / output ports (e.g., input / output (I / O) port 156), a central processing unit (CPU), a graphics processing unit (GPU), a broadband modem (e.g., 3G, 4G or LTE, 5G, etc.), memory, connectivity components (e.g., Bluetooth™, Global Positioning System (GPS), etc.), any combination thereof, and / or other components. The I / O ports 156 may include any suitable input / output ports or interfaces according to one or more protocols or specifications, such as an Inter-Integrated Circuit 2 (I2C) interface, an Inter-Integrated Circuit 3 (I3C) interface, a Serial Peripheral Interface (SPI) interface, a serial General Purpose Input / Output (GPIO) interface, a Mobile Industry Processor Interface (MIPI) (such as a MIPI CSI-2 physical (PHY) layer port or interface), an Advanced High-Performance Bus (AHB) bus, any combination thereof, and / or other input / output ports. In one illustrative example, the host processor 152 may communicate with the image sensor 130 using an I2C port, and the ISP 154 may communicate with the image sensor 130 using a MIPI port.

[0066] The image processor 150 may perform a number of tasks, such as demosaicing, color space conversion, image frame downsampling, pixel interpolation, automatic exposure (AE) control, automatic gain control (AGC), CDAF, PDAF, automatic white balance, merging image frames to form an HDR image, image recognition, object recognition, feature recognition, receiving input, managing output, managing memory, or some combination thereof. The image processor 150 may store image frames and / or processed images in a random access memory (RAM) 140 / 1325, a read-only memory (ROM) 145 / 1320, a cache, a memory unit, other storage devices, or some combination thereof.

[0067] Various input / output (I / O) devices 160 can be connected to the image processor 150. The I / O devices 160 can include a display screen, a keyboard, a keypad, a touch screen, a trackpad, a touch-sensitive surface, a printer, any other output device 1335, any other input device 1345, or some combination thereof. In some cases, subtitles can be entered into the image processing device 105B via a physical keyboard or keypad of the I / O device 160 or via a virtual keyboard or keypad of the touch screen of the I / O device 160. The I / O 160 can include one or more ports, sockets, or other connectors that enable wired connections between the image capture and processing system 100 and one or more peripheral devices, over which the image capture and processing system 100 can receive data from and / or send data to the one or more peripheral devices. The I / O 160 can also include one or more wireless transceivers that enable wireless connections between the image capture and processing system 100 and one or more peripheral devices, over which the image capture and processing system 100 can receive data from and / or send data to the one or more peripheral devices. Peripheral devices may include any of the previously discussed types of I / O devices 160 , and may themselves be considered I / O devices 160 once they are coupled to a port, receptacle, wireless transceiver, or other wired and / or wireless connector.

[0068] In some cases, image capture and processing system 100 can be a single device. In some cases, image capture and processing system 100 can be two or more separate devices, including image capture device 105A (e.g., a camera) and image processing device 105B (e.g., a computing device coupled to the camera). In some embodiments, image capture device 105A and image processing device 105B can be coupled together wirelessly, for example, via one or more wires, cables, or other electrical connectors and / or via one or more wireless transceivers. In some embodiments, image capture device 105A and image processing device 105B can be disconnected from each other.

[0069] like Figure 1 As shown, the vertical dotted line will Figure 11. The image capture and processing system 100 is divided into two parts, representing image capture device 105A and image processing device 105B. Image capture device 105A includes lens 115, control mechanism 120, and image sensor 130. Image processing device 105B includes image processor 150 (including ISP 154 and host processor 152), RAM 140, ROM 145, and I / O 160. In some cases, some components shown in image processing device 105B (such as ISP 154 and / or host processor 152) may be included in image capture device 105A.

[0070] The image capture and processing system 100 may include an electronic device, such as a mobile or fixed telephone handset (e.g., a smartphone, a cell phone, etc.), a desktop computer, a laptop or notebook computer, a tablet computer, a set-top box, a television, a camera, a display device, a digital media player, a video game console, a video streaming device, an Internet Protocol (IP) camera, or any other suitable electronic device. In some examples, the image capture and processing system 100 may include one or more wireless transceivers for wireless communication, such as cellular network communication, 1002.11 Wi-Fi communication, wireless local area network (WLAN) communication, or some combination thereof. In some embodiments, the image capture device 105A and the image processing device 105B may be different devices. For example, the image capture device 105A may include a camera device, and the image processing device 105B may include a computing device, such as a mobile handset, a desktop computer, or other computing device.

[0071] Although the image capture and processing system 100 is shown as including certain components, one of ordinary skill will understand that the image capture and processing system 100 may include more than Figure 1 . In some cases, the image capture and processing system 100 may include software, hardware, or one or more combinations of software and hardware. For example, in some embodiments, components of the image capture and processing system 100 may include and / or be implemented using electronic circuits or other electronic hardware, which may include one or more programmable electronic circuits (e.g., microprocessors, GPUs, DSPs, CPUs, and / or other suitable electronic circuits), and / or may include and / or be implemented using computer software, firmware, or any combination thereof to perform the various operations described herein. The software and / or firmware may include one or more instructions stored on a computer-readable storage medium and executable by one or more processors of an electronic device that implements the image capture and processing system 100.

[0072] In some examples, Figure 2 In some examples, the extended reality (XR) system 200 may include the image capture and processing system 100, the image capture device 105A, the image processing device 105B, or a combination thereof. Figure 3 The simultaneous localization and mapping (SLAM) system 300 may include the image capture and processing system 100, the image capture device 105A, the image processing device 105B, or a combination thereof.

[0073] Figure 2 2 is a diagram illustrating the architecture of an example extended reality (XR) system 200, according to some aspects of the present disclosure. The XR system 200 can run (or execute) XR applications and implement XR operations. In some examples, the XR system 200 can perform tracking and positioning, mapping of an environment (e.g., a scene) in the physical world, and / or positioning and rendering of virtual content on a display 209 (e.g., a screen, visible plane / area, and / or other display) as part of an XR experience. For example, the XR system 200 can generate a map (e.g., a three-dimensional (3D) map) of the environment in the physical world, track the pose (e.g., position and positioning) of the XR system 200 relative to the environment (e.g., relative to the 3D map of the environment), position and / or anchor virtual content at a specific location on the map of the environment, and render the virtual content on the display 209 such that the virtual content appears to be located at a location in the environment corresponding to the specific location on the map of the scene where the virtual content is positioned and / or anchored. The display 209 may include glass, screens, lenses, projectors, and / or other display mechanisms that allow a user to see the real-world environment and also allow XR content to be overlaid, superimposed, blended, or otherwise displayed thereon.

[0074] In this illustrative example, XR system 200 includes one or more image sensors 202, accelerometer 204, gyroscope 206, storage 207, computing component 210, XR engine 220, image processing engine 224, rendering engine 226, and communication engine 228. It should be noted that Figure 2 The components 202-228 shown in FIG are non-limiting examples provided for purposes of illustration and explanation, and other examples may include, for example, Figure 2 For example, in some cases, the XR system 200 may include one or more other sensors (e.g., one or more inertial measurement units (IMUs), radars, light detection and ranging (LIDAR) sensors, radio detection and ranging (RADAR) sensors, sound detection and ranging (SODAR) sensors, sound navigation and ranging (SONAR) sensors, audio sensors, etc.), one or more display devices, one or more other processing engines, one or more other hardware components, and / or Figure 2While various components of XR system 200 (such as image sensor 202) may be referred to herein in the singular, it should be understood that XR system 200 may include multiple of any of the components discussed herein (e.g., multiple image sensors 202).

[0075] The XR system 200 includes or communicates (wired or wirelessly) with an input device 208. The input device 208 can include any suitable input device, such as a touch screen, a pen or other pointer device, a keyboard, a mouse, buttons or keys, a microphone for receiving voice commands, a gesture input device for receiving gesture commands, a video game controller, a steering wheel, a joystick, a collection of buttons, a trackball, a remote control, any other input device 1345 discussed herein, or any combination thereof. In some cases, the image sensor 202 can capture images that can be processed for interpreting gesture commands.

[0076] The XR system 200 may also communicate with one or more other electronic devices (wired or wireless). For example, the communication engine 228 may be configured to manage connections and communicate with one or more electronic devices. In some cases, the communication engine 228 may communicate with Figure 13 Corresponding to the communication interface 1340.

[0077] In some embodiments, one or more image sensors 202, accelerometer 204, gyroscope 206, storage 207, computing component 210, XR engine 220, image processing engine 224, and rendering engine 226 may be part of the same computing device. For example, in some cases, one or more image sensors 202, accelerometer 204, gyroscope 206, storage 207, computing component 210, XR engine 220, image processing engine 224, and rendering engine 226 may be integrated into an HMD, extended reality glasses, a smartphone, a laptop, a tablet, a gaming system, and / or any other computing device. However, in some embodiments, one or more image sensors 202, accelerometer 204, gyroscope 206, storage 207, computing component 210, XR engine 220, image processing engine 224, and rendering engine 226 may be part of two or more separate computing devices. For example, in some cases, some of the components 202 - 226 may be part of or implemented by one computing device, and the remaining components may be part of or implemented by one or more other computing devices.

[0078] Storage 207 can be any storage device for storing data. Furthermore, storage 207 can store data from any component of XR system 200. For example, storage 207 can store data from image sensor 202 (e.g., image or video data), data from accelerometer 204 (e.g., measurements), data from gyroscope 206 (e.g., measurements), data from compute component 210 (e.g., processing parameters, preferences, virtual content, rendered content, scene maps, tracking and positioning data, object detection data, privacy data, XR application data, facial recognition data, occlusion data, etc.), data from XR engine 220, data from image processing engine 224, and / or data from rendering engine 226 (e.g., output frames). In some examples, storage 207 can include a buffer for storing frames for processing by compute component 210.

[0079] One or more computing components 210 may include a central processing unit (CPU) 212, a graphics processing unit (GPU) 214, a digital signal processor (DSP) 216, an image signal processor (ISP) 218, and / or other processors (e.g., a neural processing unit (NPU) implementing one or more trained neural networks). Computing component 210 may perform various operations such as image enhancement, computer vision, graphics rendering, extended reality operations (e.g., tracking, localization, pose estimation, mapping, content anchoring, content rendering, etc.), image and / or video processing, sensor processing, recognition (e.g., text recognition, facial recognition, object recognition, feature recognition, tracking or pattern recognition, scene recognition, occlusion detection, etc.), trained machine learning operations, filtering, and / or any of the various operations described herein. In some examples, computing component 210 may implement (e.g., control, operate, etc.) an XR engine 220, an image processing engine 224, and a rendering engine 226. In other examples, computing component 210 may also implement one or more other processing engines.

[0080] Image sensor 202 can include any image and / or video sensor or capture device. In some examples, image sensor 202 can be part of a multi-camera assembly (such as a dual-camera assembly). Image sensor 202 can capture image and / or video content (e.g., raw image and / or video data), which can then be processed by compute component 210, XR engine 220, image processing engine 224, and / or rendering engine 226, as described herein. In some examples, image sensor 202 can include image capture and processing system 100, image capture device 105A, image processing device 105B, or a combination thereof.

[0081] In some examples, image sensor 202 can capture image data and can generate images (also referred to as frames) based on the image data and / or can provide the image data or frames to XR engine 220, image processing engine 224, and / or rendering engine 226 for processing. The images or frames can include video frames of a video sequence or still images. The images or frames can include an array of pixels representing a scene. For example, the images can be red-green-blue (RGB) images with red, green, and blue color components per pixel; luminance, chrominance-red, chrominance-blue (YCbCr) images with a luminance component and two chrominance (color) components (chrominance-red and chrominance-blue) per pixel; or any other suitable type of color or monochrome image.

[0082] In some cases, image sensor 202 (and / or other cameras of XR system 200) can be configured to also capture depth information. For example, in some embodiments, image sensor 202 (and / or other cameras) can include an RGB depth (RGB-D) camera. In some cases, XR system 200 can include one or more depth sensors (not shown) that are separate from image sensor 202 (and / or other cameras) and can capture depth information. For example, such a depth sensor can obtain depth information independently of image sensor 202. In some examples, the depth sensor can be physically mounted in the same general location as image sensor 202, but can operate at a different frequency or frame rate than image sensor 202. In some examples, the depth sensor can take the form of a light source that can project a structured or textured light pattern, which can include one or more narrow bands of light, onto one or more objects in the scene. Depth information can then be obtained by exploiting the geometric distortion of the projected pattern caused by the surface shape of the objects. In one example, depth information can be obtained from a stereo sensor, such as a combination of an infrared camera and an infrared structured light projector registered to a camera (e.g., an RGB camera).

[0083] XR system 200 may also include other sensors in its sensor(s). The sensor(s) may include one or more accelerometers (e.g., accelerometer 204), one or more gyroscopes (e.g., gyroscope 206), and / or other sensors. The sensor(s) may provide velocity, orientation, and / or other position-related information to computing component 210. For example, accelerometer 204 may detect acceleration of XR system 200 and may generate acceleration measurements based on the detected acceleration. In some cases, accelerometer 204 may provide one or more translation vectors (e.g., up / down, left / right, forward / backward) that may be used to determine the position or pose of XR system 200. Gyroscope 206 may detect and measure the orientation and angular velocity of XR system 200. For example, gyroscope 206 may be used to measure pitch, roll, and yaw of XR system 200. In some cases, gyroscope 206 may provide one or more rotation vectors (e.g., pitch, yaw, roll). In some examples, image sensor 202 and / or XR engine 220 can use measurements obtained by accelerometer 204 (e.g., one or more translation vectors) and / or gyroscope 206 (e.g., one or more rotation vectors) to calculate the pose of XR system 200. As described above, in other examples, XR system 200 can also include other sensors, such as an inertial measurement unit (IMU), a magnetometer, gaze and / or eye tracking sensors, machine vision sensors, smart scene sensors, voice recognition sensors, impact sensors, vibration sensors, position sensors, tilt sensors, and the like.

[0084] As described above, in some cases, the one or more sensors may include at least one IMU. An IMU is an electronic device that uses a combination of one or more accelerometers, one or more gyroscopes, and / or one or more magnetometers to measure specific forces, angular rates, and / or orientations of XR system 200. In some examples, the one or more sensors may output measurement information associated with the capture of images captured by image sensor 202 (and / or other cameras of XR system 200) and / or depth information obtained using one or more depth sensors of XR system 200.

[0085] XR engine 220 can use the output of one or more sensors (e.g., accelerometer 204, gyroscope 206, one or more IMUs, and / or other sensors) to determine the pose (also known as head pose) of XR system 200 and / or the pose of image sensor 202 (or other cameras of XR system 200). In some cases, the pose of XR system 200 and the pose of image sensor 202 (or other cameras) can be the same. The pose of image sensor 202 refers to the position and orientation of image sensor 202 relative to a reference frame (e.g., with respect to scene 110). In some embodiments, the camera pose can be determined for six degrees of freedom (6DoF), which refers to three translational components (e.g., which can be given by X (horizontal), Y (vertical), and Z (depth) coordinates relative to a reference frame such as an image plane) and three angular components (e.g., roll, pitch, and yaw relative to the same reference frame). In some implementations, the camera pose may be determined for 3 degrees of freedom (3DoF), which refers to three angular components (eg, roll, pitch, and yaw).

[0086] In some cases, a device tracker (not shown) can use measurements from one or more sensors and image data from image sensor 202 to track the pose (e.g., a 6DoF pose) of XR system 200. For example, the device tracker can fuse visual data from the image data (e.g., using a visual tracking solution) with inertial data from the measurements to determine the position and motion of XR system 200 relative to the physical world (e.g., a scene) and a map of the physical world. As described below, in some examples, while tracking the pose of XR system 200, the device tracker can generate a three-dimensional (3D) map of the scene (e.g., the real world) and / or generate updates to the 3D map of the scene. 3D map updates can include, for example, but not limited to, new or updated features and / or features or landmarks associated with the scene and / or the 3D map of the scene, positioning updates that identify or update the position of XR system 200 within the scene and the 3D map of the scene, and the like. The 3D map can provide a digital representation of the scene in the real / physical world. In some examples, a 3D map can anchor location-based objects and / or content to real-world coordinates and / or objects. The XR system 200 can use a mapped scene (e.g., a scene in the physical world represented by and / or associated with a 3D map) to merge the physical and virtual worlds and / or merge virtual content or objects with the physical environment.

[0087] In some aspects, a visual tracking solution may be used by computing component 210 to determine and / or track the pose of image sensor 202 and / or XR system 200 as a whole based on images captured by image sensor 202 (and / or other cameras of XR system 200). For example, in some examples, computing component 210 may perform tracking using computer vision-based tracking, model-based tracking, and / or simultaneous localization and mapping (SLAM) techniques. For example, computing component 210 may perform SLAM or may be integrated with a SLAM system such as Figure 3 SLAM refers to a class of technologies in which a map of an environment (e.g., a map of the environment modeled by XR system 200) is created while simultaneously tracking the pose of a camera (e.g., image sensor 202) and / or XR system 200 relative to the map. The map may be referred to as a SLAM map and may be three-dimensional (3D). SLAM techniques may be performed using color or grayscale image data captured by image sensor 202 (and / or other cameras of XR system 200) and may be used to generate an estimate of 6DoF pose measurements of image sensor 202 and / or XR system 200. Such SLAM techniques configured to perform 6DoF tracking may be referred to as 6DoF SLAM. In some cases, the output of one or more sensors (e.g., accelerometer 204, gyroscope 206, one or more IMUs, and / or other sensors) may be used to estimate, correct, and / or otherwise adjust the estimated pose.

[0088] In some cases, 6DoF SLAM (e.g., 6DoF tracking) can associate features observed from certain input images from image sensor 202 (and / or other cameras) with a SLAM map. For example, 6DoF SLAM can use feature point associations from the input images to determine the pose (position and orientation) of image sensor 202 and / or XR system 200 for the input images. 6DoF map building can also be performed to update the SLAM map. In some cases, the SLAM map maintained using 6DoF SLAM can contain 3D feature points triangulated from two or more images. For example, keyframes can be selected from the input images or video stream to represent the observed scene. For each keyframe, a corresponding 6DoF camera pose associated with the image can be determined. The pose of image sensor 202 and / or XR system 200 can be determined by projecting features from the 3D SLAM map into the images or video frames and updating the camera pose based on verified 2D-3D correspondences.

[0089] In one illustrative example, the computing component 210 may extract feature points from certain input images (e.g., each input image, a subset of the input images, etc.) or from each keyframe. As used herein, a feature point (also known as a registration point) is a unique or identifiable portion of an image, such as a portion of a hand, the edge of a table, etc. The features extracted from the captured image may represent unique feature points along three-dimensional space (e.g., coordinates on the X, Y, and Z axes), and each feature point may have an associated feature location. Feature points in a keyframe may match (be identical to or correspond to) or fail to match feature points from a previously captured input image or keyframe. Feature detection may be used to detect feature points. Feature detection may include image processing operations that examine one or more pixels of an image to determine whether a feature exists at a particular pixel. Feature detection may be applied to the entire captured image or to portions of an image. For each image or keyframe, once a feature is detected, a local image patch surrounding the feature may be extracted. Features may be extracted using any suitable technique, such as Scale Invariant Feature Transform (SIFT) (which locates features and generates descriptions of the features), Learned Invariant Feature Transform (LIFT), Speed ​​Up Robust Feature (SURF), Gradient Location-Orientation histogram (GLOH), Oriented Fast and Rotated Brief (ORB), Binary Robust Invariant Scalable Keypoint (BRISK), Fast Retina Keypoint (FREAK), KAZE, Accelerated KAZE (AKAZE), Normalized Cross Correlation (NCC), descriptor matching, other suitable techniques, or combinations thereof.

[0090] In some cases, the XR system 200 may also track a user's hands and / or fingers to allow the user to interact with and / or control virtual content in the virtual environment. For example, the XR system 200 may track the pose and / or movement of the user's hands and / or fingertips to recognize or translate user interactions with the virtual environment. User interactions may include, for example, but are not limited to, moving virtual content items, resizing virtual content items, selecting input interface elements in a virtual user interface (e.g., a virtual representation of a mobile phone, a virtual keyboard, and / or other virtual interfaces), providing input through the virtual user interface, and the like.

[0091] Figure 3 is a block diagram illustrating the architecture of a simultaneous localization and mapping (SLAM) system 300. In some examples, the SLAM system 300 may be or may include an extended reality (XR) system, such as Figure 2 In some examples, the SLAM system 300 can be a wireless communication device, a mobile device or handheld device (e.g., a mobile phone or so-called "smartphone" or other mobile device), a wearable device, a personal computer, a laptop computer, a server computer, a portable video game console, a portable media player, a camera device, a manned or unmanned ground vehicle, a manned or unmanned aerial vehicle, a manned or unmanned water vehicle, a manned or unmanned underwater vehicle, a manned or unmanned vehicle, an autonomous vehicle, a vehicle, a computing system of a vehicle, a robot, other devices, or any combination thereof.

[0092] Figure 3 The SLAM system 300 includes or is coupled to each of one or more sensors 305. The one or more sensors 305 may include one or more cameras 310. Each of the one or more cameras 310 may include an image capture device 105A, an image processing device 105B, an image capture and processing system 100, another type of camera, or a combination thereof. Each of the one or more cameras 310 may be responsive to light from a particular spectrum. The spectrum may be a subset of the electromagnetic (EM) spectrum. For example, each of the one or more cameras 310 may be a VL camera responsive to the visible light (VL) spectrum, an infrared (IR) camera responsive to the IR spectrum, an ultraviolet (UV) camera responsive to light from other spectrums in other parts of the EM spectrum, or some combination thereof.

[0093] The one or more sensors 305 may include one or more other types of sensors in addition to the camera 310, such as one or more of each of the following: an accelerometer, a gyroscope, a magnetometer, an inertial measurement unit (IMU), an altimeter, a barometer, a thermometer, a radio detection and ranging (RADAR) sensor, a light detection and ranging (LIDAR) sensor, a sound navigation and ranging (SONAR) sensor, a sound detection and ranging (SODAR) sensor, a global navigation satellite system (GNSS) receiver, a global positioning system (GPS) receiver, a BeiDou navigation satellite system (BDS) receiver, a Galileo receiver, a global navigation satellite system (GLONASS) receiver, a Navigation Indian Constellation (NavIC) receiver, a Quasi-Zenith Satellite System (QZSS) receiver, a Wi-Fi positioning system (Wi-Fi positioning system) receiver, a GPS receiver, a BeiDou navigation satellite system (BDS) receiver, a Galileo receiver, a GLONASS ... system (WPS) receiver, cellular network positioning system receiver, Bluetooth® beacon positioning receiver, short-range wireless beacon positioning receiver, Personal Area Network (PAN) positioning receiver, Wide Area Network (WAN) positioning receiver, Wireless Local Area Network (WLAN) positioning receiver, other types of positioning receivers, other types of sensors discussed herein, or combinations thereof. In some examples, the one or more sensors 305 may include Figure 2 Any combination of sensors of the XR System 200.

[0094] Figure 3 The SLAM system 300 includes a visual-inertial odometry (VIO) tracker 315. The term visual-inertial odometry may also be referred to herein as visual odometry. The VIO tracker 315 receives sensor data 365 from one or more sensors 305. For example, the sensor data 365 may include one or more images captured by one or more cameras 310. The sensor data 365 may include other types of sensor data from the one or more sensors 305, such as data from any of the types of sensors 305 listed herein. For example, the sensor data 365 may include inertial measurement unit (IMU) data from one or more sensors 305.

[0095] Upon receiving sensor data 365 from one or more sensors 305, the VIO tracker 315 uses the feature tracking engine 320 of the VIO tracker 315 to perform feature detection, extraction, and / or tracking. For example, where the sensor data 365 includes one or more images captured by one or more cameras 310 of the SLAM system 300, the VIO tracker 315 may identify, detect, and / or extract features in each image. Features may include visually significant points in an image, such as portions of an image that depict edges and / or corners. The VIO tracker 315 may periodically and / or continuously receive sensor data 365 from the one or more sensors 305, for example, by continuing to receive more images from the one or more cameras 310 as the one or more cameras 310 capture video, where the images are video frames of the video. The VIO tracker 315 may generate descriptors for the features. The feature descriptors may be generated, at least in part, by generating a description of the feature as depicted in a local image patch extracted around the feature. In some examples, the feature descriptors may describe the feature as a set of one or more feature vectors. In some cases, the VIO tracker 315, with its mapping engine 330 and / or relocalization engine 355, can associate multiple features with a map of the environment based on such feature descriptors. The feature tracking engine 320 of the VIO tracker 315 can perform feature tracking by identifying features in each image that the VIO tracker 315 has previously identified in one or more previous images, in some cases based on identifying features with matching feature descriptors in different images. The feature tracking engine 320 can track changes in one or more locations where a feature is depicted in each of the different images. For example, the feature extraction engine can detect a particular corner of a room depicted in the left side of a first image captured by a first camera of the camera 310. The feature extraction engine can detect the same feature (e.g., the same particular corner of the same room) depicted in the right side of a second image captured by the first camera. The feature tracking engine 320 can identify that the feature detected in the first image and the second image are two depictions of the same feature (e.g., the same particular corner of the same room), and that the feature appears in two different locations in the two images. The VIO tracker 315 may determine that the first camera has moved based on the same feature appearing on the left side of the first image and the right side of the second image, for example, if the feature (eg, a particular corner of a room) depicts a static portion of the environment.

[0096] VIO tracker 315 may include a sensor integration engine 325. Sensor integration engine 325 may use sensor data from other types of sensors 305 (in addition to camera 310) to determine information that can be used by feature tracking engine 320 when performing feature tracking. For example, sensor integration engine 325 may receive IMU data from the IMUs of one or more sensors 305 (e.g., which may be included as part of sensor data 365). Based on the IMU data in sensor data 365, sensor integration engine 325 may determine that SLAM system 300 has rotated 15 degrees clockwise from the time a first camera of camera 310 acquires or captures a first image to the time a second image is acquired or captured. Based on this determination, sensor integration engine 325 may identify that a feature depicted at a first location in the first image is expected to appear at a second location in the second image, and that the second location is expected to be a predetermined distance (e.g., a predetermined number of pixels, inches, centimeters, millimeters, or other distance metric) to the left of the first location. Feature tracking engine 320 may consider this expectation when tracking the feature between the first image and the second image.

[0097] Based on feature tracking by feature tracking engine 320 and / or sensor integration by sensor integration engine 325, VIO tracker 315 can determine a 3D feature location 372 for a particular feature. 3D feature location 372 can include one or more 3D feature locations and can also be referred to as a 3D feature point. 3D feature location 372 can be a set of coordinates along three different axes perpendicular to each other, such as an X-axis (e.g., horizontally), a Y-axis (e.g., vertically) perpendicular to the X-axis, and a Z-axis (e.g., depthwise) perpendicular to both the X-axis and the Y-axis. VIO tracker 315 can also determine one or more keyframes 370 (hereinafter referred to as keyframes 370) corresponding to the particular feature. In some examples, a keyframe (from one or more keyframes 370) corresponding to the particular feature can be an image in which the particular feature is clearly depicted. In some examples, a keyframe corresponding to a particular feature can be an image that reduces uncertainty in a 3D feature position 372 of the particular feature when considered by the feature tracking engine 320 and / or the sensor integration engine 325 for determining the 3D feature position 372. In some examples, a keyframe corresponding to a particular feature also includes data regarding a pose 385 of the SLAM system 300 and / or the camera 310 during the capture of the keyframe. In some examples, the VIO tracker 315 can send 3D feature positions 372 and / or keyframes 370 corresponding to one or more features to the mapping engine 330. In some examples, the VIO tracker 315 can receive a map slice 375 from the mapping engine 330. The VIO tracker 315 can use the feature tracking engine 320 to extract feature information within the map slice 375 for feature tracking.

[0098] Based on the feature tracking of the feature tracking engine 320 and / or the sensor integration of the sensor integration engine 325, the VIO tracker 315 can determine a pose 385 of the SLAM system 300 and / or the camera 310 during each of the images captured in the sensor data 365. The pose 385 can include the position of the SLAM system 300 and / or the camera 310 in 3D space, such as a set of coordinates along three different axes perpendicular to each other (e.g., an X coordinate, a Y coordinate, and a Z coordinate). The pose 385 can include the orientation of the SLAM system 300 and / or the camera 310 in 3D space, such as pitch, roll, yaw, or some combination thereof. In some examples, the VIO tracker 315 can send the pose 385 to the relocalization engine 355. In some examples, the VIO tracker 315 can receive the pose 385 from the relocalization engine 355.

[0099] The SLAM system 300 also includes a map building engine 330. The map building engine 330 generates a 3D map of the environment based on the 3D feature locations 372 and / or keyframes 370 received from the VIO tracker 315. The map building engine 330 may include a map densification engine 335, a keyframe remover 340, a bundle adjuster 345, and / or a loop closure detector 350. The map densification engine 335 may perform map densification, in some examples, increasing the number and / or density of 3D coordinates describing the map geometry. The keyframe remover 340 may remove keyframes and / or, in some cases, add keyframes. In some examples, the keyframe remover 340 may remove keyframes 370 corresponding to areas of the map to be updated and / or whose corresponding confidence values ​​are low. In some examples, the bundle adjuster 345 can refine the 3D coordinates describing the scene geometry, the parameters of relative motion, and / or the optical properties of the image sensor used to generate the frame based on an optimality criterion involving corresponding image projections of all points. The loop closure detector 350 can identify when the SLAM system 300 returns to a previously mapped area and can use this information to update a map slice and / or reduce uncertainty in certain 3D feature points or other points in the map geometry. The map building engine 330 can output a map slice 375 to the VIO tracker 315. The map slice 375 can represent a 3D portion or subset of the map. The map slice 375 can include a map slice 375 representing a new, previously unmapped area of ​​the map. The map slice 375 can also include a map slice 375 representing an update (or modification or revision) to a previously mapped area of ​​the map. The map building engine 330 can output map information 380 to the relocalization engine 355. Map information 380 may include at least a portion of a map generated by map building engine 330. Map information 380 may include one or more 3D points that make up the geometry of the map, such as one or more 3D feature locations 372. Map information 380 may include one or more keyframes 370 corresponding to certain features and certain 3D feature locations 372.

[0100] The SLAM system 300 also includes a relocalization engine 355. The relocalization engine 355 can perform relocalization, for example, when the VIO tracker 315 fails to identify more than a threshold number of features in an image and / or when the VIO tracker 315 loses track of the pose 385 of the SLAM system 300 within the map generated by the map building engine 330. The relocalization engine 355 can perform relocalization by performing extraction and matching using the extraction and matching engine 360. For example, the extraction and matching engine 360 ​​can extract features from an image captured by the camera 310 of the SLAM system 300 when the SLAM system 300 is in the current pose 385, and can match the extracted features to features depicted in different keyframes 370, identified by 3D feature locations 372, and / or identified in the map information 380. By matching these extracted features with previously identified features, the relocalization engine 355 can identify that the pose 385 of the SLAM system 300 is a pose 385 in which the previously identified features are visible to the camera 310 of the SLAM system 300, and is therefore similar to one or more previous poses 385 in which the previously identified features are visible to the camera 310. In some cases, the relocalization engine 355 can perform relocalization based on wide baseline mapping or the distance between the current camera position and the camera position that originally captured the features. The relocalization engine 355 can receive information about the pose 385 from the VIO tracker 315, such as information about one or more recent poses of the SLAM system 300 and / or camera 310, and the relocalization engine 355 can base its relocalization determination on this information. Once the relocalization engine 355 relocalizes the SLAM system 300 and / or camera 310 and determines the pose 385 accordingly, the relocalization engine 355 can output the pose 385 to the VIO tracker 315.

[0101] In some examples, the VIO tracker 315 may modify the image in the sensor data 365 before performing feature detection, extraction, and / or tracking on the modified image. For example, the VIO tracker 315 may rescale and / or resample the image. In some examples, rescaling and / or resampling the image may include downscaling, downsampling, subscaling, and / or subsampling the image one or more times. In some examples, the VIO tracker 315 modifying the image may include converting the image from color to grayscale, or from color to black and white, for example, by desaturating the colors in the image, stripping certain color channels, reducing the color depth in the image, replacing the colors in the image, or a combination thereof. In some examples, the VIO tracker 315 modifying the image may include the VIO tracker 315 masking certain areas of the image. Dynamic objects may include objects that may have an appearance that changes between one image and another. For example, a dynamic object may be an object that moves within an environment, such as a person, a vehicle, or an animal. A dynamic object may be an object that has an appearance that changes at different times, such as a display screen that may display different things at different times. A dynamic object can be an object that has a changing appearance based on the pose of the camera 310, such as a reflective surface, prism, or mirror that reflects, refracts, and / or scatters light differently depending on the position of the camera 310 relative to the dynamic object. The VIO tracker 315 can detect dynamic objects using facial detection, facial recognition, facial tracking, object detection, object recognition, object tracking, or a combination thereof. The VIO tracker 315 can detect dynamic objects using one or more artificial intelligence algorithms, one or more trained machine learning models, one or more trained neural networks, or a combination thereof. The VIO tracker 315 can mask one or more dynamic objects in an image by overlaying a mask over an area of ​​the image that includes a depiction of the one or more dynamic objects. The mask can be an opaque color, such as black. The area can be a bounding box having a rectangular or other polygonal shape. The area can be determined pixel by pixel.

[0102] Figures 4A to 4E An example spatial alignment transform (SAT) of an image according to some aspects is shown. In particular, Figure 4A The front side of device 400 is shown configured to display an image from a display based on scene 410 . Figure 4B Shown is the back side of device 400 and lens array 420 having ultra-wide angle lens 422, wide angle lens 424, and telephoto lens 426. Ultra-wide angle lens 422, wide angle lens 424, and telephoto lens 426 are all planar and point in parallel directions, but each has a different center point and a different FOV.

[0103] Return Reference Figure 4A, ultra-wide-angle lens 422 has FOV 430 and has a center point 432. Wide-angle lens 424 has a larger FOV 440 that includes all of FOV 430 of ultra-wide-angle lens 422 and has a center point 442 that is offset to the right of center point 432 of ultra-wide-angle lens 422. When the back surface of device 400 points lens array 420 at scene 410, wide-angle lens 424 will be located to the left of ultra-wide-angle lens 422. The location of the center point is based on the orientation of device 400 and can be offset to the left, right, up, or down.

[0104] In some aspects, device 400 is configured to modify the image captured from wide-angle lens 424 to correspond to FOV 430. For example, device 400 can crop the image from wide-angle lens 424 to be substantially equal to FOV 430 as perceived by ultra-wide-angle lens 422. Other types of corrections may be required to reduce the effects associated with the different lenses, such as correction of some distortion, or other processing required to make the image from wide-angle lens 424 substantially the same as the scene perceived by ultra-wide-angle lens 422. In some cases, there may be various differences, such as color balance, slight changes in image quality, etc., but these effects may be minimal compared to freezing the image, discarding the image, and displaying a black image, a substantially darker image.

[0105] refer to Figure 4C , a perspective view of device 400. As shown, FOVs 430 and 440, corresponding to ultra-wide-angle lens 422 and wide-angle lens 424, respectively, are shown at a distance d from device 400. Additionally, FOV 450 of telephoto lens 426 is also shown at a distance d from device 400. In the example shown, FOVs 430 and 440 each include all of FOV 450. In some cases, a camera application on device 400 may include a zoom feature. In some cases, the camera application's zoom setting may correspond to a FOV that is not perfectly aligned with any of FOVs 430, 440, 450. For example, FOV 425 may correspond to a specific zoom setting available in the camera application. In one illustrative example, for FOV 425 , a first image captured by ultra-wide-angle lens 422 (corresponding to view 430 ) and a second image captured by wide-angle lens 424 (corresponding to view 440 ) may be combined into a single image to produce an image corresponding to the zoom setting applied by the camera.

[0106] refer to Figure 4D In some cases, the HMD 455 (e.g., Figure 2A camera of an HMD 455 (XR system 200) can capture images of the scene (e.g., via one or more image sensors 202), while one or more cameras of device 400 capture images of the scene. In some embodiments, FOV 460 associated with a camera of HMD 455 can include all of FOVs 430, 440, and 450. In some cases, a portion 462 of FOV 460 of HMD 455 may be obstructed by one or more objects. As shown, device 400 may obstruct FOV 460. Other example obstructions may include, but are not limited to, human body parts (e.g., arms, hands, etc.), mechanical fixtures (e.g., tripods, telescopic mounting structures, pan / tilt systems, etc.).

[0107] Figure 4D An example FOV 485 is shown that is larger than FOV 440 and smaller than FOV 460. In some cases, HMD 455 and device 400 can exchange data through a communication interface (e.g., wired or wireless). In some cases, HMD 455 and device 400 can exchange image frames (or sequences of frames). In some cases, an aperture fusion engine (e.g., Figure 6 The aperture fusion engine 600 of the HMD 455 can combine the images captured by the device 400 to generate a combined image corresponding to the FOV 485.

[0108] Figure 4E An example of misalignment between the FOV 460 of the HMD 455 and the FOVs 430, 440, and 450 of the device 400 is shown. As shown, the example target FOV 495 can partially overlap with the FOVs 430, 440, and 450 of the device 400. In some cases, the HMD 455 and the device 400 can exchange positioning information via a communication link. In some cases, the aperture fusion engine (e.g., Figure 6 The aperture fusion engine 600) can obtain positioning information as input to improve the generation of the combined image.

[0109] In some cases, a user (eg, a user of HMD 455 ) may be unaware of the misalignment between FOV 460 and FOVs 430 , 440 , 450 . Figure 8A and Figure 8B shows an aperture fusion system (e.g., Figure 5 Example indicator 810 of misalignment between cameras operating together as part of the aperture fusion system 500). Figure 8A As shown, the FOV 850 associated with the device 800 and the HMD (e.g., Figure 4E860 associated with the HMD 455) may be misaligned relative to the scene 803. In some cases, the HMD and / or device 800 may determine that the FOV 850 and the FOV 860 are misaligned. In some cases, the HMD and / or device 800 may generate an indicator to assist in alignment between cameras operating together as part of an aperture fusion system. In one illustrative example, the indicator 810 may be displayed on a display of the HMD (e.g., Figure 2 850 and FOV 860). As shown, indicator 810 may indicate an adjustment (e.g., shift, rotation, movement, etc.) for adjusting device 800 to align FOV 850 and FOV 860. In another example, indicator 810 may indicate an adjustment for adjusting HMD, device 800, and / or both to align FOV 850 and FOV 860. Other types of indicators may also be used to indicate an adjustment, including but not limited to audio, tactile, and the like. Figure 8B FOVs 850 and 860 are shown after adjusting the relative position between the HMD and device 800. As indicated, the HMD can remove indicator 810 after FOVs 850 and 860 are within the target alignment amount relative to scene 803.

[0110] In some cases, aperture fusion systems (e.g. Figure 5 The aperture fusion system 500 can be configured to automatically control the captured image based on the indicator 810 and / or the target alignment amount relative to the scene 803. For example, in some cases, the aperture fusion system 500 can pause image fusion and / or image capture when the alignment amount between the FOVs 850 and 860 falls below the target alignment amount. In some embodiments, the aperture fusion system 500 can pause image fusion and / or capture when the indicator 810 indicates an adjustment. For example, in some cases, the aperture fusion system 500 can output a signal generated by the aperture fusion system (e.g., Figure 5 In some embodiments, the aperture fusion system 500 may capture an image from one of the cameras that are partially operated while the other cameras are misaligned with the scene 803. In some cases, the aperture fusion system 500 may initiate (or resume) image fusion and / or image capture when the FOVs 850 and 860 are within the target alignment. Figure 5 The aperture fusion system 500 may begin (or resume) image fusion and / or image capture when the indicator 810 is removed.

[0111] For example, in some cases, the amount of alignment can be determined based on one or more photogrammetric techniques. In some cases, features can be extracted from images captured by the HMD and device 800. Features can be extracted using any suitable technique, such as Scale Invariant Feature Transform (SIFT) (which locates features and generates descriptions of the features), Learned Invariant Feature Transform (LIFT), Speeded Up Robust Features (SURF), Gradient Location Orientation Histogram (GLOH), Oriented Rapid Rotation Brief (ORB), Binary Robust Invariant Scalable Keypoints (BRISK), Fast Retinal Keypoints (FREAK), KAZE, Accelerated KAZE (AKAZE), Normalized Cross Correlation (NCC), descriptor matching, other suitable techniques, or combinations thereof. In some examples, any suitable feature matching technique can be used to match features detected in each of the two images. In one illustrative example, a K-Nearest Neighbor (KNN) algorithm can be used to classify features. In some cases, the distance between features with matching classifiers in the two images can be used to determine the amount of alignment between FOVs 850 and 860.

[0112] In another illustrative example, alignment based on the relative poses of the HMD and device 800 can be used to determine alignment. For example, ray tracing (e.g., using rays derived from the poses of the HMD and device 800) can be used to determine alignment. In another example, the amount of alignment can be determined based on the amount of overlap between FOVs 850 and 860.

[0113] Figure 5 is a block diagram illustrating an aperture fusion system 500. Aperture fusion system 500 includes an HMD 505 and a mobile device 550. HMD 505 may include one or more cameras 502, one or more inertial sensors 504, a SLAM system 510, a mobile device tracking engine 515, a communication engine 525, and an image processing engine 535. Mobile device 550 may include one or more cameras 552, one or more inertial sensors 554, a display 559, an aperture fusion engine 560, an image processing engine 575, and a communication engine 585. In some embodiments, mobile device 550 may optionally include SLAM system 555. Display 559 may include glass, a screen, a lens, a projector, and / or other display mechanism that allows a user to see an image displayed thereon.

[0114] In some cases, the HMD 505 may be Figure 25. For example, one or more cameras 502 may correspond to image capture device 105A, image processing device 105B, image sensor 130, image sensor 202, and / or camera 310. In some cases, one or more inertial sensors 504 may correspond to accelerometer 204, gyroscope 206, and / or any other inertial sensor. In some cases, SLAM system 510 of HMD 505 may correspond to Figure 2 XR system 200 and / or Figure 3 The SLAM system 300 is similar to and performs the same Figure 2 XR system 200 and / or Figure 3 The communication engine 525 may correspond to the communication engine 228. The image processing engine 535 may be similar to the image processing engine 224 and perform similar functions as the image processing engine 224. The communication engine 525 may correspond to the communication engine 228. The image processing engine 535 may be similar to the image processing engine 224 and perform similar functions as the image processing engine 224.

[0115] exist Figure 5 In the example shown, the SLAM system 510 includes a mobile device tracking engine 515 that can be used to specifically track the pose (e.g., positioning information) of a mobile device 550 operating in cooperation with the HMD 505 in the aperture fusion system 500. In some cases, the mobile device tracking engine 515 can be configured to detect specific features associated with the handheld device, such as the presence of a display 559, edges, corners, etc. In some embodiments, the mobile device tracking engine 515 can be configured to detect special tracking indicators displayed on the display 559. For example, Figure 7 An example of a tracking indicator 760 is shown displayed on a display 759 of a mobile device 750. In some cases, the mobile device tracking engine 515 can be configured to detect a camera application 770. For example, the mobile device tracking engine 515 can detect a camera preview, user interface elements, and the like.

[0116] The communication engine 525 of the HMD 505 and the communication engine 585 of the mobile device 550 can communicate via a (wired or wireless) communication link 530. In some cases, the communication link 530 can be bidirectional. In some cases, the HMD 505 and / or the mobile device 550 can send positioning information (e.g., from the SLAM system 510, the mobile device tracking engine 515, and / or the SLAM system 555) via the communication link 530. For example, the positioning information can include pose information of the mobile device 550 determined by the mobile device tracking engine 515. As another example, the positioning information can include a SLAM map and / or a pose of the HMD 505. In some cases, the positioning information can include a map based on a combination of the SLAM maps of the mobile device 550 and the HMD 505. In some cases, the HMD 505 and / or the mobile device 550 can send image frames (e.g., image streams, video data, still images). For example, in Figure 5 In the configuration shown, video data from the HMD 505 can be processed by the image processing engine 535 and sent to the mobile device 550 via the communication link. The examples of communication between the communication engine 525 and the communication engine 585 provided herein are non-limiting and provided as examples. In some cases, more, less, and / or different information can be transmitted via the communication link 530 without departing from the scope of this disclosure.

[0117] In some cases, the SLAM system 555 of the mobile device 550 may be coupled with Figure 2 XR system 200 and / or Figure 3 The SLAM system 300 is similar to and performs the same Figure 2 XR system 200 and / or Figure 3 The aperture fusion engine 560 can be used to combine the image (or image sequence) of the scene 503 captured by the one or more cameras 502 of the HMD 505 with the image (or image sequence) of the scene 503 captured by the one or more cameras 552 into a combined image.

[0118] Figure 6 is a block diagram showing the architecture of the aperture fusion engine 600. The aperture fusion engine 600 can be used with Figure 5 The aperture fusion engine 600 corresponds to the aperture fusion engine 560. The aperture fusion engine 600 includes various components for generating a combined image (also referred to herein as a fused image) based on two or more input images. For illustration purposes, Figure 6 The example aperture fusion engine 600 receives two images (a first image 610 and a second image 612) as input. For example, the first image 610 may be a first image taken by a first device (e.g., Figure 5The second image 612 may be an image captured by a camera of a separate second device (e.g., Figure 5 In some cases, the first image 610 may be an image captured by a single camera of the first device and / or the second image 612 may be an image captured by a single camera of the second device. In some cases, the first image 610 may be an image combined from multiple cameras of the first device and / or the second image 612 may be an image combined from multiple cameras of the second device. In one illustrative example, the first image 610 may be an image captured by a camera with a wide-angle lens (e.g., Figure 4C 4 ) and an additional image captured by a second image sensor having an ultra-wide angle lens (e.g., ultra-wide angle lens 422 of FIG. 4 ), as described with respect to FIG. Figure 4C As described. Aperture fusion engine 600 may also obtain positioning information 614 as input. Positioning information 614 may include, but is not limited to, the pose of the HMD (e.g., determined by SLAM system 510), the pose of the mobile device (e.g., determined by SLAM system 510, mobile device tracking engine 515, and / or SLAM system 555). In some cases, the HMD and mobile device may share SLAM map information (e.g., determined as part of a SLAM operation).

[0119] In some cases, the aperture fusion engine 600 can implement various types of machine learning algorithms to generate a combined image based on two or more input images. In some embodiments, a deep generative neural network model (e.g., a generative adversarial network (GAN)) can be used to train the occlusion engine 602, the view synthesis engine 604, the image normalization engine 606, the fusion engine 608, and / or any combination thereof. A GAN is a form of generative neural network that can learn patterns in input data so that the neural network model can generate new synthesized outputs that can be plausibly derived from the original data set.

[0120] A GAN can include two neural networks operating together. One of the neural networks (called the generative neural network or generator, denoted G(z)) generates a synthesized output, while the other neural network (called the discriminative neural network or discriminator, denoted D(x)) evaluates the synthesized output for realism (whether the synthesized output comes from an original dataset, such as a training dataset, or is generated by the generator). The generator G(z) can correspond to the occlusion engine 602, the viewpoint synthesis engine 604, the image normalization engine 606, the fusion engine 608, and / or any combination thereof. The generator is trained to try and trick the discriminator into determining that a synthesized image (or set of images) generated by the generator is a real image (or set of images) from a training dataset (e.g., the first set of training images). The training process continues, and the generator becomes better at generating synthesized images that look like real images. The discriminator continues to discover flaws in the synthesized images, and the generator figures out what the discriminator is looking at to determine the flaws in the images. Once the network is trained, the generator is able to produce realistic-looking images that the discriminator cannot distinguish from real images.

[0121] There is a dueling aspect between the generator G and the discriminator D, with the parameters of the discriminator D being maximized. The discriminator D will attempt to discriminate between real images (from the set of training data) and fake images (generated by the generator G based on the set of second training images), and the generator G should minimize the discriminator D's ability to identify fake images. During the training process, the parameters of the generator G (e.g., the weights of the nodes of the neural network and, in some cases, other parameters such as bias) can be adjusted so that the generator G outputs video frames that are indistinguishable from real video frames associated with the second domain. A loss function can be used to analyze the errors in the generator G and the discriminator D. In some cases, separate loss functions can be provided for the generator G and the discriminator D. In one illustrative example, a binary cross-entropy loss function can be used. Other loss functions can also be used in some cases. In some examples, a single minimax function can be used by both the generator G and the discriminator D. The generator G and the discriminator D can be adjusted with opposing objectives relative to the minimax function. In one illustrative example, the parameters of the generator G can be adjusted to minimize (or maximize) the minimax function, while the parameters of the discriminator D can be adjusted to maximize (or minimize) the minimax function.

[0122] In some cases, the machine learning algorithms used for the occlusion engine 602, the view synthesis engine 604, the image normalization engine 606, the fusion engine 608, any portion thereof, and / or any combination thereof may include, but are not limited to, transformers, time-delay neural networks (TDNNs), deep feed-forward neural networks (DFFNNs), recurrent neural networks (RNNs), autoencoders (AEs), variation AEs (VAEs), denoising AEs (DAEs), sparse AEs (SAEs), Markov chains (MCs), perceptrons, or some combination thereof. The machine learning algorithms may be supervised learning algorithms, unsupervised learning algorithms, semi-supervised learning algorithms, any combination thereof, or other learning techniques.

[0123] like Figure 6 As shown, the occlusion engine 602 can obtain a second image 612 (e.g., from Figure 5 The second image may include one or more obstacles, such as a mobile device (e.g., Figure 5 The occlusion engine 602 may extract features from the second image and classify one or more objects based on the extracted features. In some cases, the occlusion engine 602 may perform semantic segmentation. In semantic segmentation, the occlusion engine 602 may associate each object in the scene with one or more classifications (also referred to herein as labels). In some cases, semantic segmentation does not distinguish between two objects if more than one object has the same label.

[0124] In some cases, once one or more obstacles are classified based on the second image 612, the occlusion engine 602 may replace pixels of the second image to remove the obstacles. In some embodiments, the occlusion engine 602 may perform an inpainting process to replace pixels previously occupied by unwanted objects in the input image. In some cases, the occlusion engine 602 may receive information that may be used after determining an obstacle (e.g., Figure 5 Positioning information 614 used during the location of the mobile device 550).

[0125] As described above, in some cases, the occlusion engine 602 can be implemented using a GAN. During training, a generator G for the GAN can receive an input image with occlusions (e.g., objects blocking portions of a scene captured in the input image) and generate an output image with the occlusions removed, and the goal of the GAN is to generate realistic images with the occlusions removed. For example, the input image may include a mobile device (e.g., Figure 5In some cases, the loss function of the generator G may include a loss term that penalizes the non-obstructed portion of the second image 612 for generating an image that is different from the second image 612. For example, the generator G should generate an image that has a similar or identical appearance to the second image 612, except for pixels corresponding to any obstacles. The discriminator D will try and distinguish between real images without occlusions (e.g., from the training dataset) and pseudo images generated by the generator G based on images with occlusions (e.g., from the second training dataset). For example, the training dataset may include images from one or more cameras (e.g., from Figure 5 In one illustrative example, an image of a scene with an occlusion (e.g., a scene being blocked by an HMD 505 and / or one or more additional cameras) is captured. Figure 5 Images of the same scene (occluded by the mobile device 550) can be input to the generator G, and the resulting output images can be included in the second training dataset.

[0126] During inference (e.g., after the generator G has been trained to generate realistic images with obstacles removed), the occlusion engine 602 can obtain the second image 612 and generate a realistic image without the obstacles. In one illustrative example, the occlusion engine 602 can perform an inpainting operation to generate pixel values ​​for the portions of the scene that were occluded in the second image 612. Figure 6 In the example shown, images generated by occlusion engine 602 may be provided as input to view synthesis engine 604 .

[0127] In another illustrative example, occlusion engine 602 can be trained using a supervised learning process. For example, a training dataset can include images with obstacles and images with obstacles removed by a skilled artist. In some cases, the images with obstacles can be input into occlusion engine 602, and occlusion engine 602 can generate output images with the obstacles removed. In some cases, a loss function can penalize the difference between the image output by occlusion engine 602 and the training dataset images with the obstacles removed.

[0128] In one illustrative example, an image of a scene can be captured by a mobile device and an HMD. In some cases, the image captured by the HMD may be obscured by the mobile device (e.g., when the mobile device is held in front of the wearer of the HMD). In some cases, the occlusion engine 602 can remove the obstruction (e.g., the mobile device) from the image captured by the HMD. Other types of indicators can also be used to indicate adjustments, including but not limited to audio, haptics, etc.

[0129] The viewpoint synthesis engine 604 can be configured to obtain the first image 610, the second image 612, and the positioning information 614 to generate an image with a novel viewpoint. In some cases, the novel viewpoint can be different from the viewpoint represented in the first image 610 (e.g., Figure 5 In some cases, the novel viewpoint may correspond to the viewpoint of the second image 612 (e.g., Figure 5 505). For illustrative purposes, the operation of the viewpoint synthesis engine 604 will be described with respect to a novel viewpoint corresponding to the viewpoint of the first image. In some cases (not shown), the novel viewpoint can be the same as the viewpoint of the second image 612. In some cases, the novel viewpoint can be different from the viewpoint of the first image 610 or the viewpoint of the second image 612. In some cases, the viewpoint synthesis engine 604 can be configured to generate a transform between a viewpoint contained in the first input image 610 and / or the second image 612 and the novel viewpoint.

[0130] As described above, the viewpoint synthesis engine 604 can be implemented using a GAN. As an illustrative example, during training, the generator G of the GAN can receive a set of images of an area captured from different viewpoints (e.g., from a second training dataset) and generate an output image of the area from a novel viewpoint, and the goal of the GAN is to generate realistic images from the novel viewpoint. The discriminator D will try and distinguish between real images (e.g., from the training dataset) and fake images from the novel viewpoint generated by the generator G (e.g., from the second training dataset). In one illustrative example, the training dataset may include images captured by an HMD (e.g., Figure 5 In some cases, the second training dataset can be generated by the generator G based on the first images (e.g., from Figure 5 of the mobile device 550 and a second image (e.g., from Figure 5In some cases, the images output by the generator G may have the appearance of being captured from a novel viewpoint. In some cases, the discriminator D may receive a set of images, which may include all images from the training dataset or may include images from the training dataset combined with pseudo images generated by the generator G. In some cases, the discriminator D may determine whether the set of images is all real or whether the set of images contains pseudo images.

[0131] During inference, the viewpoint synthesis engine 604 can generate an image from a novel viewpoint based on the first image 610, the output of the occlusion engine 602, and the positioning information 614. For example, the positioning information 614 can be used as part of a determination of a transformation of the second image 612 to the viewpoint of the first image 610. In some cases, the positioning information can be used to determine a relative pose between electronic devices that are not rigidly attached to each other such that the relative pose can change. In some cases, the electronic devices can be connected with a non-rigid connection. For example, the body of a user can be considered to be a non-rigid connection between an HMD worn by the user and a handheld mobile device. As another example, the positioning information can include relative pose changes that can occur between a fixed camera (e.g., a camera on a tripod, an IP camera, etc.) and a non-fixed camera (e.g., in a handheld and / or wearable device). In one illustrative example, the positioning information 614 can include an HMD (e.g., Figure 5 HMD 505), the pose of the mobile device (e.g., Figure 5 The present invention may also include the pose of the HMD and the mobile device 550), the relative pose between the HMD and the mobile device, any other positioning information, and / or any combination thereof.

[0132] In some cases, indicators (e.g. Figure 8A An indicator 810 is provided to indicate an adjustment (e.g., shift, rotation, movement, etc.) between the first image sensor and the second image sensor to correct the misalignment. In some examples, the indicator can be generated based on the positioning information 614. In some cases, the indicator can be displayed on a display of the HMD, the mobile device, or both.

[0133] like Figure 6 As shown in , the image normalization engine 606 may receive the output image from the view synthesis engine 604, with the novel viewpoint and the first image 610 as input. In some cases, the image normalization engine 606 may be configured to normalize the two input images. In some cases, normalizing the input images may include taking into account different image attributes in the input images to produce an output image that appears to be captured by a single camera. For example, in an HMD (e.g., Figure 5 The camera in the HMD 505) is connected to the camera included in the mobile device (e.g. Figure 5The image normalization engine 606 may produce images with different image properties compared to the camera in the mobile device 550. Example image properties include, but are not limited to, resolution, brightness, white balance, color balance, focus, depth of field, FOV, distortion, and / or any other image properties. In some cases, the image normalization engine 606 may be configured to normalize for different lighting conditions that may be present in the input images.

[0134] As described above, the image normalization engine 606 can be implemented using a GAN. As an illustrative example, during training, the GAN's generator G can receive a set of images with uniform image properties (e.g., from a training dataset) and generate a normalized output image based on two input images with non-uniform image properties (e.g., an image captured by an HMD and an image captured by a mobile device). The goal of the GAN is to generate realistic images with uniform image properties. The discriminator D will attempt to distinguish between real images (e.g., from the training dataset) and fake images generated by the generator G (e.g., from a second training dataset).

[0135] In another illustrative example, image normalization engine 606 can be trained using a supervised learning process. For example, image normalization engine 606 can receive a training dataset that includes input image pairs having non-uniform image properties and normalized images generated based on the input image pairs by a skilled expert. In some cases, a loss function can penalize image normalization engine 606 based on the difference between the image generated by image normalization engine 606 and the normalized image included in the training dataset.

[0136] During inference, image normalization engine 606 may receive two images as input (eg, the output of view synthesis engine 604 and first image 610 ) and generate a normalized output image based on the input images.

[0137] like Figure 6As shown in FIG, fusion engine 608 may receive as input a first image 610 and the output of image normalization engine 606 and generate an output image having a realistic appearance. For example, fusion engine 608 may be configured to select between a pixel of first image 610 and a pixel of the output image from image normalization engine 606 for each pixel location and use the selected pixel value in the output image. In some cases, fusion engine 608 may be configured to blend pixel information at a pixel location based on the pixel of first image 610 and the pixel of the output image from image normalization engine 606 at the same pixel location. In some cases, fusion engine 608 may generate an output pixel value based on a weighted sum of the two input pixel values ​​at each pixel location. In some cases, fusion engine 608 may output an image with occlusion removed, from a novel viewpoint, having a normalized appearance (e.g., having uniform image properties), the image including pixel information from first image 610 and second image 612, the normalized appearance having the appearance of being captured by a single camera.

[0138] Although Figure 6 The example aperture fusion engine 600 depicts separate machine learning models for the occlusion engine 602, view synthesis engine 604, and image normalization engine 606, but other configurations may be used without departing from the scope of this disclosure. For example, in some cases, the occlusion engine 602, view synthesis engine 604, and image normalization engine 606 may be combined into a single machine learning model. In some cases, more or fewer machine learning models may be used without departing from the scope of this disclosure. In some cases, one or more functions of the aperture fusion engine 600 may be distributed among one or more machine learning models, with Figure 6 The configuration shown in is different.

[0139] In some cases, the aperture fusion engine 600 can be used to combine images captured by separate devices from different FOVs, such as with respect to Figure 4D-4E For example, for a zoom level corresponding to FOV 485, the aperture fusion engine 600 may generate an output image based on a first image 610 captured by the ultra-wide-angle lens 422 and a second image captured by the HMD 455. Thus, in addition to changes in positioning between unconnected devices, the aperture fusion engine 600 may also be used to provide a smooth transition between zoom levels that fall between the FOVs of different cameras included in an aperture fusion system (e.g., the aperture fusion system 500) that includes multiple separate devices.

[0140] Return to Figure 5 , Figure 5The example aperture fusion system 500 shown in FIG. 5 shows an aperture fusion engine 560 included in a mobile device 550. In some cases, the computing resources of the HMD 505 included in the aperture fusion system 500 may be constrained by thermal requirements, battery power, and / or other constraints. In some cases, it may be desirable to include the aperture fusion engine 560 in the mobile device 550, which may have different constraints. However, it should be understood that the aperture fusion techniques described herein can be implemented by the HMD 505, the mobile device 550, a server, Figure 13 The system may be executed by the computing system 1300, any other individual device, and / or any combination thereof.

[0141] An example operation of an embodiment of the systems and techniques described herein will now be provided. In a first step, a user may be interested in capturing one or more images or videos of a scene. The user may wear an HMD having a first camera (e.g., Figure 5 The HMD 505 may include an image processing unit (I20) and may access a mobile device (e.g., a smartphone) having a second camera. The aperture fusion system may receive positioning information (e.g., positioning information 614) from the HMD and / or the mobile device. A user may initiate the capture of one or more images or videos of a scene on the mobile device (e.g., by providing input via a user interface of a camera application). The first camera included in the HMD may also capture images or videos of the scene from different perspectives. The perspective of the mobile device relative to the HMD may change over time. For example, a user may initially hold the mobile device with their arm extended in front of their torso. In such an example, the mobile device with the second camera may be lower than the HMD with the first camera. The mobile device may also be at a different distance from the scene than the HMD (e.g., closer or farther away). At different times, the user may hold the mobile device in their extended arm above their head. When held above the user's head, the mobile device may be higher than the HMD. The mobile device may be at the same distance from the scene than the HMD (e.g., approximately aligned with, held directly above, the HMD) or at a different distance (e.g., closer or farther away). For example, a user may wish to capture an image of a scene that is obscured by one or more people, objects, and / or any other obstructions by holding the mobile device above the head.

[0142] In an example embodiment, the aperture fusion system receives as input a first image captured from a first camera of the HMD and a second image captured from a second camera of the mobile device. The aperture fusion system receives positioning information (e.g., positioning information 614) from the HMD and / or the mobile device. In some locations, the mobile device and / or a portion of the user's body may obstruct the image captured by the first camera of the HMD (e.g., Figure 4BThe aperture fusion system can remove occlusions or obstacles (e.g., by Figure 6 The occlusion engine 602) and outputs a resulting image with the occlusion removed. As described herein, the occlusion engine performs feature detection and / or object classification to determine the presence and location of the occlusion in the first image. Additionally or alternatively, the occlusion engine uses positioning information (e.g., the location of the mobile device) to determine the location of the occlusion in the first image. In some cases, the occlusion engine can remove the occlusion based on the location determined based on the positioning information. The aperture fusion system processes the HMD image with the occlusion removed and provides an image from a second camera included in the mobile device to a view synthesis engine (e.g., Figure 6 The view synthesis engine 604 generates an image from a synthesized viewpoint based on the first image, the second image, and / or the positioning information. In an example embodiment, the synthesized viewpoint is the same as the viewpoint of the first image.

[0143] The synthesized viewpoint image and the second image are normalized by an image normalization engine (e.g., Figure 6 The image normalization engine 606 of the mobile device is normalized. The normalization engine generates a normalized image having uniform image properties to provide the appearance that the normalized image was captured by a single camera. In an example embodiment, the normalized image has image properties that are consistent with the image properties of the second image from the mobile device. The fusion engine (e.g., Figure 6 The fusion engine 608 of the embodiment can generate a combined image based on the second image and the normalized image. The combined image can be output to a display (e.g., a display included in an HMD, a display of a mobile device) and / or stored in a storage (e.g., Figure 13 computing system 1300, RAM 1325 and / or cache 1312).

[0144] In an example embodiment, the aperture fusion system provides a combined image of the scene even when the relative pose between the HMD and the mobile device changes. If the first camera of the HMD or the second camera of the mobile device becomes misaligned with the scene, the aperture fusion system generates an indicator (e.g., Figure 8A The system also includes an indicator 810 (not shown) that provides instructions for adjusting the HMD, mobile device, or both. When the camera becomes misaligned and the indicator is displayed, the aperture fusion system suspends fusion and / or image capture. For example, if the mobile device becomes misaligned with the scene, the HMD image is used instead of the combined image. When alignment is restored and the indicator is removed, the aperture fusion system resumes fusion and / or image capture.

[0145] Figure 9Ais a perspective diagram 900 illustrating an unmanned ground vehicle (UGV) 910 performing feature tracking and / or visual simultaneous localization and mapping (VSLAM) according to some examples. Figure 9A The UGV 910 shown in perspective view 900 of FIG. can be an example of a SLAM system 300. The UGV 910 includes a first camera 930A and a second camera 930B along the front surface of the UGV 910. The first camera 930A and the second camera 930B can be two of the one or more cameras 310. In some examples, the UGV 910 can include one or more additional cameras in addition to the first camera 930A and the second camera 930B. In some examples, the UGV 910 can include one or more additional sensors in addition to the first camera 930A and the second camera 930B. The UGV 910 includes a plurality of wheels 915 along the bottom surface of the UGV 910. The wheels 915 can serve as a means of transportation for the UGV 910 and can be motorized using one or more motors that can be actuated by a motion actuator of the UGV 910. The motion actuator, the motors, and therefore the wheels 915 can be actuated to move the UGV 910 along a path.

[0146] Figure 9B is a perspective view 950 illustrating an unmanned aerial vehicle (UAV) 920 performing feature tracking and / or visual simultaneous localization and mapping (VSLAM) according to some examples. Figure 9B The UAV 920 shown in perspective view 950 of FIG. 1 may be an example of a SLAM system 300 . UAV 920 includes a first camera 930A and a second camera 930B along the front of the body of UAV 920. In some examples, UAV 920 may include one or more additional cameras in addition to first camera 930A and second camera 930B. In some examples, UAV 920 may include one or more additional sensors in addition to first camera 930A and second camera 930B. UAV 920 includes a plurality of propellers 925 along the top of UAV 920. Propellers 925 may be spaced apart from the body of UAV 920 by one or more appendages to prevent propellers 925 from snagging on circuitry on the body of UAV 920 and / or to prevent propellers 925 from obstructing the field of view of first camera 930A and / or second camera 930B. The propellers 925 can serve as a means of transportation for the UAV 920 and can be driven using one or more motors that can be actuated by motion actuators of the UAV 920. The motion actuators, motors, and therefore the propellers 925 can be actuated to move the UAV 920 along a path.

[0147] In the case of a SLAM system 300 (such as a UGV 910 or a UAV 920), the SLAM system 300 may include a path planning engine and / or a motion actuator. The path planning engine may generate a path along which the vehicle will move. In some examples, the path planning engine may use the Dijkstra algorithm to plan the path. In some examples, the path planning engine may include stationary and / or moving obstacle avoidance when planning the path. In some examples, the path planning engine may include determining how to optimally move the vehicle from a first pose to a second pose when planning the path. In some examples, the path planning engine may plan a path that is optimized to reach and observe every portion of a first area of ​​the environment (e.g., a first set of one or more rooms in the environment) before moving to a second area of ​​the environment (e.g., a second set of one or more rooms in the environment) when planning the path. In some examples, the path planning engine may plan a path that is optimized to reach and observe a predetermined set of rooms in the environment (e.g., every room in the environment) as quickly as possible. In some examples, the path planning engine can plan a path back to a previously observed room to re-observe a particular feature to refine one or more map points corresponding to the feature in the local map and / or global map (e.g., to perform loop closure). In some examples, the path planning engine can plan a path back to a previously observed room to observe a portion of the previously observed room that lacks map points in the local map and / or global map to see if any features can be observed in that portion of the room. The motion actuator can actuate one or more motors to actuate a drive vehicle (e.g., wheels 915 or propellers 925) to move the vehicle along the path planned by the path planning engine.

[0148] Figure 10A1000 is a perspective view illustrating a head-mounted display (HMD) 1010 performing feature tracking and / or visual simultaneous localization and mapping (VSLAM) according to some examples. HMD 1010 may be, for example, an augmented reality (AR) headset, a virtual reality (VR) headset, a mixed reality (MR) headset, an extended reality (XR) headset, or some combination thereof. HMD 1010 may be an example of XR system 200, SLAM system 300, HMD 455, HMD 505, or a combination thereof. HMD 1010 includes a first camera 1030A and a second camera 1030B along the front of HMD 1010. First camera 1030A and second camera 1030B may be two of image sensors 202. In some examples, HMD 1010 may have only a single camera. In some examples, HMD 1010 may include one or more additional cameras in addition to first camera 1030A and second camera 1030B. In some examples, HMD 1010 may include one or more additional sensors in addition to first camera 1030A and second camera 1030B.

[0149] Figure 10B is shown being worn by user 1020 according to some examples Figure 10A 1030 shows a perspective view of a head-mounted display (HMD) 1010. User 1020 wears HMD 1010 on user 1020's head above user 1020's eyes. HMD 1010 can capture images using a first camera 1030A and a second camera 1030B. In some examples, HMD 1010 displays one or more display images based on the images captured by first camera 1030A and second camera 1030B toward user 1020's eyes. The display images can provide a stereoscopic view of the environment, in some cases with overlaid information and / or other modifications. For example, HMD 1010 can display a first display image based on the image captured by first camera 1030A to user 1020's right eye. HMD 1010 can also display a second display image based on the image captured by second camera 1030B to user 1020's left eye. For example, the HMD 1010 may provide overlaid information in a displayed image overlaid on images captured by the first camera 1030A and the second camera 1030B.

[0150] HMD 1010 does not include wheels 915, propellers 925, or other means of transportation of its own. Instead, HMD 1010 relies on the movements of user 1020 to move HMD 1010 relative to the environment. Therefore, in some cases, when implementing SLAM techniques, HMD 1010 may skip path planning using a path planning engine and / or movement actuation using motion actuators. In some cases, HMD 1010 may still perform path planning using a path planning engine and may indicate directions to user 1020 to follow a suggested path, thereby guiding the user along the suggested path planned using the path planning engine. In some cases, such as when HMD 1010 is a VR headset, the environment may be fully or partially virtual. If the environment is at least partially virtual, movement through the virtual environment may also be virtual. For example, movement through the virtual environment may be controlled by input device 208. Motion actuators may include any such input device 208. Movement through a virtual environment may not require wheels 915, propellers 925, legs, or any other form of transportation. If the environment is virtual, HMD 1010 can still perform path planning using a path planning engine and / or motion actuation. If the environment is virtual, HMD 1010 can perform motion actuation using motion actuators by performing virtual movement within the virtual environment. Even if the environment is virtual, SLAM technology can still be valuable because the virtual environment may be unmapped and / or may have been generated by a device other than HMD 1010 (such as a remote server or console associated with a video game or video game platform). In some cases, feature tracking and / or SLAM can be performed in a virtual environment, even by a vehicle or other device with its own physical transportation system that allows it to physically move about the physical environment. For example, SLAM can be performed in a virtual environment to test whether (e.g., SLAM system 300, SLAM system 510, SLAM system 555) is functioning properly without wasting time or energy on movement and without wearing out the physical transportation system.

[0151] Figure 11A1100 is a perspective view of a front surface 1155 of a mobile device 1150 that uses one or more front-facing cameras 1130A-1130B to perform feature tracking and / or visual simultaneous localization and mapping (VSLAM), according to some examples. Mobile device 1150 may be an example of XR system 200, SLAM system 300, device 400, mobile device 550, or a combination thereof. Mobile device 1150 may be, for example, a cellular phone, a satellite phone, a portable gaming console, a music player, a fitness tracking device, a wearable device, a wireless communication device, a laptop, a mobile device, any other type of computing device or computing system 1300 discussed herein, or a combination thereof. Front surface 1155 of mobile device 1150 includes display screen 1145. Front surface 1155 of mobile device 1150 includes first camera 1130A and second camera 1130B. First camera 1130A and second camera 1130B are shown in a bezel surrounding display screen 1145 on front surface 1155 of mobile device 1150. In some examples, first camera 1130A and second camera 1130B may be positioned in a notch or cutout cut out of display screen 1145 on front surface 1155 of mobile device 1150. In some examples, first camera 1130A and second camera 1130B may be under-display cameras positioned between display screen 1145 and the rest of mobile device 1150, such that light passes through a portion of display screen 1145 before reaching first camera 1130A and second camera 1130B. First camera 1130A and second camera 1130B in perspective view 1100 are front-facing cameras. First camera 1130A and second camera 1130B face in a direction perpendicular to the planar surface of front surface 1155 of mobile device 1150. First camera 1130A and second camera 1130B may be two of one or more cameras 310. In some examples, front surface 1155 of mobile device 1150 may have only a single camera. In some examples, the mobile device 1150 can include one or more additional cameras in addition to the first camera 1130A and the second camera 1130B. In some examples, the mobile device 1150 can include one or more additional sensors in addition to the first camera 1130A and the second camera 1130B.

[0152] Figure 11B1190 is a perspective view of a rear surface 1165 of a mobile device 1150 using one or more rear-facing cameras 1130C-1130D to perform feature tracking and / or visual simultaneous localization and mapping (VSLAM), according to some examples. The mobile device 1150 includes a third camera 1130C and a fourth camera 1130D on the rear surface 1165 of the mobile device 1150. The third camera 1130C and the fourth camera 1130D of the perspective view 1190 are rear-facing. The third camera 1130C and the fourth camera 1130D face in a direction perpendicular to the planar surface of the rear surface 1165 of the mobile device 1150. Although the rear surface 1165 of the mobile device 1150 does not have a display screen 1145 as shown in the perspective view 1190, in some examples, the rear surface 1165 of the mobile device 1150 may have a second display screen. If the back surface 1165 of the mobile device 1150 has a display screen 1145, then any positioning of the third camera 1130C and the fourth camera 1130D relative to the display screen 1145 can be used, as discussed with respect to the first camera 1130A and the second camera 1130B on the front surface 1155 of the mobile device 1150. The third camera 1130C and the fourth camera 1130D can be two of the one or more cameras 310. In some examples, the back surface 1165 of the mobile device 1150 can have only a single camera. In some examples, the mobile device 1150 can include one or more additional cameras in addition to the first camera 1130A, the second camera 1130B, the third camera 1130C, and the fourth camera 1130D. In some examples, the mobile device 1150 can include one or more additional sensors in addition to the first camera 1130A, the second camera 1130B, the third camera 1130C, and the fourth camera 1130D.

[0153] Like HMD 1010, mobile device 1150 does not include wheels 915, propellers 925, or other means of transportation of its own. Instead, mobile device 1150 relies on the movements of the user holding or wearing mobile device 1150 to move mobile device 1150 relative to the environment. Therefore, in some cases, when implementing SLAM techniques, mobile device 1150 may skip path planning using a path planning engine and / or motion actuation using motion actuators. In some cases, mobile device 1150 may still perform path planning using the path planning engine and may indicate directions to the user to follow a suggested path, thereby guiding the user along the suggested path planned using the path planning engine. In some cases, such as when mobile device 1150 is used for AR, VR, MR, or XR, the environment may be fully or partially virtual. In some cases, mobile device 1150 may be inserted into a head-mounted device (HMD) (e.g., into a cradle of the HMD), such that mobile device 1150 functions as a display for the HMD, with display screen 1145 of mobile device 1150 serving as the HMD's display. If the environment is at least partially virtual, movement through the virtual environment may also be virtual. For example, movement through the virtual environment may be controlled by one or more joysticks, buttons, video game controllers, mice, keyboards, trackpads, and / or other input devices coupled to the mobile device 1150 in a wired or wireless manner. The motion actuator may include any such input device. Movement through the virtual environment may not require wheels 915, propellers 925, legs, or any other form of transportation. If the environment is a virtual environment, the mobile device 1150 may still use a path planning engine and / or motion actuation to perform path planning. If the environment is a virtual environment, the mobile device 1150 may use the motion actuator to perform motion actuation by performing virtual movement within the virtual environment.

[0154] Figure 12 is a flow chart illustrating an example of a process 1200 for implementing image processing techniques according to some examples. At block 1202, the process 1200 includes receiving from a first device (e.g., Figure 5 A first image sensor of the mobile device 550, HMD 505 obtains a first image of the scene.

[0155] At block 1204, process 1200 includes receiving a request from a second device (e.g., Figure 5 The second image sensor of the HMD 505 and the mobile device 550 obtains a second image including at least a portion of the scene. In some aspects, the second image is sent via a communication link between the first device and the second device. In some embodiments, the communication link is a wireless communication link.

[0156] At block 1206, process 1200 includes determining a position between the first device and the second device based on a relative pose between the first device and the second device (eg, by Figure 5 In some examples, the positioning includes at least one or more of a SLAM map, sensor measurements, inertial sensor measurements, an image, or a feature vector.

[0157] At block 1208, process 1200 includes normalizing one or more image attributes between the first image and the second image (e.g., by Figure 6 In some cases, the image normalization engine 606 is used to normalize one or more image attributes between the first image and the second image. In some cases, normalizing one or more image attributes between the first image and the second image includes adjusting first one or more image attributes of the first image or second one or more image attributes of the second image to produce a third image having the first one or more image attributes or the second one or more image attributes. In some cases, the one or more image attributes include at least one or more of resolution, brightness, white balance, color balance, focus, depth of field, field of view, or distortion.

[0158] At block 1210, process 1200 includes generating a third image based on the first image and the second image based on the positioning between the first device and the second device and the normalization between the first image and the second image (e.g., by Figure 6 fusion engine 608 of the embodiment). In some cases, the second image depicts at least a portion of the first device; and process 1200 includes removing at least a portion of the first device from the second image. In some aspects, determining the positioning between the first device and the second device includes detecting one or more features associated with the first device in the second image. In some cases, at least a portion of the first device is not depicted in the first image. In some examples, generating the third image includes removing an object from the second image. In some aspects, the object is not present in the first image. In some embodiments, generating the third image includes generating an intermediate image based on the second image. In some aspects, generating the intermediate image includes at least partially removing the object from the second image. In some cases, process 1200 includes generating the third image based on the first image and the intermediate image. In some examples, generating the intermediate image includes detecting one or more features associated with the object in the second image and generating a segmentation associated with the object based on the one or more features. In some cases, generating the intermediate image also includes inpainting pixels of the intermediate image corresponding to the object after at least partially removing the object. In some examples, the object includes at least one or more of a human body part, an electronic device, or a mechanical structure.

[0159] In some aspects, process 1200 includes obtaining a fourth image of the second scene from the first image sensor and obtaining a fifth image of the second scene from the second image sensor. In some aspects, the fourth image is transmitted via a communication link (e.g., Figure 5 In some embodiments, process 1200 includes determining an additional positioning between the first device and the second device. In some cases, the additional positioning is based on an additional relative pose between the first device and the second device, and the additional relative pose is different from the relative pose (e.g., when the first device and the second device are non-rigidly attached). In some cases, process 1200 includes normalizing one or more image attributes between the fourth image and the fifth image, and generating a sixth image based on the fourth image and the fifth image based on the additional positioning between the first device and the second device and the normalized one or more image attributes between the fourth image and the fifth image.

[0160] In some embodiments, the first image includes a first perspective of a scene (e.g., a first viewpoint), and the second image includes a second perspective of the scene (e.g., a second viewpoint) that is different from the first perspective of the scene, and generating the combined image includes adjusting pixels of the second image to the first perspective or adjusting pixels of the first image to the second perspective.

[0161] In some examples, the first device includes a first housing, and the second device includes a second housing. In some cases, the first device and the second device are configured such that a relative pose between the first device and the second device can be changed.

[0162] In some aspects, process 1200 includes determining a misalignment between a first image of a scene and a second image of the scene; and based on the misalignment, generating an indicator (e.g., Figure 8A indicator 810).

[0163] Figure 12 The process 1200 shown in may also include any of the discussed operations shown in or discussed with respect to the image capture and processing system 100, the image capture device 105A, the image processing device 105B, the XR system, the SLAM system 300, or a combination thereof. Figure 12The image processing techniques may represent at least some of the operations of the image capture and processing system 100, the image capture device 105A, the image processing device 105B, the XR system 200, the SLAM system 300, the unmanned ground vehicle (UGV) 910, the unmanned aerial vehicle (UAV) 920, the head-mounted display (HMD) 1010, the mobile device 1150, the computing system 1300, or a combination thereof.

[0164] In some cases, at least a subset of the techniques shown in process 1200 can be performed remotely by one or more network servers of a cloud service. In some examples, the processes described herein (e.g., process 1200 and / or other processes described herein) can be performed by a computing device or apparatus. In some examples, process 1200 can be performed by a Figure 1 In some examples, process 1200 may be performed by image capture device 105A. Figure 1 The process 1200 can also be performed by the image processing device 105B. Figure 1 The process 1200 may also be performed by the image capture and processing system 100. Figure 2 XR devices, Figure 3 SLAM system 300, Figure 5 Aperture Fusion System 500, Figure 6 Aperture Fusion Engine 600, Figure 9A Unmanned Ground Vehicle (UGV) 910, Figure 9B Unmanned aerial vehicles (UAVs) 920, Figures 10A-10B Head-mounted display (HMD) 1010, Figures 11A-11B Executed by mobile device 1150, variations thereof, or combinations thereof.

[0165] Process 1200 can also be performed by Figure 13The computing device may be implemented using a computing device that utilizes the architecture of computing system 1300 shown in FIG. The computing device may include any suitable device, such as a mobile device (e.g., a mobile phone), a desktop computing device, a tablet computing device, a wearable device (e.g., a VR headset, an AR headset, AR glasses, a web-connected watch or smartwatch, or other wearable device), a server computer, an autonomous vehicle or a computing device of an autonomous vehicle, a robotic device, a television, and / or any other computing device with the resources to perform the processes described herein (including process 1200). In some cases, the computing device or apparatus may include various components, such as one or more input devices, one or more output devices, one or more processors, one or more microprocessors, one or more microcomputers, one or more cameras, one or more sensors, and / or other components configured to implement the steps of the processes described herein. In some examples, the computing device may include a display, a network interface configured to transmit and / or receive data, any combination thereof, and / or other components. The network interface may be configured to transmit and / or receive data based on the Internet Protocol (IP) or other types of data.

[0166] Components of a computing device may be implemented in circuitry. For example, a component may include and / or be implemented using electronic circuitry or other electronic hardware, which may include one or more programmable electronic circuits (e.g., a microprocessor, a graphics processing unit (GPU), a digital signal processor (DSP), a central processing unit (CPU), and / or other suitable electronic circuitry), and / or may include and / or be implemented using computer software, firmware, or any combination thereof to perform the various operations described herein.

[0167] Depend on Figure 1 (of the image capture and processing system 100), Figure 2 (XR System 200), Figure 3 (of the SLAM system 300) and Figure 13 The processes illustrated in the block diagram (of system 1300) and the flowchart illustrating process 1200 are described or organized as a logical flow chart, the operations of which represent a sequence of operations that can be implemented in hardware, computer instructions, or a combination thereof. In the context of computer instructions, an operation represents computer-executable instructions stored on one or more computer-readable storage media that, when executed by one or more processors, perform the operations. Generally, computer-executable instructions include routines, programs, objects, components, data structures, etc. that perform specific functions or implement specific data types. The order in which the operations are described is not intended to be construed as a limitation, and any number of the described operations can be combined in any order and / or in parallel to implement the processes.

[0168] In addition, the processes shown in block diagrams 100, 200, 300, 500, 600, and 1300, as well as the flowcharts showing process 1200 and / or other processes described herein, can be executed under the control of one or more computer systems configured with executable instructions and can be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) that is executed on one or more processors, through hardware, or a combination thereof. As described above, the code can be stored on a computer-readable or machine-readable storage medium, for example, in the form of a computer program including multiple instructions that can be executed by one or more processors. The computer-readable or machine-readable storage medium can be non-transitory.

[0169] Figure 13 is a diagram illustrating an example of a system for implementing certain aspects of the present technology. In particular, Figure 13 An example of a computing system 1300 is shown, which can be, for example, any computing device that makes up the image capture and processing system 100, the image capture device 105A, the image processing device 105B, the XR system, the SLAM system 300, the aperture fusion system 500, the aperture fusion engine 600, or any component thereof, wherein the components of the system communicate with each other using a connection 1305. The connection 1305 can be a physical connection using a bus, or a direct connection to the processor 1310, such as in a chipset architecture. The connection 1305 can also be a virtual connection, a networked connection, or a logical connection.

[0170] In some aspects, computing system 1300 is a distributed system in which the functionality described in this disclosure can be distributed across a data center, multiple data centers, a peer-to-peer network, etc. In some cases, one or more of the described system components represent a plurality of such components, each performing some or all of the functionality for which the component is described. In some cases, the components can be physical or virtual devices.

[0171] Example system 1300 includes at least one processing unit (CPU or processor) 1310 and connections 1305 coupling various system components including system memory 1315, such as read-only memory (ROM) 1320 and random access memory (RAM) 1325, to processor 1310. Computing system 1300 may include a cache 1312, which is a high-speed memory directly connected to, proximate to, or integrated as part of processor 1310.

[0172] Processor 1310 may include any general-purpose processor and hardware or software services, such as services 1332, 1334, and 1336, stored in storage device 1330, configured to control processor 1310, as well as specialized processors where software instructions are incorporated into the actual processor design. Processor 1310 may essentially be a completely self-contained computing system containing multiple cores or processors, a bus, a memory controller, a cache, etc. Multi-core processors may be symmetric or asymmetric.

[0173] To enable user interaction, computing system 1300 includes input device 1345, which can represent any number of input mechanisms, such as a microphone for voice, a touch-sensitive screen for gesture or graphical input, a keyboard, a mouse, motion input, and the like. Computing system 1300 can also include output device 1335, which can be one or more of a variety of output mechanisms. In some instances, a multimodal system can enable a user to provide multiple types of input / output to communicate with computing system 1300. Computing system 1300 can include a communication interface 1340, which can generally govern and manage user input and system output. The communication interface may use a wired and / or wireless transceiver to perform or facilitate receiving and / or sending wired or wireless communications, including utilizing an audio jack / plug, a microphone jack / plug, a Universal Serial Bus (USB) port / plug, an Apple® Lightning® port / plug, an Ethernet port / plug, a fiber optic port / plug, a proprietary wired port / plug, BLUETOOTH® wireless signal transmission, BLUETOOTH® Low Energy (BLE) wireless signal transmission, IBEACON® wireless signal transmission, radio frequency identification (RFID) wireless signal transmission, near field communication (NFC) wireless signal transmission, dedicated short range communication (DSRC) wireless signal transmission, 1002.11 The communication interface 1340 may also include one or more global navigation satellite system (GNSS) receivers or transceivers for determining the location of the computing system 1300 based on one or more signals received from one or more satellites associated with one or more GNSS systems. GNSS systems include, but are not limited to, the United States-based Global Positioning System (GPS), the Russian-based Global Navigation Satellite System (GLONASS), the China-based BeiDou Navigation Satellite System (BDS), and the European-based Galileo GNSS. There is no restriction to operating on any particular hardware arrangement, and thus the basic features herein may be readily substituted for improved hardware or firmware arrangements as such are developed.

[0174] The storage device 1330 may be a non-volatile and / or non-transitory and / or computer-readable memory device and may be a hard disk or other type of computer-readable medium that can store data accessible by a computer, such as a magnetic cassette, a flash memory card, a solid-state memory device, a digital versatile disk, a cartridge, a floppy disk, a flexible disk, a hard disk, a magnetic tape, a magnetic stripe, any other magnetic storage medium, a flash memory, a memristor memory, or a memory card. memory), any other solid-state memory, Compact Disc Read-Only Memory (CD-ROM), Rewritable Compact Disc (CD), Digital Video Disc (DVD), Blu-ray Disc (BDD), Holographic Disc, other optical media, Secure Digital (SD) card, micro Secure Digital (microSD) card, Memory Stick® card, smart card chip, EMV chip, Subscriber Identity Module (SIM) card, mini / micro / nano / pico SIM card, other integrated circuit (IC) chips / cards, Random Access Memory (RAM), Static RAM (SRAM), Dynamic RAM (DRAM), Read-Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Flash EPROM, Cache Memory (L1 / L2 / L3 / L4 / L5 / L#), Resistive Random Access Memory (RRAM / ReRAM), Phase Change Memory (PCM), Spin Transfer Torque RAM (STRAM), RAM, STT-RAM), other memory chips or cartridges, and / or combinations thereof.

[0175] Storage devices 1330 may include software services, servers, services, etc. that, when the code defining such software is executed by processor 1310, enable the system to perform functions. In some aspects, hardware services that perform specific functions may include software components stored in computer-readable media that, in combination with the necessary hardware components (such as processor 1310, connectivity 1305, output devices 1335, etc.) to perform the functions.

[0176] As used herein, the term "computer-readable medium" includes, but is not limited to, portable or non-portable storage devices, optical storage devices, and various other media capable of storing, containing, or carrying instructions and / or data. Computer-readable media may include non-transitory media in which data can be stored and that do not include carrier waves and / or transitory electronic signals propagated wirelessly or via a wired connection. Examples of non-transitory media include, but are not limited to, magnetic disks or tapes, optical storage media such as compact discs (CDs) or digital versatile discs (DVDs), flash memory, memory, or storage devices. A computer-readable medium may have code and / or machine-executable instructions stored thereon, which may represent a procedure, function, subroutine, program, routine, subroutine, module, software package, class, or any combination of instructions, data structures, or program statements. Code segments may be coupled to other code segments or hardware circuits by passing and / or receiving information, data, arguments, parameters, or memory contents. Information, arguments, parameters, data, etc. may be passed, forwarded, or transmitted using any suitable means, including memory sharing, message passing, token passing, network transmission, and the like.

[0177] In some aspects, computer-readable storage devices, media, and memories may include cables or wireless signals containing bit streams, etc. However, when referred to, non-transitory computer-readable storage media expressly excludes media such as energy, carrier signals, electromagnetic waves, and signals themselves.

[0178] Specific details are provided in the above description to provide a thorough understanding of the aspects and examples provided herein. However, it will be understood by those skilled in the art that these aspects can be practiced without these specific details. For clarity of explanation, in some instances, the present technology can be presented as including various functional blocks, which include functional blocks comprising devices, device components, steps in the method embodied in software or a combination of hardware and software or routines. In addition to those components shown in the accompanying drawings and / or described in this article, additional components can be used. For example, circuits, systems, networks, processes and other components can be shown as components in block diagram form to avoid blurring these aspects with unnecessary details. In other instances, known circuits, processes, algorithms, structures and techniques can be shown without unnecessary details to avoid blurring these aspects.

[0179] Various aspects may be described above as processes or methods depicted as flow charts, flow diagrams, data flow diagrams, structure diagrams, or block diagrams. Although a flow chart may describe operations as a sequential process, many operations may be performed in parallel or simultaneously. In addition, the order of the operations may be rearranged. A process terminates when its operations are completed, but may have additional steps not included in the diagram. A process may correspond to a method, function, procedure, subroutine, subprogram, etc. When a process corresponds to a function, its termination may correspond to the function returning to the calling function or the main function.

[0180] The processes and methods according to the above examples can be implemented using computer-executable instructions stored in or otherwise available from a computer-readable medium. Such instructions may include, for example, instructions and data that cause or otherwise configure a general-purpose computer, a special-purpose computer, or a processing device to perform a specific function or group of functions. Portions of the computer resources used may be accessible over a network. The computer-executable instructions may be, for example, binary files, intermediate format instructions such as assembly language, firmware, source code, etc. Examples of computer-readable media that can be used to store instructions, information used, and / or information created during the methods according to the described examples include magnetic or optical disks, flash memory, USB devices provided with non-volatile memory, networked storage devices, etc.

[0181] Devices implementing the processes and methods disclosed herein may include hardware, software, firmware, middleware, microcode, hardware description languages, or any combination thereof, and may take any of a variety of form factors. When implemented in software, firmware, middleware, or microcode, program code or code segments (e.g., a computer program product) for performing the necessary tasks may be stored on a computer-readable or machine-readable medium. A processor may perform the necessary tasks. Typical examples of form factors include laptop computers, smartphones, mobile phones, tablet devices or other small form factor personal computers, personal digital assistants, rackmount devices, standalone devices, etc. The functionality described herein may also be embodied in peripheral devices or add-in cards. As another example, such functionality may also be implemented on a circuit board in different chips or different processes executed in a single device.

[0182] Instructions, the media for carrying such instructions, computing resources for executing them, and other structure for supporting such computing resources are example means for providing the functionality described in this disclosure.

[0183] In the foregoing description, aspects of the present application have been described with reference to their specific aspects, but those skilled in the art will recognize that the present application is not limited thereto. Therefore, although the illustrative aspects of the present application have been described in detail herein, it should be understood that the inventive concept can be variously embodied and adopted in other ways, and the appended claims are intended to be interpreted as including such variations, unless limited by the prior art. The various features and aspects of the above-mentioned application can be used individually or in combination. In addition, without departing from the broader spirit and scope of this specification, various aspects can be utilized in any number of environments and applications beyond those described herein. Therefore, the description and drawings are to be considered illustrative rather than restrictive. For illustrative purposes, the method is described in a particular order. It should be understood that in alternative aspects, the method can be performed in an order different from the described order.

[0184] One of ordinary skill will understand that the less than ("<") and greater than (">") symbols or terms used herein may be replaced by the less than or equal to ("≤") and greater than or equal to ("≥") symbols, respectively, without departing from the scope of the present specification.

[0185] Where a component is described as being “configured to” perform certain operations, such configuration may be achieved, for example, by designing electronic circuits or other hardware to perform those operations, by programming programmable electronic circuits (e.g., a microprocessor or other suitable electronic circuit) to perform those operations, or any combination thereof.

[0186] The phrase "coupled to" refers to any component being directly or indirectly physically connected to other components, and / or any component being in direct or indirect communication with other components (e.g., via a wired or wireless connection, and / or other suitable communication interfaces).

[0187] Claim language or other language that recites "at least one of" a set and / or "one or more" a set indicates that one member of the set or multiple members of the set (in any combination) satisfies the claim. For example, claim language that recites "at least one of A and B" means A, B, or A and B. In another example, claim language that recites "at least one of A, B, and C" means A, B, C, or A and B, or A and C, or B and C, or A, B, and C. The language "at least one of" a set and / or "one or more" a set does not limit the set to the items listed in the set. For example, claim language that recites "at least one of A and B" may mean A, B, or A and B, and may additionally include items not listed in the set of A and B.

[0188] The various illustrative logic blocks, modules, circuits, and algorithmic steps described in conjunction with the aspects disclosed herein can be implemented as electronic hardware, computer software, firmware, or a combination thereof. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been generally described above with respect to their functions. Whether such functions are implemented as hardware or software depends on the specific application and the design constraints imposed on the entire system. Technicians can implement the described functions in a varying manner for each specific application, but such implementation decisions should not be interpreted as resulting in a departure from the scope of this application.

[0189] The techniques described herein may also be implemented in electronic hardware, computer software, firmware, or any combination thereof. Such techniques may be implemented in any of a variety of devices, such as a general-purpose computer, a wireless communication device handset, or an integrated circuit device with multiple uses, including applications in wireless communication device handsets and other devices. Any features described as modules or components may be implemented together in an integrated logic device or separately as discrete but interoperable logic devices. If implemented in software, the techniques may be implemented at least in part by a computer-readable data storage medium including program code comprising instructions that, when executed, perform one or more of the methods described above. The computer-readable data storage medium may form part of a computer program product, which may include packaging materials. The computer-readable medium may include memory or data storage media, such as random access memory (RAM) (such as synchronous dynamic random access memory (SDRAM)), read-only memory (ROM), non-volatile random access memory (NVRAM), electrically erasable programmable read-only memory (EEPROM), flash memory, magnetic or optical data storage media, and the like. Additionally or alternatively, the technology may be implemented at least in part by a computer-readable communication medium that carries or communicates program code in the form of instructions or data structures and can be accessed, read, and / or executed by a computer, such as a propagated signal or wave.

[0190] The program code may be executed by a processor, which may include one or more processors, such as one or more digital signal processors (DSPs), general-purpose microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other equivalent integrated or discrete logic circuitry. Such a processor may be configured to perform any of the techniques described herein. A general-purpose processor may be a microprocessor; however, in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration. Therefore, as used herein, the term "processor" may refer to any of the foregoing structures, any combination of the foregoing structures, or any other structure or device suitable for implementation of the techniques described herein. Furthermore, in some aspects, the functionality described herein may be provided within dedicated software or hardware modules configured for encoding and decoding, or incorporated into a combined video encoder-decoder (CODEC).

[0191] Illustrative aspects of the present disclosure include:

[0192] Aspect 1 A device for generating an image based on two or more images comprises: a first device, comprising: a first image sensor; a memory; and one or more processors coupled to the memory and configured to: obtain a first image of a scene from the first image sensor; obtain a second image of the scene from a second image sensor of a second device, wherein the second image is sent via a communication link between the first device and the second device; determine the positioning between the first device and the second device based on the relative posture between the first device and the second device; normalize one or more image attributes between the first image and the second image; and generate a third image based on the first image and the second image based on the positioning between the first device and the second device and the normalized one or more image attributes between the first image and the second image.

[0193] Aspect 2 An apparatus according to Aspect 1, wherein: the first device includes a first shell; the second device includes a second shell different from the first shell; and the first device and the second device are configured so that the relative posture between the first device and the second device can be changed.

[0194] Aspect 3. An apparatus according to any one of aspects 1 to 2, wherein the first device comprises a mobile device and the second device comprises a head-mounted display.

[0195] Aspect 4 An apparatus according to any one of Aspects 1 to 3, wherein the second image depicts at least a portion of the first device; and wherein, to generate the third image, the one or more processors are configured to remove at least a portion of the first device from the second image.

[0196] Aspect 5 An apparatus according to any one of Aspects 1 to 4, wherein, in order to determine the positioning between the first device and the second device, the one or more processors are configured to detect one or more features associated with the first device in the second image, wherein at least a portion of the first device is not depicted in the first image.

[0197] Aspect 6 According to the apparatus described in any one of Aspects 1 to 5, one or more processors are configured to: obtain a fourth image of the second scene from the first image sensor; obtain a fifth image of the second scene from the second image sensor, wherein the fifth image is sent via a communication link between the first device and the second device; determine an additional positioning between the first device and the second device, wherein the additional positioning is based on an additional relative pose between the first device and the second device, wherein the additional relative pose is different from the relative pose; normalize one or more image attributes between the fourth image and the fifth image; and generate a sixth image based on the fourth image and the fifth image based on the additional positioning between the first device and the second device and the normalized one or more image attributes between the fourth image and the fifth image.

[0198] Aspect 7. An apparatus according to any one of aspects 1 to 6, wherein the communication link is a wireless communication link.

[0199] Aspect 8 An apparatus according to any one of Aspects 1 to 7, wherein, in order to normalize one or more image attributes between a first image and a second image, one or more processors are configured to adjust first one or more image attributes of the first image or second one or more image attributes of the second image to generate a third image having the first one or more image attributes or the second one or more image attributes.

[0200] Aspect 9: An apparatus according to any one of aspects 1 to 8, wherein the one or more image attributes include at least one or more of resolution, brightness, white balance, color balance, focus, depth of field, field of view, or distortion.

[0201] Aspect 10 In an apparatus according to any one of Aspects 1 to 9, one or more processors are configured to: obtain input associated with a change in zoom; obtain a fourth image of a scene from a first image sensor; obtain a fifth image including at least a portion of the scene from a second image sensor; determine an additional positioning between the first device and the second device based on an additional relative pose between the first device and the second device; normalize one or more image attributes between the fourth image and the fifth image; and generate a sixth image based on the fourth image and the fifth image based on the positioning between the first device and the second device, the input associated with the change in zoom, and the normalization of one or more image attributes between the fourth image and the fifth image.

[0202] Aspect 11. An apparatus according to any one of aspects 1 to 10, wherein a first field of view (FOV) associated with the third image is different from a second FOV associated with the sixth image.

[0203] Aspect 12: An apparatus according to any one of Aspects 1 to 11, wherein the positioning comprises at least one or more of a SLAM map, a sensor measurement result, an inertial sensor measurement result, an image, or a feature vector.

[0204] Aspect 13 In an apparatus according to any one of Aspects 1 to 12, one or more processors are configured to: determine a misalignment between a first image of a scene and a second image of the scene; and based on the misalignment, generate an indicator for indicating an adjustment between the first image sensor and the second image sensor to correct the misalignment.

[0205] Aspect 14: The apparatus according to any one of aspects 1 to 13, wherein the first image includes a first field of view (FOV), and the second image includes a second FOV different from the first FOV.

[0206] Aspect 15: An apparatus according to any one of Aspects 1 to 14, wherein, to determine the misalignment between the first image of the scene and the second image of the scene, the one or more processors are configured to determine an amount of overlap between the first FOV and the second FOV.

[0207] Aspect 16: According to the apparatus of any one of aspects 1 to 15, to generate the indicator, the one or more processors are configured to generate the indicator for indicating the adjustment based on determining that the misalignment exceeds a misalignment threshold.

[0208] Aspect 17. An apparatus according to any one of Aspects 1 to 16, wherein, to determine that the misalignment exceeds a misalignment threshold, the one or more processors are configured to determine an amount of overlap between the first FOV and the second FOV.

[0209] Aspect 18. An apparatus according to any one of Aspects 1 to 17, wherein determining that the misalignment exceeds a misalignment threshold comprises determining that an amount of overlap between the first FOV and the second FOV is below a FOV overlap threshold.

[0210] Aspect 19: An apparatus according to any one of aspects 1 to 18, wherein the indication of adjustment comprises an indication of at least one or more of shifting, rotating, or moving at least one or more of the first device or the second device.

[0211] Aspect 20: According to the apparatus of any one of aspects 1 to 19, the one or more processors are configured to: display an indicator on at least one or more of a display of the first device or a display of the second device.

[0212] Aspect 21. An apparatus according to any one of aspects 1 to 20, wherein the indicator provides an indication of an adjustment for adjusting the first device to align the first FOV with the second FOV.

[0213] Aspect 22: An apparatus according to any one of Aspects 1 to 21, wherein the indicator is displayed on a display of the first device.

[0214] Aspect 23. An apparatus according to any one of aspects 1 to 22, wherein the indicator provides an indication of an adjustment for adjusting the second device to align the second FOV with the first FOV.

[0215] Aspect 24: An apparatus according to any one of Aspects 1 to 23, wherein the indicator is displayed on a display of the second device.

[0216] Aspect 25. An apparatus according to any one of Aspects 1 to 24, wherein: the first image sensor is associated with a first optical axis; and the second image sensor is associated with a second optical axis, wherein the first optical axis and the second optical axis intersect.

[0217] Aspect 26. An apparatus according to any one of Aspects 1 to 25, wherein, to generate the third image, the one or more processors are configured to remove an object from the second image, wherein the object is not present in the first image.

[0218] Aspect 27 An apparatus according to any one of Aspects 1 to 26, wherein, in order to generate a third image, one or more processors are configured to: generate an intermediate image based on the second image, wherein generating the intermediate image includes at least partially removing an object from the second image; and generate the third image based on the first image and the intermediate image.

[0219] Aspect 28 An apparatus according to any one of Aspects 1 to 27, wherein, to generate the intermediate image, the one or more processors are configured to detect one or more features associated with the object in the second image and generate a segmentation associated with the object based on the one or more features.

[0220] Aspect 29 A method for generating a combined image based on two or more images, comprising: obtaining a first image of a scene from a first image sensor of a first device; obtaining a second image including at least a portion of the scene from a second image sensor of a second device, wherein the second image is sent via a communication link between the first device and the second device; determining a positioning between the first device and the second device based on a relative posture between the first device and the second device; normalizing one or more image attributes between the first image and the second image; and generating a third image based on the first image and the second image based on the positioning between the first device and the second device and the normalized one or more image attributes between the first image and the second image.

[0221] Aspect 30: A method according to Aspect 29, wherein the first device includes a first shell; the second device includes a second shell different from the first shell; and the first device and the second device are configured so that the relative posture between the first device and the second device can be changed.

[0222] Aspect 31. A method according to any one of Aspects 29 to 30, wherein the first device comprises a mobile device and the second device comprises a head-mounted display.

[0223] Aspect 32: A method according to any one of Aspects 29 to 31, wherein the second image depicts at least a portion of the first device, and wherein generating the third image includes removing at least a portion of the first device from the second image.

[0224] Aspect 33: The method according to any one of Aspects 29 to 32, further comprising detecting one or more features associated with the first device in the second image, wherein the first device is not present in the first image.

[0225] Aspect 34 A method according to any one of Aspects 29 to 33, wherein: the second image depicts at least one or more of a human body part, an electronic device, or a mechanical structure; and generating the third image includes removing at least one or more of the human body part, the electronic device, or the mechanical structure from the second image.

[0226] Aspect 35 The method according to any one of Aspects 29 to 34 further includes: obtaining a fourth image of the second scene from the first image sensor; obtaining a fifth image of the second scene from the second image sensor, wherein the fourth image is sent via a communication link between the first device and the second device; determining an additional positioning between the first device and the second device, wherein the additional positioning is based on an additional relative pose between the first device and the second device, wherein the additional relative pose is different from the relative pose; normalizing one or more image attributes between the fourth image and the fifth image; and generating a sixth image based on the fourth image and the fifth image based on the additional positioning between the first device and the second device and the normalized one or more image attributes between the fourth image and the fifth image.

[0227] Clause 36: A method according to any one of clauses 29 to 35, wherein the FOV associated with the third image is different from the FOV associated with the sixth image.

[0228] Aspect 37: A method according to any one of aspects 29 to 36, wherein the communication link is a wireless communication link.

[0229] Aspect 38 A method according to any one of Aspects 29 to 37, wherein normalizing one or more image attributes between the first image and the second image includes adjusting first one or more image attributes of the first image or second one or more image attributes of the second image to produce a third image having the first one or more image attributes or the second one or more image attributes.

[0230] Clause 39: A method according to any one of clauses 29 to 38, wherein the one or more image attributes include at least one or more of resolution, brightness, white balance, color balance, focus, depth of field, field of view, or distortion.

[0231] Aspect 40 A method according to any one of Aspects 29 to 39, wherein: the first image includes a first perspective of a scene, and the second image includes a second perspective of the scene that is different from the first perspective of the scene; and generating the combined image includes adjusting pixels of the second image to the first perspective or adjusting pixels of the first image to the second perspective.

[0232] Aspect 41. The method according to any one of Aspects 29 to 40, wherein the second device is a head-mounted display and the first device is a mobile device.

[0233] Aspect 42: A method according to any one of Aspects 29 to 41, wherein the positioning includes at least one or more of a SLAM map, sensor measurements, inertial sensor measurements, an image, or a feature vector.

[0234] Aspect 43 The method according to any one of Aspects 29 to 42 also includes: determining a misalignment between the first image of the scene and the second image of the scene; and based on the misalignment, generating an indicator for indicating an adjustment between the first image sensor and the second image sensor to correct the misalignment.

[0235] Aspect 44: A method according to any one of aspects 29 to 43, wherein the first image includes a first FOV and the second image includes a second FOV different from the first FOV.

[0236] Aspect 45. The method according to any one of aspects 29 to 44, wherein generating the indicator comprises generating the indicator indicating the adjustment based on determining that the misalignment exceeds a misalignment threshold.

[0237] Aspect 46: A method according to any one of aspects 29 to 45, wherein determining that the misalignment exceeds a misalignment threshold comprises determining an amount of overlap between the first FOV and the second FOV.

[0238] Aspect 47 A method according to any one of aspects 29 to 46, wherein determining that the misalignment exceeds a misalignment threshold comprises determining an amount of overlap between the first FOV and the second FOV.

[0239] Aspect 48: A method according to any one of aspects 29 to 47, wherein determining that the misalignment exceeds a misalignment threshold comprises determining that an amount of overlap between the first FOV and the second FOV is below a FOV overlap threshold.

[0240] Aspect 49 The method according to any one of aspects 29 to 48 further includes displaying an indicator on at least one or more of the display of the first device or the display of the second device.

[0241] Aspect 50: The method according to any one of aspects 29 to 49, wherein the indicator provides an indication of an adjustment for adjusting the first device to align the first FOV with the second FOV.

[0242] Aspect 51: A method according to any one of Aspects 29 to 50, wherein the indicator is displayed on a display of the first device.

[0243] Aspect 52: A method according to any one of aspects 29 to 51, wherein the indicator provides an indication of an adjustment for adjusting the second device to align the second FOV with the first FOV.

[0244] Aspect 53: A method according to any one of Aspects 29 to 52, wherein the indicator is displayed on a display of the second device.

[0245] Aspect 54: A method according to any one of aspects 29 to 53, wherein the indication of adjustment comprises an indication of at least one or more of shifting, rotating, or moving at least one or more of the first device or the second device.

[0246] Aspect 55: A method according to any one of Aspects 29 to 54, wherein: the first image sensor is associated with a first optical axis; and the second image sensor is associated with a second optical axis, wherein the first optical axis and the second optical axis intersect.

[0247] Aspect 56: The method according to any one of Aspects 29 to 55, wherein generating the third image comprises removing an object from the second image, wherein the object is not present in the first image.

[0248] Aspect 57 A method according to any one of Aspects 29 to 56, wherein: generating the third image includes generating an intermediate image based on the second image, wherein generating the intermediate image includes at least partially removing the object from the second image; and generating the third image based on the first image and the intermediate image.

[0249] Clause 58: A method according to any one of Clauses 29 to 57, wherein generating the intermediate image comprises detecting one or more features associated with the object in the second image and generating a segmentation associated with the object based on the one or more features.

[0250] Aspect 59: A non-transitory computer-readable storage medium having instructions stored thereon, which, when executed by one or more processors, cause the one or more processors to perform any of the operations in Aspect 1 to Aspect 58.

[0251] Aspect 60: An apparatus comprising means for performing any of the operations in Aspect 1 to Aspect 58.

Claims

1. An apparatus for generating an image based on two or more images, comprising: The first device includes: a first image sensor; Memory; and one or more processors coupled to the memory and configured to: obtaining a first image of a scene from the first image sensor; obtaining a second image of the scene from a second image sensor of a second device, wherein the second image is sent via a communication link between the first device and the second device; Determining the positioning of the first device and the second device based on the relative position between the first device and the second device; normalizing one or more image properties between the first image and the second image; and Based on the positioning between the first device and the second device and normalizing the one or more image properties between the first image and the second image, a third image based on the first image and the second image is generated.

2. The device according to claim 1, wherein: The first device includes a first housing; the second device comprising a second housing different from the first housing; and The first device and the second device are configured such that a relative posture between the first device and the second device can be changed.

3. The device according to claim 1, wherein The first device comprises a mobile device, and the second device comprises a head-mounted display.

4. The device according to claim 1, wherein The second image depicts at least a portion of the first device; and wherein, to generate the third image, the one or more processors are configured to remove the at least a portion of the first device from the second image.

5. The device according to claim 4, wherein To determine the positioning between the first device and the second device, the one or more processors are configured to detect one or more features associated with the first device in the second image, wherein the at least a portion of the first device is not depicted in the first image.

6. The apparatus of claim 1 , wherein the one or more processors are configured to: obtaining a fourth image of a second scene from the first image sensor; A fifth image of the second scene is obtained from the second image sensor, wherein: The fifth image is sent via a communication link between the first device and the second device; determining an additional position between the first device and the second device, wherein the additional position is based on an additional relative pose between the first device and the second device, wherein the additional relative pose is different from the relative pose; normalizing one or more image attributes between the fourth image and the fifth image; and A sixth image based on the fourth image and the fifth image is generated based on the additional positioning between the first device and the second device and normalizing the one or more image properties between the fourth image and the fifth image.

7. The device according to claim 1, wherein The communication link is a wireless communication link.

8. The device according to claim 1, wherein In order to normalize the one or more image attributes between the first image and the second image, the one or more processors are configured to adjust the first one or more image attributes of the first image or the second one or more image attributes of the second image to generate the third image having the first one or more image attributes or the second one or more image attributes.

9. The device according to claim 1, wherein The one or more image attributes include at least one or more of resolution, brightness, white balance, color balance, focus, depth of field, field of view, or distortion; Wherein, to generate the third image, the one or more processors are configured to remove an object from the second image, wherein the object is not present in the first image.

10. The apparatus of claim 1 , wherein the one or more processors are configured to: obtaining input associated with a change in zoom; obtaining a fourth image of the scene from the first image sensor; obtaining a fifth image including at least a portion of the scene from the second image sensor; determining an additional positioning between the first device and the second device based on the additional relative pose between the first device and the second device; normalizing one or more image attributes between the fourth image and the fifth image; as well as A sixth image based on the fourth image and the fifth image is generated based on the positioning between the first device and the second device, the input associated with the change in zoom, and normalizing the one or more image properties between the fourth image and the fifth image.

11. The device according to claim 10, wherein A first field of view associated with the third image is different from a second field of view associated with the sixth image.

12. The device according to claim 1, wherein The positioning includes at least one or more of a SLAM map, a sensor measurement result, an inertial sensor measurement result, an image, or a feature vector.

13. The device according to claim 1, wherein The one or more processors are configured to: determining a misalignment between the first image of the scene and the second image of the scene; as well as Based on the misalignment, an indicator is generated to indicate an adjustment between the first image sensor and the second image sensor to correct the misalignment.

14. The device according to claim 13, wherein The first image includes a first field of view (FOV) and the second image includes a second FOV different from the first FOV.

15. The device according to claim 14, wherein To determine the misalignment between the first image of the scene and the second image of the scene, the one or more processors are configured to determine an amount of overlap between the first FOV and the second FOV.

16. A method for generating a combined image based on two or more images, comprising: obtaining a first image of a scene from a first image sensor of a first device; obtaining a second image including at least a portion of the scene from a second image sensor of a second device, wherein the second image is sent via a communication link between the first device and the second device; Determining the positioning of the first device and the second device based on the relative position between the first device and the second device; normalizing one or more image properties between the first image and the second image; and Based on the positioning between the first device and the second device and normalizing the one or more image properties between the first image and the second image, a third image based on the first image and the second image is generated.

17. The method according to claim 16, wherein The first device includes a first housing; the second device comprising a second housing different from the first housing; and The first device and the second device are configured such that a relative posture between the first device and the second device can be changed.

18. The method according to claim 16, wherein The first device comprises a mobile device, and the second device comprises a head-mounted display.

19. The method according to claim 16, wherein The second image depicts at least a portion of a first device, and wherein generating the third image includes removing the at least a portion of the first device from the second image.

20. The method of claim 19, further comprising detecting one or more features associated with the first device in the second image, wherein The first device does not exist in the first image.

21. The method of claim 16, wherein: The second image depicts at least one or more of a human body part, an electronic device, or a mechanical structure; and Generating the third image includes removing the at least one or more of the human body part, electronic device, or mechanical structure from the second image.

22. The method of claim 16, further comprising: obtaining a fourth image of a second scene from the first image sensor; obtaining a fifth image of the second scene from the second image sensor, wherein the fourth image is sent via a communication link between the first device and the second device; determining an additional position between the first device and the second device, wherein the additional position is based on an additional relative pose between the first device and the second device, wherein the additional relative pose is different from the relative pose; normalizing one or more image attributes between the fourth image and the fifth image; and A sixth image based on the fourth image and the fifth image is generated based on the additional positioning between the first device and the second device and normalizing the one or more image properties between the fourth image and the fifth image.

23. The method according to claim 22, wherein The FOV associated with the third image is different from the FOV associated with the sixth image.

24. The method according to claim 16, wherein The communication link is a wireless communication link.

25. The method according to claim 16, wherein Normalizing the one or more image attributes between the first image and the second image includes adjusting first one or more image attributes of the first image or second one or more image attributes of the second image to produce the third image having the first one or more image attributes or the second one or more image attributes.

26. The method according to claim 16, wherein The one or more image attributes include at least one or more of resolution, brightness, white balance, color balance, focus, depth of field, FOV, or distortion.

27. The method of claim 16, wherein: The first image includes a first perspective of the scene, and the second image includes a second perspective of the scene that is different from the first perspective of the scene; and Generating the combined image includes adjusting pixels of the second image to the first perspective or adjusting pixels of the first image to the second perspective.

28. The method according to claim 16, wherein The second device is a head mounted display and the first device is a mobile device.

29. The method according to claim 16, wherein The positioning includes at least one or more of a SLAM map, a sensor measurement result, an inertial sensor measurement result, an image, or a feature vector.

30. The method of claim 16, further comprising: determining a misalignment between the first image of the scene and the second image of the scene; as well as Based on the misalignment, an indicator is generated to indicate an adjustment between the first image sensor and the second image sensor to correct the misalignment.

Images