Depth estimation from RGB images

Abstract

A system for generating an augmented reality effect using image data of a hand and a depth estimation model. A depth estimation model is trained using a pairing of the synthetic 2D image data with the depth set and the segmentation mask. An augmented reality system captures image data of a hand in a real-world scene and generates an augmented reality effect using the image data and a depth estimation model. Augmented reality effects are provided to a user during an augmented reality experience.

Description

[0001] Priority requirements

[0002] This application claims the benefit of U.S. Patent Application Serial No. 18 / 179,784, filed on March 7, 2023, which is incorporated herein by reference in its entirety. Technical Field

[0003] This disclosure relates generally to image processing, and more specifically to determining 3D data from 2D images. Background Technology

[0004] User devices such as head-mounted wearables can be implemented with transparent or semi-transparent displays, through which the user of the head-mounted wearable can view their surroundings. Such head-mounted wearables allow users to view their surroundings through transparent or semi-transparent displays, and also to see objects generated for display that appear as part of the surrounding environment and / or superimposed on the surrounding environment (e.g., virtual objects, such as renderings of 2D or 3D graphical models, images, videos, text, etc.). This is often referred to as “augmented reality” or “AR.” Head-mounted wearables can also completely obscure the user’s field of vision and display a virtual environment that the user can move or be moved by. This is often referred to as “virtual reality” or “VR.” In a hybrid form, a view of the surrounding environment is captured using a camera device, and then that view, along with augmentations, is displayed to the user on a display that obscures their eyes. As used herein, unless the context otherwise indicates, the term extended reality (XR) refers to augmented reality, virtual reality, and any hybrid of these technologies.

[0005] Wearable head-mounted devices can be used to provide XR experiences to users using XR technology. Other types of user devices, such as mobile devices with one or more cameras and displays, can also be used to provide XR experiences. During an XR experience, the user interacts with the XR user interface to perform various tasks or participate in entertainment activities. Attached Figure Description

[0006] In the accompanying drawings (which are not necessarily drawn to scale), similar reference numerals may describe similar parts in different views. To facilitate identification of any discussion of a particular element or action, one or more of the highest-order digits in the reference numerals indicate the drawing number in which the element was first introduced. Some non-limiting examples are shown in the figures:

[0007] Figure 1A These are stereoscopic images based on some examples of wearable head devices.

[0008] Figure 1BThe following are examples. Figure 1A Another view of the head-mounted wearable device.

[0009] Figure 2A This is a front view of a mobile device based on some examples.

[0010] Figure 2B This is a rear view of a mobile device based on some examples.

[0011] Figure 3 It is a graphical representation of a computer machine based on some examples, within which a set of instructions can be executed to cause the computer machine to perform any or more of the methods discussed herein.

[0012] Figure 4A It is a collaborative graph of the pipeline trained based on some example depth estimation models.

[0013] Figure 4B This is an activity diagram based on some examples of methods for generating synthetic 2D image data.

[0014] Figure 4C This is an activity graph of a depth estimation model training method based on some examples.

[0015] Figure 5A This is a sequence diagram illustrating XR session methods that utilize depth estimation models as components of an XR system, based on some examples.

[0016] Figure 5B It is a diagram generated from estimated depth data based on some examples.

[0017] Figure 6 These are illustrations of various XR effects based on some examples.

[0018] Figure 7 A system of head-worn wearable devices based on some examples is shown.

[0019] Figure 8 It is a graphical representation of the data structures maintained in the database based on some examples.

[0020] Figure 9 It is a diagrammatic representation of a networked environment in which the content of this disclosure can be deployed, based on some examples.

[0021] Figure 10 It is a graphical representation of a messaging system with both client-side and server-side functionalities, based on some examples.

[0022] Figure 11 This is a block diagram illustrating a software architecture based on some examples. Detailed Implementation

[0023] This disclosure relates to a method for estimating depth or distance to a user using 2D image data during an XR experience. Therefore, 3D information (e.g., depth) of the user's hand can be conveniently determined from 2D image data during an XR experience. The 3D information can then be used in various ways during the XR experience while reducing the computational load on the processing system used to generate the depth data. The estimated depth is used to provide the XR effect to the user within the context of the XR experience.

[0024] In some examples, the synthetic image training data generation method includes receiving 3D data of a hand and using the 3D data to generate a 3D model of the hand, wherein the 3D model includes depth data of the hand. The method also includes using the 3D model to generate synthetic 2D image data including synthetic 2D images. Target depth data including a depth dataset and a segmentation mask is generated using the synthetic 2D images and the 3D model. The synthetic 2D image data and the target depth data are used to train a depth estimation model.

[0025] In use, the XR system captures image data of a hand in a real-world scene and uses the image data and a depth estimation model to generate estimated depth data. The interactive system uses the estimated depth data and image data to generate XR effects for the XR experience and presents the XR experience, including the XR effects, to the user in the user interface.

[0026] In some examples, a detection model is used to detect the location of the hand in both the training and use of the depth estimation model. This location is used to generate cropping boundary data, which is then used to generate cropped synthetic 2D images for training the depth estimation model. Additionally, during the use of the depth estimation model, a detection model is employed to detect the location of the hand in image data captured by the XR system. This location is used to generate cropped image data. The XR system uses the cropped image and the depth estimation model to generate estimated depth data.

[0027] In some examples, the depth estimation model is trained to estimate the depth of limbs or parts of the human body, excluding hands, such as, but not limited to, arms, legs, feet, head, etc. Therefore, the synthesized 2D image is associated with limbs or parts of the human body. Additionally, the detection model is trained to detect limbs or parts of the human body, as well as designated landmarks of the limbs or body.

[0028] In some examples, the depth estimation model is trained to estimate the depth of a physical object. The physical object can be any type of physical object suitable for 3D scanning. Therefore, the synthetic 2D image is associated with the physical object. Additionally, a detection model is trained to detect objects and designated landmarks of those objects.

[0029] Other technical features may be readily apparent to those skilled in the art from the accompanying drawings, description and claims.

[0030] Head wearable devices

[0031] Figure 1A This is a perspective view of a head-mounted wearable device 100 based on some examples. The head-mounted wearable device 100 can be an XR system, for example... Figure 9 The client device of the computing system 902, or the head-worn device 100, can be a standalone XR system. The head-worn device 100 may include a frame 102 made of any suitable material, such as plastic, or a metal comprising any suitable shape memory alloy. In one or more examples, the frame 102 includes a first optical element holder or left optical element holder 104 (e.g., a display or lens holder) and a second optical element holder or right optical element holder 106 connected by a nose bridge 110. A first optical element or left optical element 152 and a second optical element or right optical element 108 may be disposed within the left optical element holder 104 and the right optical element holder 106, respectively. The right optical element 108 and left optical element 152 may be a lens, a display, a display assembly, or a combination thereof. Any suitable display assembly may be disposed within the head-worn device 100.

[0032] Frame 102 further includes a left arm or left temple 120 and a right arm or right temple 122. In some examples, frame 102 may be formed from a single piece of material to have a uniform or monolithic construction.

[0033] The head-mounted wearable device 100 may include a computing machine, such as computer 118, which may be of any suitable type to be carried by frame 102, and in one or more examples, may be of a suitable size and shape to be partially housed in one of the left temple piece 120 or the right temple piece 122. Computer 118 may include one or more processors with memory, a wireless communication circuitry, and a power supply. As discussed below, computer 118 includes a low-power circuitry system 728, a high-speed circuitry system 730, and a display processor. Various other examples may include these elements in different configurations or integrated in different ways. Additional details of the aspects of computer 118 may be implemented as shown in the computing machine 300 discussed herein.

[0034] The computer 118 additionally includes a battery 116 or other suitable portable power supply. In some examples, the battery 116 is disposed in the left temple 120 and electrically coupled to the computer 118 disposed in the right temple 122. The head-worn wearable device 100 may include a connector or port (not shown) for charging the battery 116, a wireless receiver, a transmitter or transceiver (not shown), or a combination of such devices.

[0035] The head-mounted wearable device 100 includes a first camera device or left camera device 112 and a second camera device or right camera device 114. Although two camera devices are depicted, other examples contemplate the use of a single or additional (i.e., more than two) camera devices.

[0036] In some examples, in addition to the left camera device 112 and the right camera device 114, the head-mounted wearable device 100 includes any number of input sensors or other input / output devices. Such sensors or input / output devices may additionally include biometric sensors, positioning sensors, motion sensors, etc. In some examples, motion sensors include accelerometer components (e.g., accelerometers), gravity sensor components, rotation sensor components (e.g., gyroscopes), etc. In some examples, motion sensors may be incorporated into inertial motion units (IMUs), etc.

[0037] In some examples, the head-worn device 100 identifies its position (location) and orientation in 3D space, where position and orientation together constitute the attitude of the head-worn device 100. In some examples, the attitude comprises six values: three for position in a 3D Cartesian coordinate system with three orthogonal axes (horizontal or X-axis, vertical or Y-axis, and depth or Z-axis), and three for rotation (pitch, yaw, and roll) about each corresponding axis. These six values ​​are simply referred to as the device's 6D attitude. In some examples, the attitude tracking components (not shown) of the head-worn device 100 include sensors and components such as, but not limited to, a set of cameras, a Global Positioning System (GPS), an IMU, a gravimeter, etc., whose outputs can be used to determine the attitude of the head-worn device 100.

[0038] In some examples, the left camera 112 and the right camera 114 provide tracking image data for use by the head-mounted wearable device 100 to determine 3D information from the real-world scene.

[0039] The head-wearable device 100 may also include a touchpad 124, which is mounted to or integrated with one or both of the left temple 120 and the right temple 122. The touchpad 124 is generally arranged vertically, and in some examples is approximately parallel to the user's temple. As used herein, generally vertical alignment means that the touchpad is more vertical than horizontal, although it may be more vertical than this. Additional user input may be provided via one or more buttons 126, which, in the illustrated example, are located on the outer upper edges of the left optics retainer 104 and the right optics retainer 106. The one or more touchpads 124 and buttons 126 provide a means by which the head-wearable device 100 can receive input from the user of the head-wearable device 100.

[0040] Figure 1B The head-worn device 100 is shown from the perspective of a user wearing it. For clarity, [the following text is incomplete and likely refers to a different viewpoint]. Figure 1B The middle part is omitted Figure 1A Many elements are shown in the diagram. For example... Figure 1A The above, Figure 1B The wearable head device 100 shown includes a left optical element 138 and a right optical element 142, which are respectively fixed in a left optical element holder 130 and a right optical element holder 134.

[0041] The head-mounted wearable device 100 includes: a right front optical assembly 128, which includes a left near-eye display 148 and a right near-eye display 132; and a left front optical assembly 140, which includes a left projector 144 and a right projector 150.

[0042] In some examples, the near-eye display is a waveguide. The waveguide includes reflective or diffractive structures (e.g., gratings and / or optical elements such as mirrors, lenses, or prisms). Light 136 emitted by the right projector 150 encounters the diffractive structure of the waveguide of the right near-eye display 132, which directs the light toward the user's right eye to provide an image on or in the right optical element 142, superimposed with a view of the real-world scene seen by the user. Similarly, light 146 emitted by the left projector 144 encounters the diffractive structure of the waveguide of the left near-eye display 148, which directs the light toward the user's left eye to provide an image on or in the left optical element 138, superimposed with a view of the real-world scene seen by the user. A combination of a graphics processing unit, an image display driver, a right front optical assembly 128, a left front optical assembly 140, a left optical element 138, and a right optical element 142 provides the optical engine for the head-mounted wearable device 100. The head-mounted wearable device 100 uses an optical engine to generate an overlay of the user's real-world scene view, including displaying a user interface to the user of the head-mounted wearable device 100.

[0043] However, it should be understood that other display technologies or configurations can be used within the optical engine to display images to the user in the user's field of view. For example, instead of projectors and waveguides, LCDs, LEDs, or other display panels or surfaces can be provided.

[0044] In use, the user of the head-mounted wearable device 100 will see information, content, and various user interfaces on a near-eye display. As described in more detail herein, the user can then use the touchpad 124 and / or buttons 126 on associated devices (e.g., Figure 7 The device interacts with the head-worn device 100 by touch input or voice input on the mobile device 714 shown, and / or by hand movements, positioning and location recognized by the head-worn device 100.

[0045] In some examples, the optical engine of the XR system is incorporated into a lens, such as a contact lens, that comes into contact with the user's eye. The XR system uses the contact lens to generate images for the XR experience.

[0046] In some examples, the head-mounted wearable device 100 includes an XR system. In some examples, the head-mounted wearable device 100 is a component of an XR system that includes additional computing components. In some examples, the head-mounted wearable device 100 is a component of an XR system that includes additional user input systems or devices.

[0047] mobile device

[0048] Figure 2A It is based on the front view of some example mobile devices 206, and Figure 2BThis is a rear view of a mobile device 206 based on some examples. The mobile device 206 can be an XR system such as... Figure 9 The client device of the computing system 902, or mobile device 206, can be a standalone XR system. Mobile device 206 includes a screen 208 configured to display images of an XR experience to a user. In some examples, screen 208 is a touchscreen configured to receive user input. In some examples, mobile device 206 includes one or more physical input devices (not shown), such as, but not limited to, buttons, switches, etc., configured to receive user input.

[0049] Mobile device 206 includes computing machinery, such as computer 204, which can be of any suitable type for housing in mobile device 206. Computer 204 may include one or more processors having memory, wireless communication circuitry, and power supply. Additional details of various aspects of computer 204 may be implemented as shown in computing machinery 300 discussed herein.

[0050] Mobile device 206 includes one or more camera devices 202. In some examples, in addition to one or more camera devices 202, head-mounted wearable device 100 also includes any number of input sensors or other input / output devices. Such sensors or input / output devices may additionally include biometric sensors, positioning sensors, motion sensors, etc. Any biometric data collected by the biometric components is captured and stored only with user approval and is deleted upon user request. Furthermore, such biometric data may be used for very limited purposes, such as authentication. To ensure the restricted and authorized use of biometric information and other personally identifiable information (PII), access to the data is limited to authorized personnel (if any). Any use of biometric data may be strictly limited to authentication purposes, and biometric data may not be shared or sold to any third party without the user's explicit consent. In addition, appropriate technical and organizational measures are implemented to ensure the security and confidentiality of this sensitive information.

[0051] In some examples, one or more camera devices 202 provide image data for use by mobile device 206 to determine 3D information from real-world scenes.

[0052] The combination of a graphics processing unit (GPU), an image display driver, and a screen 208 provides the optical engine for the mobile device 206. The mobile device 206 uses the optical engine to generate an overlay of the user's real-world scene view, including displaying the user interface to the user on the mobile device 206.

[0053] However, it should be understood that other display technologies or configurations can be used within the optical engine to display images to the user within their field of view. For example, LCD, LED, or other display panels or surfaces can be provided.

[0054] In use, information, content, and various user interfaces will be presented to the user of the mobile device 206 on screen 208. As described in more detail herein, the user can then interact with the mobile device 206 using methods and devices, including but not limited to touchscreens, touchpads, a set of buttons and / or a set of switches, voice input or touch input on associated devices and / or hand movements, positioning, and location recognized by the mobile device 206.

[0055] In some examples, in addition to the camera unit 202, the mobile device 206 includes any number of input sensors or other input / output devices. Such sensors or input / output devices may additionally include biometric sensors, positioning sensors, motion sensors, etc. Any biometric data collected by the biometric component is captured and stored only with user approval and is deleted upon user request. Furthermore, such biometric data may be used for very limited purposes, such as authentication. To ensure restricted and authorized use of biometric information and other personally identifiable information (PII), access to the data is limited to authorized personnel (if any). Any use of biometric data may be strictly limited to authentication purposes, and biometric data may not be shared or sold to any third party without the user's explicit consent. Additionally, appropriate technical and organizational measures are implemented to ensure the security and confidentiality of this sensitive information.

[0056] In some examples, motion sensors include accelerometer components (e.g., accelerometers), gravity sensor components, rotation sensor components (e.g., gyroscopes), etc. In some examples, motion sensors may be incorporated into an IMU, etc.

[0057] In some examples, the mobile device 206 identifies its position (location) and orientation in 3D space, where position and orientation together constitute the attitude of the mobile device 206. In some examples, the attitude comprises six values: three for position in a 3D Cartesian coordinate system with three orthogonal axes (horizontal or X-axis, vertical or Y-axis, and depth or Z-axis), and three for rotation (pitch, yaw, and roll) about each corresponding axis. These six values ​​are simply referred to as the 6D attitude of the mobile device 206. In some examples, the attitude tracking components of the mobile device 206 (not shown) include sensors and components such as, but not limited to, a set of cameras, a Global Positioning System (GPS), an IMU, a gravimeter, etc., whose outputs can be used to determine the attitude of the mobile device 206.

[0058] In some examples, mobile device 206 includes an XR system. In some examples, mobile device 206 is a component of an XR system that includes additional computing components. In some examples, mobile device 206 is a component of an XR system that includes additional user input systems or devices.

[0059] Computer Machine Architecture

[0060] Figure 3 This is a schematic representation of a computing machine 300 within which instructions 302 (e.g., software, programs, applications, applets, or other executable code) can be executed to cause the computing machine 300 to perform any or more of the methods discussed herein. For example, instructions 302 can cause the computing machine 300 to perform any or more of the methods described herein. Instructions 302 transform a general, unprogrammed computing machine into a specific computing machine 300 programmed to perform the described and illustrated functions in the described manner. The computing machine 300 can operate as a standalone device or can be coupled (e.g., networked) to other computing machines. In a networked deployment, the computing machine 300 can operate as a server computing machine or a client computing machine in a server-client network environment, or as a peer computing machine in a peer-to-peer (or distributed) network environment. The computing machine 300 may include, but is not limited to, a server computer, client computer, personal computer (PC), tablet computer, laptop computer, netbook, set-top box (STB), personal digital assistant (PDA), entertainment media system, cellular phone, smartphone, mobile device, wearable device (e.g., smartwatch), smart home device (e.g., smart appliance), other smart device, web device, network router, network switch, network bridge, or any computing machine capable of sequentially or otherwise executing instructions 302 specifying actions to be taken by the computing machine 300. Furthermore, although a single computing machine 300 is shown, the term "computing machine" should also be considered as a collection of computing machines that individually or jointly execute instructions 302 to perform any or more of the methods discussed herein. For example, the computing machine 300 may include computing system 902 or any one of a plurality of server devices forming part of interactive server system 910. In some examples, the computing machine 300 may also include both a client system and a server system, wherein certain operations of a particular method or algorithm are performed on the server side and certain operations of a particular method or algorithm are performed on the client side.

[0061] The computing machine 300 may include a processor 304, a memory 306, and an input / output (I / O) unit 308 that can be configured to communicate with each other via a bus 310. In the example, processor 304 (e.g., a central processing unit (CPU), a reduced instruction set computing (RISC) processor, a complex instruction set computing (CISC) processor, a graphics processing unit (GPU), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a radio frequency integrated circuit (RFIC), another processor, or any suitable combination thereof) may include, for example, processors 312 and 314 that execute instruction 302. The term "processor" is intended to include multi-core processors, which may include two or more independent processors (sometimes referred to as "cores") capable of executing instructions simultaneously. Although Figure 3 Multiple processors 304 are shown, but computing machine 300 may include a single processor with a single core, a single processor with multiple cores (e.g., a multi-core processor), multiple processors with a single core, multiple processors with multiple cores, or any combination thereof.

[0062] Memory 306 includes main memory 316, static memory 318, and storage cells 320, all of which are accessible by processor 304 via bus 310. Main memory 306, static memory 318, and storage cells 320 store instructions 302 embodying any one or more of the methods or functions described herein. Instructions 302 may also reside wholly or partially in main memory 316, in static memory 318, in machine-readable medium 322 within storage cell 320, in at least one processor of processor 304 (e.g., in the processor's cache memory), or in any suitable combination thereof during execution by computer 300.

[0063] I / O component 308 may include various components for receiving input, providing output, generating output, sending information, exchanging information, capturing measurements, etc. The specific I / O component 308 included in a particular computer will depend on the type of computer. For example, a portable computer such as a mobile phone may include a touch input device or other such input mechanism, while a headless server computer may not include such a touch input device. It should be understood that I / O component 308 may include... Figure 3Many other components are not shown. In various examples, I / O component 308 may include user output component 324 and user input component 326. User output component 324 may include visual components (e.g., displays such as plasma display panels (PDPs), light-emitting diode (LED) displays, liquid crystal displays (LCDs), projectors, or cathode ray tube (CRT) displays), acoustic components (e.g., speakers), haptic components (e.g., vibration motors, resistance mechanisms), other signal generators, etc. User input component 326 may include alphanumeric input components (e.g., keyboards, touchscreens configured to receive alphanumeric input, photoelectric keyboards, or other alphanumeric input components), pointing-based input components (e.g., mice, touchpads, trackballs, joysticks, motion sensors, or other pointing instruments), haptic input components (e.g., physical buttons, touchscreens or other haptic input components that provide positioning and force for touch or touch gestures), audio input components (e.g., microphones), etc.

[0064] In another example, I / O component 308 may include biometric component 328, motion component 330, environmental component 332, or position component 334, and various other components. For example, biometric component 328 includes components for detecting expressions (e.g., hand expressions, facial expressions, voice expressions, body posture, or eye tracking), measuring biosignals (e.g., blood pressure, heart rate, body temperature, sweating, or brain waves), and identifying people (e.g., voice recognition, retinal recognition, facial recognition, fingerprint recognition, or EEG-based recognition). Motion component 330 includes: accelerometer component (e.g., accelerometer), gravity sensor component, and rotation sensor component (e.g., gyroscope).

[0065] Environmental component 332 includes, for example, one or more camera devices (with still image / photograph and video capabilities), lighting sensor components (e.g., photometers), temperature sensor components (e.g., one or more thermometers for detecting ambient temperature), humidity sensor components, pressure sensor components (e.g., barometers), acoustic sensor components (e.g., one or more microphones for detecting background noise), proximity sensor components (e.g., infrared sensors for detecting nearby objects), gas sensors (e.g., gas detection sensors for detecting the concentration of hazardous gases for safety purposes or for measuring pollutants in the atmosphere), depth or distance sensors (e.g., sensors for determining the distance to an object or for determining the depth of object features in a 3D coordinate system), or other components that can provide indications, measurements, or signals corresponding to the surrounding physical environment.

[0066] Regarding the camera device, the computing system 902 may have a camera device system including, for example, a front-facing camera on the front surface of the computing system 902 and a rear-facing camera on the rear surface of the computing system 902. The front-facing camera may be used, for example, to capture still images and videos (e.g., "selfies") of the user of the computing system 902, which can then be enhanced with the enhancement data (e.g., filters) described above. The rear-facing camera may be used, for example, to capture still images and videos in a more conventional camera device mode, wherein these images are similarly enhanced with the enhancement data. In addition to the front-facing and rear-facing cameras, the computing system 902 may also include a 360° camera for capturing 360° photos and videos.

[0067] Furthermore, the camera system of the computing system 902 may include dual rear cameras (e.g., a main camera and a depth-sensing camera), or even include triple, quadruple, or quintuple rear camera configurations on the front and rear sides of the computing system 902. For example, these multiple camera systems may include wide-angle cameras, ultra-wide-angle cameras, telephoto cameras, macro cameras, and depth sensors.

[0068] The position component 334 includes a positioning sensor component (e.g., a GPS receiver component), an altitude sensor component (e.g., an altimeter or barometer that detects air pressure and from which altitude can be obtained), an orientation sensor component (e.g., a magnetometer), etc.

[0069] A wide variety of technologies can be used to implement communication. I / O component 308 also includes a communication component 336 operable to couple computer 300 to network 338 or device 340 via a suitable coupling or connection. For example, communication component 336 may include a network interface component or other suitable device that interfaces with network 338. In further examples, communication component 336 may include wired communication components, wireless communication components, cellular communication components, near field communication (NFC) components, etc. Components (e.g.) (low power consumption) Components and other communication components for providing communication via other modes. Device 340 can be another computing machine or any peripheral device of various peripheral devices (e.g., a peripheral device coupled via USB).

[0070] Furthermore, communication component 336 can detect identifiers, or include components operable to detect identifiers. For example, communication component 336 may include a radio frequency identification (RFID) tag reader component, an NFC smart tag detection component, an optical reader component (e.g., an optical sensor for detecting one-dimensional barcodes such as Universal Product Code (UPC) barcodes, multi-dimensional barcodes such as Quick Response (QR) codes, Aztec codes, Data Matrix, Dataglyph, MaxiCode, PDF417, UltraCode, UCC RSS-2D barcodes, and other optical codes), or an acoustic detection component (e.g., a microphone for identifying audio signals from the tag). Additionally, various information can be derived via communication component 336, such as location derived via Internet Protocol (IP) geolocation, etc. Location can be obtained through signal triangulation or by detecting NFC beacon signals that indicate a specific location.

[0071] Various memories (e.g., main memory 316, static memory 318, and the memory of processor 304) and storage units 320 may store one or more sets of instructions and data structures (e.g., software) embodied or used by any or more of the methods or functions described herein. These instructions (e.g., instruction 302) cause various operations to implement the disclosed examples when executed by processor 304.

[0072] Instruction 302 can be sent or received over network 338 via a transmission medium using a network interface device (e.g., a network interface component included in communication component 336) and using any of several known transmission protocols (e.g., Hypertext Transfer Protocol (HTTP)). Similarly, instruction 302 can be sent or received via a transmission medium through a coupling to device 340 (e.g., a peer-to-peer coupling).

[0073] Depth estimation

[0074] Figure 4A The collaboration graph for pipeline 400a is trained based on depth estimation models from some examples. Figure 4B It is an activity graph generated based on some examples of synthetic image data generation method 400b, and Figure 4C This is an activity diagram of a depth estimation model training method 400c based on some examples. The depth estimation model training pipeline 400a is used by a data processing system such as a computing machine 300 to generate a depth estimation model 430, which is used to estimate the depth of objects in a real-world scene during an XR experience provided to a user.

[0075] Reference Figure 4A and Figure 4B In operation 402, the synthetic image generation unit 420 receives 3D data 432 comprising one or more dimensional measurement datasets 434 of a hand, including one or more measurements. The dimensional measurement dataset 434 comprises measurements of the hand obtained when the hand is held in various poses. For example, various methods can be used to generate the dimensional measurement dataset 434 of the 3D data 432. In some examples, the dimensional measurement dataset 434 includes a point cloud of the hand, wherein the point cloud comprises a set of 3D points identified in a 3D coordinate system. The point cloud of an object, such as a measured hand, can be generated by any number of dimensional measurement methods used to obtain dimensional measurements of a physical object, such as, but not limited to, contact-based scanning using physical contact probes, laser triangulation using scanning or point lasers, structured light scanning, time-of-flight scanning, photogrammetry using multiple camera devices, etc.

[0076] The image synthesis generation component 420 generates one or more measured 3D model data 440 of a hand using the dimensional measurement dataset 434 of the 3D data 432. For example, for each dimensional measurement dataset 434 of the 3D data 432, the image synthesis generation component 420 generates a corresponding 3D model 442 comprising a 3D mesh of 3D points in a point cloud, which includes the dimensional measurement dataset 434 of the hand in a pose. In some examples, the 3D data of the dimensional measurement dataset 434 is downsampled by averaging a subset of the 3D points in the point cloud of the dimensional measurement dataset 434. In some examples, the 3D data of the dimensional measurement dataset 434 is upsampled by generating interpolated 3D points using a subset of the 3D points in the point cloud of the dimensional measurement dataset 434.

[0077] In operation 404, the composite image generation unit 420 uses one or more measured 3D model data of the hand to generate composite 2D image data 422, including composite 2D images such as composite 2D image 436. For example, for each 3D model 442 of 3D model data 440, the composite image generation unit 420 uses the 3D model 442 and camera device and lighting parameter data 418 to generate composite 2D image 436, the camera device and lighting parameter data 418 including a set 448 of camera device and lighting parameters, such as, but not limited to, lighting level, lighting angle, camera device angle, and camera device distance, to generate composite 2D image 436. The composite image generation unit 420 applies texture to the 3D model 442 using a specified lighting angle and lighting level of the camera device and the lighting parameter data 418. The composite image generation unit 420 projects the textured 3D model onto a 2D plane to generate composite 2D image 436 using a specified camera device angle and camera device distance relative to the 3D model 442. In some examples, multiple combinations of lighting level, lighting angle, camera angle, and camera distance are used to create multiple synthetic 2D images 436 based on each 3D model 442. In some examples, the values ​​of lighting level, lighting angle, camera angle, and camera distance are randomized. Upon completion of the generation process, the synthetic 2D image data 422 comprises a set of synthetic 2D images 436 simulating various hands in various poses or positions, as if the images were captured by a physical camera under various lighting conditions, camera angles, and camera distances.

[0078] In operation 406, the composite image generation unit 420 generates target depth data 424 using composite 2D image data 422 and 3D model data 440. The target depth data 424 includes a depth set 438, which is the depth of a hand from a camera device of an XR system, capturing image data of the hand for an XR experience provided to a user by the XR system. The target depth data 424 also includes a segmentation mask 450 for the composite 2D image 436, which is used to identify and assign attributes to portions of the composite 2D image 436, such as, but not limited to, assigning depth data to landmarks of the hand depicted in the composite 2D image 436, and assigning depth data to individual pixels of the composite 2D image 436. For example, the 3D model data 440 includes 3D points in a three-dimensional coordinate system having an X-axis, Y-axis, Z-axis, a defined origin, and defined units of measurement. The image synthesis generation component 420 applies a transformation to 3D points to transform them into an XR3D coordinate system with a horizontal axis (X), a vertical axis (Y), and a depth axis (Z). In use, the depth estimation model 430 estimates depth values ​​using a 2D image of a hand captured in a real-world scene. The depth values ​​are measured from designated landmarks on the hand, which serve as the origin or reference point. Therefore, when generating target depth data 424, the image synthesis generation component 420 determines the depth value of each pixel in the synthesized 2D image 436 of the synthesized 2D image data 422 based on the designated landmarks of the hand depicted in the synthesized 2D image 436. The target depth data 424 and the synthesized 2D image data 422 generated by the image synthesis generation component 420 are used to train the depth estimation model 430, as shown in the reference. Figure 4C A more complete description.

[0079] In some examples, the specified landmark is the wrist of the hand determined from the 3D model data 440.

[0080] In some examples, the segmentation mask 450 of the target depth data 424 is manually annotated to identify parts of the synthetic 2D image 436.

[0081] In some examples, 3D data 432 represents a limb or part of the human body other than the hand, such as, but not limited to, arms, legs, feet, head, etc. Therefore, target depth data 424 and synthetic 2D image data 422 are associated with limbs or parts of the human body. Additionally, detection model 426 is trained to detect limbs or parts of the human body, as well as designated landmarks of the limbs or body.

[0082] In some examples, 3D data 432 includes scans of physical objects other than hands. The physical object can be any type of physical object suitable for 3D scanning. Therefore, target depth data 424 and synthetic 2D image data 422 are associated with the physical object. Additionally, a detection model 426 is trained to detect the object and its designated landmarks.

[0083] Reference Figure 4A and Figure 4C In operation 408, the depth estimation training unit 428 receives depth model training data 446. For example, the depth model training data 446 includes... Figure 4B The synthesized 2D image data 422 includes a synthesized 2D image 436, and the target depth data 424 includes a depth set 438 corresponding to the corresponding synthesized 2D image 436 of the synthesized 2D image data 422 and a segmentation mask 450. Figure 4B (Both). Synthetic 2D image data 422 and target depth data 424 provide tuples of synthetic 2D images 436 paired with depth set 438 and segmentation mask 450. Depth model training data 446 also includes model parameters 444 of depth estimation model 430. Depth estimation training component 428 trains depth estimation model 430 using tuples of synthetic 2D images 436, depth set 438 and segmentation mask 450, and model parameters 444. Model parameters 444 include parameters or coefficients of depth estimation model 430. During training, the input-output pairings of the tuples are trained to fit model parameters 444. After fitting model parameters 444 (after training), depth estimation model 430 uses model parameters 444 to generate estimated depth sets and estimated segmentation masks using image data captured by the XR system during an XR session.

[0084] In operation 410, the depth estimation training component 428 uses computer vision methods to detect the localization of the hand and designated landmarks in the synthetic 2D image 436. The computer vision methods include, but are not limited to, Harris corner detection, Shi-Tomasi corner detection, Scale Invariant Feature Transform (SIFT), Speed-Up Robust Features (SURF), Speed-Up Segmentation Test Features (FAST), Oriented FAST, and Rotation BRIEF (ORB).

[0085] In some examples, the depth estimation training component 428 uses artificial intelligence methods and a detection model 426 previously generated using machine learning methods to detect the localization of the hand and designated landmarks. In some examples, the detection model 426 includes, but is not limited to, neural networks, learned vector quantization networks, logistic regression models, support vector machines, random decision forests, Naive Bayes models, linear discriminant analysis models, K-nearest neighbor models, etc. In some examples, the machine learning methods may include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, dimensionality reduction, self-learning, feature learning, sparse dictionary learning, anomaly detection, etc.

[0086] In some examples, the depth estimation training component 428 uses the detection model 426 to generate predicted distances from specified landmarks on the hand in the synthetic 2D image 436 to a camera device located in the XR system that captures images of the hand during the XR experience provided to the user by the XR system.

[0087] In some examples, the specified landmark is the wrist of the hand.

[0088] In operation 412, the depth estimation training unit 428 generates cropping boundary data, such as but not limited to bounding box data, for each of the synthesized 2D images 436 based on the localization of the detected hand and designated landmark in the synthesized 2D image. For example, in a synthesized 2D image composed of pixels organized by rows and columns, the depth estimation training unit 428 determines the leftmost pixel among the pixels including the detected hand and designated landmark, and sets a left boundary one pixel column to the left of the leftmost pixel. In a similar manner, the depth estimation training unit 428 determines the topmost pixel among the pixels including the detected hand and designated landmark, and sets an upper cropping boundary one row above the topmost pixel; determines the bottommost pixel among the pixels including the detected hand and designated landmark, and sets a lower cropping boundary one row below the bottommost pixel; and determines the rightmost pixel among the pixels including the detected hand and designated landmark, and sets a right cropping boundary one pixel column to the right of the rightmost pixel.

[0089] In operation 414, the depth estimation training unit 428 generates a cropped synthetic 2D image by cropping each synthetic 2D image 436 using corresponding cropping boundary data. For example, the depth estimation training unit 428 crops all pixels to the left of the left cropping boundary, to the right of the right cropping boundary, above the upper cropping boundary, and below the lower cropping boundary in the synthetic 2D image 436.

[0090] In operation 416, the depth estimation training component 428 generates a depth estimation model 430 using a cropped synthetic 2D image and target depth data 424. For example, the depth estimation training component 428 trains the depth estimation model 430 using tuples of paired synthetic 2D images 436 and a depth set 438 based on one or more machine learning techniques. For example, the depth estimation training component 428 can train model parameters 444 by minimizing a loss function using a benchmark ground truth of the target depth data 424. For example, the loss function can use the depth set 438 of the target depth data 424, a segmentation mask 450 of the target depth data 424, or a combination of the depth set 438 and the segmentation mask 450.

[0091] The depth estimation model 430 may include any one or a combination of classifiers or neural networks such as artificial neural networks, convolutional neural networks, adversarial networks, generative adversarial networks, deep feedforward networks, radial basis function networks, recurrent neural networks, long / short-term memory networks, gated recurrent units, autoencoders, variational autoencoders, denoising autoencoders, sparse autoencoders, Markov chains, Hopfield networks, Boltzmann machines, restricted Boltzmann machines, deep belief networks, deep convolutional networks, deconvolutional networks, deep convolutional inverse graph networks, liquid machines, extreme learning machines, echo state networks, deep residual networks, Kohonen networks, support vector machines, and neural Turing machines.

[0092] In some examples, the derivative of the loss function is calculated by comparing the estimated depth set of the synthetic 2D image 436 with the ground truth value of the paired depth set 438 of the synthetic 2D image 436. The calculated derivative of the loss function is used to update the model parameters 444 of the depth estimation model 430.

[0093] In some examples, the derivative of the loss function is calculated by comparing the estimated segmentation mask of the synthetic 2D image 436 with the ground truth value of the paired segmentation mask 450 of the synthetic 2D image 436. The calculated derivative of the loss function is used to update the model parameters 444 of the depth estimation model 430.

[0094] In some examples, the derivative of the loss function is calculated by comparing the estimated depth set 542 and estimated segmentation mask 544 of the synthetic 2D image 436 with the ground truth values ​​of the paired depth set 438 and segmentation mask 450 of the synthetic 2D image 436. The calculated derivative of the loss function is used to update the model parameters 444 of the depth estimation model 430.

[0095] The model parameters 444 of the depth estimation model 430 are trained, adapted, or optimized by minimizing the loss function of a set of multiple synthetic 2D image data 422 and target depth data 424. In this way, the depth estimation model 430 is trained to establish a relationship between images including image data of a hand captured in a real-world scene and a set of depth data of the hand, as referenced. Figure 5A A more complete description.

[0096] In some examples, the depth estimation model 430 is trained to generate segments of the synthetic 2D image 436. For example, the synthetic 2D image 436 is annotated to identify specified parts of the hand, such as, but not limited to, fingers, thumb, palm, back of hand, wrist, etc.

[0097] In some examples, the depth model training data 446 is a limb or part of the human body other than the hand, such as, but not limited to, the arm, leg, foot, head, etc. Therefore, the target depth data 424 and the synthetic 2D image data 422 are associated with a limb or part of the human body. Additionally, the detection model 426 is trained to detect limbs or parts of the human body and designated landmarks of the limb or human body.

[0098] In some examples, the deep model training data 446 is a physical object. Therefore, the target depth data 424 and the synthetic 2D image data 422 are associated with the object. Additionally, the detection model 426 is trained to detect the object and its designated landmarks.

[0099] Figure 5A This is a sequence diagram illustrating an XR session method 500a that utilizes a depth estimation model 430 as a component of an XR system 512, based on some examples. Figure 5B This is an illustration of depth estimation method 500b based on some examples. XR system 512 uses XR session method 500a to provide user 516 with an XR experience 510 of interactive application 528.

[0100] In operation 502, the interactive application 528 uses one or more camera devices 530 of the XR system 512 to capture image data 520 of a real-world scene 518, which includes one or more images 536 within the real-world scene 518. The one or more camera devices 530 transmit the image data 520 to the depth estimation unit 526 and the interactive application 528. In some examples, the image data 520 includes monocular red-green-blue (RGB) image data captured by a single camera device of the XR system 512.

[0101] In operation 504, depth estimation unit 526 receives image data 520. Depth estimation unit 526 uses image data 520 and depth estimation model 430 to generate estimated depth data 522 for each hand 546 included in images 536 of image data 520 captured by one or more camera devices 530. For example, depth estimation unit 526 detects the position of the hand and designated landmarks of the hand 546 in images 536 of image data 520. For example, depth estimation training unit 428 uses computer vision methods to detect the localization of the hand 546 and designated landmarks in images 536, including but not limited to Harris corner detection, Shi-Tomasi corner detection, Scale Invariant Feature Transform (SIFT), Speed-Up Robust Features (SURF), Speed-Up Segmentation Test Features (FAST), Oriented FAST, and Rotation BRIEF (ORB).

[0102] In some examples, the depth estimation component 526 uses artificial intelligence methods and a detection model 426 previously generated using machine learning methods to detect the localization of the hand 546 and designated landmarks. In some examples, the detection model 426 includes, but is not limited to, neural networks, learned vector quantization networks, logistic regression models, support vector machines, random decision forests, Naive Bayes models, linear discriminant analysis models, K-nearest neighbor models, etc. In some examples, the machine learning methods may include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, dimensionality reduction, self-learning, feature learning, sparse dictionary learning, anomaly detection, etc. In some examples, the depth estimation component 526 uses the detection model 426 to generate estimated distances between one or more camera devices 530 from the captured image data 520 and the designated landmarks of the hand 546.

[0103] Depth estimation component 526 generates cropping boundary data using the localization of the detected hand 546 and designated landmarks. Using the cropping boundary data, depth estimation component 526 generates a cropped image 540 of image 536 by cropping image 536 to the detected hand 546 and designated landmarks, as described with reference to the trained depth estimation model 430. Depth estimation component 526 generates estimated depth data 522 using depth estimation model 430 and the cropped image 540 of cropped image data 538. Estimated depth data 522 includes an estimated depth set 542 of the hand 546 in image 536 and an estimated segmentation mask 544. The estimated depth set 542 is an estimate or prediction of the depth from the designated landmarks of the detected hand 546 for each foreground pixel in image 536 associated with the hand 546. The estimated segmentation mask 544 includes a segmentation mask for each pixel. The combination of detecting the hand 546 in image 536 of image data 520, cropping image 536 to the hand 546 and specified landmarks of the hand 546, and generating an estimated depth set 542 of the hand 546 using the cropped version of image 536 enables dense reconstruction of the hand 546 in metric space.

[0104] In operation 506, the interactive application 528 receives estimated depth data 522 and uses the estimated depth data 522 to generate XR experience image data 524. For example, the estimated depth data 522 is a hand 546 in an image 536 of a real-world scene 518. The estimated depth set 542 may include a 3D point cloud defining the surface of the hand 546 in the XR 3D coordinate system of the XR system 512. Therefore, the estimated depth data 522 includes a partial 3D model that can be used by the XR system 512 to generate XR effects such as, but not limited to, XR effect 602, XR effect 604, XR effect 606, and XR effect 608. Figure 6 (All of the above). The interactive application 528 uses image data 520 and an estimated depth set 542 to generate XR experience image data 524 for the XR experience 510. The interactive application 528 transmits the XR experience image data 524 to the image processing unit 514 of the XR system 512.

[0105] In operation 508, the image processing unit 514 receives XR experience image data 524 from the interactive application 528. The image processing unit 514 uses the XR experience image data 524 to generate user interface data 532 for the XR experience 510. The image processing unit 514 uses the user interface data 532 to provide the XR experience 510, including the XR experience image data 524, to the user 516 via the display 534 of the XR system 512.

[0106] In some examples, the XR system 512 operates on image data 520 of human body parts other than the hands, such as, but not limited to, arms, legs, feet, head, etc. Therefore, image 536 and the estimated depth set 542 and estimated segmentation mask 544 generated using image 536 are associated with limbs or parts of the human body. Detection model 426 is trained to detect limbs or parts of the human body and designated landmarks of the limbs or human body, and depth estimation model 430 is trained to generate the estimated depth set 542 for limbs or parts of the human body.

[0107] In some examples, the XR system 512 operates on image data 520 of physical objects other than hands. The physical object can be any type of physical object suitable for imaging using one or more camera devices 530. Therefore, image 536 and the estimated depth set 542 and estimated segmentation mask 544 generated using image 536 are associated with the physical object. Additionally, detection model 426 is trained to detect objects and specified landmarks of the objects, and depth estimation model 430 is trained to generate the estimated depth set 542 of the objects.

[0108] In some examples, the XR system 512 continuously repeats the operation of the XR session method 500a in order to provide the XR experience 510 to the user 516 in real time.

[0109] In some examples, the operation of interactive application 528 is distributed across a network. For example, interactive application 528 is a web application that connects to a server via a network such as, but not limited to, the Internet. Interactive application 528 transmits image data 520 to the server, and the server generates XR experience image data 524 and transmits the XR experience image data 524 to interactive application 528 via the network.

[0110] In some examples, the interactive application 528 synthesizes image data 520 and XR experience image data 524, and transmits the synthesized image data to the image processing unit 514. The image processing unit 514 receives the synthesized image data and uses it to generate user interface data 532.

[0111] Figure 6 These are illustrations of various XR effects based on some examples. Figure 5A The XR system 512 uses estimated depth data 522 generated by depth estimation model 430 to generate XR effects. The XR effect 602 is achieved using (…). Figure 5BAn illustration of reshaping and / or relighting shader effects using the estimated depth set 542. An XR effect 604 is an illustration of depth-based interaction with physical objects such as, but not limited to, sheets of liquid, using the estimated depth set 542. An XR effect 606 is an illustration of reconstructing a point cloud from a single image using the estimated depth set 542. An XR effect 608 is an illustration of realistic occlusion of virtual objects using the estimated depth set 542.

[0112] Systems with head-worn devices

[0113] Figure 7 A system 700, including a head-worn wearable device 718 with a selector input device, is shown according to some examples. Figure 7 This is a high-level functional block diagram of an example head-mounted wearable device 718 that is communicatively coupled to a mobile device 714 and various server systems 704 (e.g., interactive server system 910) via various networks 908.

[0114] The head-mounted wearable device 718 includes one or more camera devices, each of which may be, for example, a visible light camera 708, an infrared emitter 710, and an infrared camera 712.

[0115] The mobile device 714 connects to the head-mounted wearable device 718 using both low-power wireless connectivity 716 and high-speed wireless connectivity 720. The mobile device 714 also connects to server system 704 and network 706.

[0116] The head-worn device 718 also includes two image displays in the image display 722 of the optical components. The two image displays 722 of the optical components include one image display associated with the left lateral side of the head-worn device 718 and one image display associated with the right lateral side of the head-worn device 718. The head-worn device 718 also includes an image display driver 724, an image processor 726, a low-power circuitry system 728, and a high-speed circuitry system 730. The image displays 722 of the optical components are used to present images and videos to the user of the head-worn device 718, including images that may include a graphical user interface.

[0117] The image display driver 724 commands and controls the image display 722 of the optical components. The image display driver 724 can directly deliver image data to the image display 722 of the optical components for presentation, or it can convert the image data into a signal or data format suitable for delivery to the image display device. For example, the image data can be video data formatted according to compression formats such as H.264 (MPEG-4 Part 10), HEVC, Theora, Dirac, RealVideo RV40, VP8, VP9, ​​etc., and still image data can be formatted according to compression formats such as Portable Network Group (PNG), Joint Photographic Experts Group (JPEG), Tag Image File Format (TIFF), or Exchangeable Image File Format (EXIF), etc.

[0118] The head-wearable device 718 includes a frame and a pole (or temple) extending laterally from the frame. The head-wearable device 718 also includes a user input device 732 (e.g., a touch sensor or a press button), comprising an input surface on the head-wearable device 718. The user input device 732 (e.g., a touch sensor or a press button) is used to receive input selections from the user to manipulate a graphical user interface of the presented image.

[0119] Figure 7 The components shown for the head-wearable device 718 are located on one or more circuit boards, such as PCBs or flexible PCBs, in the frame or temples. Alternatively or additionally, the depicted components may be located in the blocks, frames, hinges, or nose bridge of the head-wearable device 718. The left and right visible light camera devices 708 may include digital camera elements, such as complementary metal-oxide-semiconductor (CMOS) image sensors, charge-coupled devices, camera lenses, or any other corresponding visible light or light-capturing elements that can be used to capture data, including images of scenes with unknown objects.

[0120] The head-mounted wearable device 718 includes a memory 702 that stores instructions for performing a subset or all of the functions described herein. The memory 702 may also include a storage device.

[0121] like Figure 7As shown, the high-speed circuit system 730 includes a high-speed processor 734, a memory 702, and a high-speed wireless circuit system 736. In some examples, an image display driver 724 is coupled to the high-speed circuit system 730 and operated by the high-speed processor 734 to drive the left and right image displays of the image display 722 of the optical components. The high-speed processor 734 can be any processor capable of managing the high-speed communication and operation of any general-purpose computing system required by the head-worn device 718. The high-speed processor 734 includes the processing resources required to manage high-speed data transmission over the high-speed wireless connection 720 to a wireless local area network (WLAN) using the high-speed wireless circuit system 736. In some examples, the high-speed processor 734 executes an operating system for the head-worn device 718, such as a LINUX operating system or another such operating system, and this operating system is stored in the memory 702 for execution. Among other duties, the high-speed processor 734, which executes the software architecture for the head-worn device 718, manages data transmission with the high-speed wireless circuit system 736. In some examples, the high-speed wireless circuit system 736 is configured to implement the Institute of Electrical and Electronics Engineers (IEEE) 802.11 communication standard, also referred to herein as WiFi. In some examples, the high-speed wireless circuit system 736 may implement other high-speed communication standards.

[0122] The low-power wireless circuit system 738 and high-speed wireless circuit system 736 of the head-mounted wearable device 718 may include a short-range transceiver (Bluetooth). TM The device 714 (including transceivers communicating via low-power wireless connection 716 and high-speed wireless connection 720) can be implemented using the architectural details of the head-mounted wearable device 718, or using other components of the network 706.

[0123] Memory 702 includes any storage device capable of storing various data and applications, including camera data generated by the left and right visible light imaging devices 708 and 708, the infrared imaging device 712 and the image processor 726, and images generated by the image display driver 724 for display on the image display 722 of the optical components, etc. Although memory 702 is shown as integrated with the high-speed circuit system 730, in some examples, memory 702 may be a separate, independent component of the head-mounted wearable device 718. In some such examples, electrical wiring may provide a connection from the image processor 726 or the low-power processor 740 to memory 702 via a chip including the high-speed processor 734. In some examples, the high-speed processor 734 may manage addressing of memory 702 such that the low-power processor 740 will activate the high-speed processor 734 whenever a read or write operation involving memory 702 is required.

[0124] like Figure 7 As shown, the low-power processor 740 or high-speed processor 734 of the head-mounted wearable device 718 may be coupled to a camera device (visible light camera 708, infrared emitter 710 or infrared camera 712), an image display driver 724, a user input device 732 (e.g., a touch sensor or a press button), and a memory 702.

[0125] The head-mounted wearable device 718 is connected to a host computer. For example, the head-mounted wearable device 718 is paired with a mobile device 714 via a high-speed wireless connection 720 or connected to a server system 704 via a network 706. The server system 704 may be one or more computing devices as part of a service or network computing system, and may include, for example, a processor, memory, and a network communication interface to communicate with the mobile device 714 and the head-mounted wearable device 718 via the network 706.

[0126] Mobile device 714 includes a processor and a network communication interface coupled to the processor. The network communication interface allows communication via network 706, low-power wireless connection 716, or high-speed wireless connection 720. Mobile device 714 may also store at least a portion of the instructions for generating dual-channel audio content in the memory of mobile device 714 to implement the functions described herein.

[0127] The output components of the head-worn wearable device 718 include visual components, such as displays like liquid crystal displays (LCDs), plasma display panels (PDPs), light-emitting diode (LED) displays, projectors, or waveguides. The image display of the optical components is driven by an image display driver 724. The output components of the head-worn wearable device 718 also include acoustic components (e.g., speakers), haptic components (e.g., vibration motors), other signal generators, etc. Input components of the head-worn wearable device 718, mobile device 714, and server system 704, such as user input device 732, may include alphanumeric input components (e.g., keyboards, touchscreens configured to receive alphanumeric input, photoelectric keyboards, or other alphanumeric input components), pointing-based input components (e.g., mice, touchpads, trackballs, joysticks, motion sensors, or other pointing instruments), haptic input components (e.g., physical buttons, touchscreens or other haptic input components that provide positioning and force for touch or touch gestures), audio input components (e.g., microphones), etc.

[0128] The head-mounted wearable device 718 may also include additional peripheral device elements. Such peripheral device elements may include biometric sensors, additional sensors, or display elements integrated with the head-mounted wearable device 718. For example, peripheral device elements may include any I / O components, including output components, motion components, position components, or any other such elements described herein.

[0129] For example, biometric components include those for detecting expressions (e.g., hand gestures, facial expressions, voice expressions, body posture, or eye tracking), measuring biosignals (e.g., blood pressure, heart rate, body temperature, sweating, or brain waves), and identifying people (e.g., voice recognition, retinal recognition, facial recognition, fingerprint recognition, or EEG-based recognition). Motion components include accelerometer components (e.g., accelerometers), gravity sensor components, rotation sensor components (e.g., gyroscopes), etc. Positioning components include positioning sensor components (e.g., Global Positioning System (GPS) receiver components) for generating positioning coordinates, and Wi-Fi or Bluetooth for generating positioning system coordinates. TM Transceivers, altitude sensor components (e.g., altimeters or barometers that detect air pressure and determine altitude), orientation sensor components (e.g., magnetometers), etc. The coordinates of such a positioning system can also be received from the mobile device 714 via a low-power wireless circuit system 738 or a high-speed wireless circuit system 736 through a low-power wireless connection 716 and a high-speed wireless connection 720.

[0130] Data Architecture

[0131] Figure 8This is a schematic diagram illustrating a data structure 800 that can be stored in a database 804 of an interactive server system 910, according to certain examples. Although the contents of the database 804 are shown as including multiple tables, it will be appreciated that data can be stored in other types of data structures (e.g., as an object-oriented database).

[0132] Database 804 includes message data stored in message table 806. For any given message, this message data includes at least message sender data, message receiver (or recipient) data, and a payload. See below for reference. Figure 8 Further details are provided regarding information that can be included in the message and is contained within the message data stored in message table 806.

[0133] Entity table 808 stores entity data and (for example, links to entity diagram 810 and profile data 802). Entities whose records are maintained in entity table 808 can include individuals, company entities, organizations, objects, locations, events, etc. Regardless of the entity type, any entity whose data is stored in the interactive server system 910 can be an identifiable entity. Each entity is assigned a unique identifier and an entity type identifier (not shown).

[0134] Entity Graph 810 stores information about relationships and associations between entities. For example, such relationships could be social or professional relationships based on interests or activities (e.g., working at a common company or organization). Some relationships between entities can be unidirectional, such as an individual user subscribing to digital content (e.g., a newspaper or other digital media channel or brand) for a business or publishing user. Other relationships can be bidirectional, such as the "friend" relationships between various users of Interactive System 900.

[0135] Certain licenses and relationships can be attached to each relationship, and also to each direction of the relationship. For example, a two-way relationship (e.g., a friend relationship between individual users) may include authorization for the public disclosure of digital content items between the individual users, but certain restrictions or filters may be imposed on the public disclosure of such digital content items (e.g., using content characteristics, location data, or time of day data). Similarly, a subscription relationship between an individual user and a business user may impose varying degrees of restrictions on the public disclosure of digital content from the business user to the individual user, and may greatly limit or prevent the public disclosure of digital content from the individual user to the business user. As an example of an entity, a specific user may (e.g., through privacy settings) record certain restrictions in the record for that entity within entity table 808. Such privacy settings may be applied to all types of relationships in the context of interaction system 900, or selectively applied to only certain types of relationships.

[0136] Profile data 802 stores various types of profile data about a specific entity. Using privacy settings specified by the specific entity, profile data 802 can be selectively used and presented to other users of the interactive system 900. In the case of an individual, profile data 802 includes, for example, a username, phone number, address, settings (e.g., notification and privacy settings), and an avatar representation (or a set of such avatar representations) selected by the user. The specific user can then selectively include one or more of these avatar representations within the content of messages transmitted via the interactive system 900 and on a map interface displayed to other users by the interactive client 904. The set of avatar representations may include "status avatars," which present a graphical representation of a status or activity that the user can choose to transmit at a specific time.

[0137] In the case that the entity is a group, in addition to the group name, members and various settings for the associated group (e.g., notifications), the profile data 802 for the group may similarly include one or more avatar representations associated with the group.

[0138] Database 804 also stores enhancement data, such as overlays or filters, in enhancement table 812. Enhancement data is associated with and applied to videos (video data is stored in video table 814) and images (image data is stored in image table 816).

[0139] In some examples, filters are displayed as overlays on images or videos during presentation to the message recipient. Filters can be of various types, including user-selected filters from a set of filters presented to the message sender by the interactive client 904 when the message sender is composing a message. Other types of filters include geolocation filters (also known as geographic filters), which can be presented to the message sender using geolocation. For example, geolocation filters specific to nearby or particular locations can be presented by the interactive client 904 within the user interface using geolocation information determined by the Global Positioning System (GPS) unit of the computing system 902.

[0140] Another type of filter is a data filter, which can be selectively presented to the message sender by the interactive client 904 using other inputs or information collected by the computing system 902 during the message creation process. Examples of data filters include the current temperature at a specific location, the current speed of the message sender, the battery life of the computing system 902, or the current time.

[0141] Other augmented data that can be stored in image table 816 includes augmented reality content items (e.g., corresponding to an applied lens or augmented reality experience). Augmented reality content items can be real-time special effects and sounds that can be added to images or videos.

[0142] As described above, augmented data includes augmented reality (AR), virtual reality (VR), and mixed reality (MR) content items, overlays, image transformations, images, and modifications that can be applied to image data (e.g., video or images). This includes real-time modifications, which modify images using modifications as they are captured by the device sensors (e.g., one or more camera devices) of computing system 902 and then displayed on the screen of computing system 902. This also includes modifications to stored content (e.g., video clips that can be modified in a collection or group). For example, in computing system 902 that accesses multiple augmented reality content items, a user can use a single video clip with multiple augmented reality content items to see how different augmented reality content items will modify the stored clip. Similarly, real-time video capture can be modified to show how the video image currently captured by the sensors of computing system 902 will modify the captured data. Such data may simply be displayed on the screen without being stored in memory, or the content captured by the device sensors may be recorded and stored in memory with or without modification (or both). In some systems, the preview feature can simultaneously show how different augmented reality content items will look in different windows on the monitor. For example, this allows multiple windows with different pseudo-random animations to be viewed on the monitor at the same time.

[0143] Therefore, using data from augmented reality content items and various systems, or other such transformation systems that use that data to modify the content, can involve: the detection of objects (e.g., faces, hands, bodies, cats, dogs, surfaces, objects, etc.) in video images; tracking such objects as they leave, enter, and move around within the field of view; and modifying or transforming such objects while tracking them. In various examples, different methods can be used to implement such transformations. Some examples may involve: generating 3D mesh models of one or more objects; and using transformations of the models and animated textures within the video to implement the transformations. In some examples, tracking points on objects can be used to place images or textures (which can be two-dimensional or three-dimensional) at the tracked locations. In yet another example, neural network analysis of video images can be used to place images, models, or textures within the content (e.g., images or video frames). Thus, augmented reality content items involve both images, models, and textures used to create transformations within the content, and the additional modeling and analysis information required to implement such transformations using object detection, tracking, and placement.

[0144] Real-time video processing can be performed using any type of video data (e.g., video streams, video files, etc.) stored in the memory of any type of computerized system. For example, a user can load video files and store them in the device's memory, or the device's sensors can be used to generate video streams. Furthermore, computer-animated models can be used to process any object, such as a human face and parts of the human body, animals, or inanimate objects (e.g., chairs, cars, or other objects).

[0145] In some examples, when a specific modification is selected along with the content to be transformed, the element to be transformed is identified by the computing device and then detected and tracked if the element to be transformed exists in a frame of the video. The elements of the object are modified according to the modification request, thereby transforming the frames of the video stream. Different methods can be used to transform the frames of the video stream for different kinds of transformations. For example, for frame transformations that primarily involve changing the form of elements of an object, (e.g., using an Active Shape Model (ASM) or other known methods) characteristic points are calculated for each element of the object. A mesh using these characteristic points is then generated for each element of the object. This mesh is used in subsequent stages of tracking the elements of the object in the video stream. During tracking, the mesh for each element is aligned with the position of each element. Additional points are then generated on the mesh.

[0146] In some examples, transforming certain regions of an object using its elements can be performed by calculating characteristic points for each element of the object and generating a mesh using the calculated characteristic points. Points are generated on the mesh, and then various regions based on these points are generated. The elements of the object are then tracked by aligning the regions of each element with the positions of at least one of the elements, and the properties of the regions can be modified using modification requests, thereby transforming frames of the video stream. Depending on the specific modification request, the properties of the mentioned regions can be transformed in different ways. Such modifications can involve: changing the color of the region; removing parts of the region from the frames of the video stream; including new objects in the region using the modification request; and modifying or distorting the elements of the region or object. Any combination of such modifications or other similar modifications can be used in various examples. For certain models to be animated, some characteristic points can be selected as control points to determine the entire state space of options for model animation.

[0147] In some examples of computer animation models that use face detection to transform image data, a specific face detection algorithm (e.g., Viola-Jones) is used to detect faces in the image. The Active Shape Model (ASM) algorithm is then applied to the facial regions of the image to detect facial feature reference points.

[0148] Other methods and algorithms suitable for face detection can be used. For example, in some examples, landmarks are used to locate virtual features, which represent distinguishable points present in most of the images considered. For example, for facial landmarks, the location of the left pupil could be used. If the initial landmark is unrecognizable (e.g., in the case of a person wearing an eye patch), secondary landmarks can be used. Such landmark recognition processes can be used for any such object. In some examples, a set of landmarks forms a shape. The shape can be represented as a vector using the coordinates of the points in the shape. One shape is aligned with another shape using a similarity transformation (allowing translation, scaling, and rotation) that minimizes the average Euclidean distance between the points of the shapes. The mean shape is the average of the aligned training shapes.

[0149] The transformation system can capture image or video streams on a client device (e.g., computing system 902) and perform complex image manipulations locally on computing system 902 while maintaining an appropriate user experience, computation time, and power consumption. Complex image manipulations can include size and shape changes, mood shifts (e.g., changing a face from frowning to smiling), state shifts (e.g., aging a subject, reducing apparent age, changing gender), style shifts, application of graphical elements, and any other suitable image or video manipulation implemented by a convolutional neural network that has been configured to execute efficiently on computing system 902.

[0150] In some examples, a computer animation model for transforming image data can be used by a system in which a user can capture an image or video stream (e.g., a selfie) using a computing system 902 that operates as part of an interactive client 904 operating on the computing system 902. A transformation system operating within the interactive client 904 determines the presence of faces within the image or video stream and provides a modification icon associated with the computer animation model to transform the image data, or the computer animation model may exist in association with the interface described herein. This modification icon will be included as part of the modification operation, serving as a basis for modifying the user's face within the image or video stream. Once a modification icon is selected, the transformation system initiates a process to transform the user's image to reflect the selected modification icon (e.g., generating a smiley face on the user). Once the image or video stream is captured and the specified modification is selected, the modified image or video stream can be presented in a graphical user interface displayed on the computing system 902. The transformation system may implement a complex convolutional neural network on a portion of the image or video stream to generate and apply the selected modification. In other words, users can capture image or video streams, and once an edit icon is selected, the modified result can be presented to the user in real-time or near real-time. Furthermore, while the video stream is being captured, the modifications can be persistent, and the selected edit icon continues to be toggled. Machine-trained neural networks can be used to achieve such modifications.

[0151] The graphical user interface (GUI) presenting the modifications performed by the transformation system can offer users additional interactive options. Such options can be implemented using an interface designed to initiate the selection and content capture of a specific computer animation model (e.g., initiated from a content creator GUI). In various examples, the modifications can be persistent after the initial selection of the modification icon. Users can toggle the modification on or off by tapping or otherwise selecting the face modified by the transformation system, and save it for later viewing or browsing to other areas of the imaging application. In cases where multiple faces are modified by the transformation system, users can globally toggle the modification on or off by tapping or selecting a single face modified and displayed within the GUI. In some examples, individual faces within a group of multiple faces can be modified separately, or such modifications can be toggled individually by tapping or selecting a single face or a series of individual faces displayed within the GUI.

[0152] Story table 818 stores data about collections of messages and associated image, video, or audio data, compiled into collections (e.g., stories or galleries). The creation of a specific collection can be initiated by a specific user (e.g., each user whose records are maintained in entity table 808). A user can create a "personal story" in the form of a collection of content that has been created and sent / broadcast by that user. For this purpose, the user interface of interactive client 904 can include user-selectable icons that allow message senders to add specific content to their personal stories.

[0153] Collections can also constitute "live stories" as a collection of content from multiple users, created manually, automatically, or using a combination of manual and automatic techniques. For example, a "live story" can constitute a curated stream of user-submitted content from various locations and events. Users whose client devices have location services enabled and who are at a co-located event at a specific time can be presented with the option to contribute content to a specific live story, for example, through the user interface of interactive client 904. Interactive client 904 can identify a live story to a user using their location. The end result is a "live story" told from a collective perspective.

[0154] Another type of content collection is called a "location story," which allows users whose computing system 902 is located within a specific geographic location (e.g., on a college or university campus) to contribute to a specific collection. In some examples, contributing to a location story may require secondary authentication to verify that the end user belongs to a specific organization or other entity (e.g., a student on a university campus).

[0155] As mentioned above, video table 814 stores video data, which in some examples is associated with messages whose records are maintained within message table 806. Similarly, image table 816 stores image data associated with messages whose message data is stored in entity table 808. Entity table 808 can associate various enhancements from enhancement table 812 with various images and videos stored in image table 816 and video table 814.

[0156] Database 804 also includes entity relationship information collected by entity relationship system 1022.

[0157] Networked computing environment

[0158] Figure 9This is a block diagram illustrating an example interactive system 900 for facilitating interactions on a network, such as exchanging text messages, making text audio and video calls, or playing games. The interactive system 900 includes multiple computing systems 902, each hosting multiple applications including an interactive client 904 and other applications 906. Each interactive client 904 is communicatively coupled to other instances of the interactive client 904 (e.g., hosted on corresponding other computing systems 902), an interactive server system 910, and a third-party server 912 via one or more communication networks including a network 908 (e.g., the Internet). The interactive client 904 can also communicate with the locally hosted applications 906 using an application programming interface (API).

[0159] Each computing system 902 may include one or more user devices, such as mobile devices 714, head-mounted wearable devices 718, and computer client devices 914, which are communicatively connected to exchange data and messages.

[0160] Interactive client 904 interacts with other interactive clients 904 and with interactive server system 910 via network 908. The data exchanged between interactive clients 904 (e.g., interactive 916) and between interactive client 904 and interactive server system 910 includes functions (e.g., commands for invoking functions) and payload data (e.g., text, audio, video, or other multimedia data).

[0161] Interactive server system 910 provides server-side functionality to interactive client 904 via network 908. While some functions of interactive system 900 are described herein as being performed by interactive client 904 or interactive server system 910, the location of certain functions—whether within interactive client 904 or interactive server system 910—may be a design choice. For example, it may be technically preferred to initially deploy certain technologies and functions within interactive server system 910, but later migrate those technologies and functions to interactive client 904, which has sufficient processing power in computing system 902.

[0162] The interactive server system 910 supports various services and operations provided to the interactive client 904. These operations include sending data to and receiving data from the interactive client 904, and processing data generated by the interactive client 904. This data may include message content, client device information, geolocation information, media enhancements and overlays, message content persistence conditions, entity relationship information, and live event information. Data exchange within the interactive system 900 is invoked and controlled via functions available through the user interface (UI) of the interactive client 904.

[0163] Specifically, turning to interactive server system 910, application programming interface (API) server 918 is coupled to interactive server 920 and provides a programming interface to interactive server 920, making the functionality of interactive server 920 accessible to interactive client 904, other applications 906, and third-party server 912. Interactive server 920 is communicatively coupled to database server 922, facilitating access to database 924, which stores data associated with the interactions processed by interactive server 920. Similarly, web server 926 is coupled to interactive server 920 and provides a web-based interface to interactive server 920. To this end, web server 926 processes incoming network requests via Hypertext Transfer Protocol (HTTP) and several other related protocols.

[0164] Application Programming Interface (API) server 918 receives and transmits interactive data (e.g., command and message payloads) between interactive server 920 and computing system 902 (as well as interactive client 904 and other applications 906) and third-party server 912. Specifically, API server 918 provides a set of interfaces (e.g., routines and protocols) that can be invoked or queried by interactive client 904 and other applications 906 to invoke the functions of interactive server 920. Application Programming Interface (API) server 918 exposes various functions supported by interaction server 920, including account registration; login functionality; sending interactive data from one interactive client 904 to another interactive client 904 via interaction server 920; communication of media files (e.g., images or videos) from interactive client 904 to interaction server 920; setting up media data sets (e.g., stories); retrieving the friend list of users of computing system 902; retrieving messages and content; adding and deleting entities (e.g., friends) to an entity graph (e.g., a social graph); the location of friends within the entity graph; and opening application events (e.g., related to interactive client 904).

[0165] Interactive server 920 hosts multiple systems and subsystems, as shown below. Figure 10 describe.

[0166] Application of links

[0167] Returning to interactive client 904, the features and functionality of external resources (e.g., linked application 906 or applet) become available to the user via the interface of interactive client 904. In this context, "external" refers to the fact that application 906 or applet is outside of interactive client 904. External resources are typically provided by third parties, but may also be provided by the creator or provider of interactive client 904. Interactive client 904 receives the user's selection of options to launch or access the features of such external resources. External resources may be application 906 installed on computing system 902 (e.g., a "local application"), or a smaller version (e.g., an "applet") of an application hosted on or away from computing system 902 (e.g., on a third-party server 912). A smaller version of an application includes a subset of the application's features and functionality (e.g., a fully native version of the application) and is implemented using markup language documentation. In some examples, a smaller version of an application (e.g., an "applet") is a web-based markup language version of the application and is embedded in interactive client 904. In addition to using markup language documents (e.g., .*ml files), mini-programs can combine scripting languages ​​(e.g., .*js files or .json files) and stylesheets (e.g., .*ss files).

[0168] In response to receiving a user's selection of an option to launch or access an external resource, the interactive client 904 determines whether the selected external resource is a web-based external resource or a locally installed application 906. In some cases, the application 906, locally installed on the computing system 902, can be launched independently of and separately from the interactive client 904, for example, by selecting an icon corresponding to the application 906 on the main screen of the computing system 902. A smaller version of such an application can be launched or accessed via the interactive client 904, and in some examples, no or limited portions of the smaller application can be accessed outside the interactive client 904. The smaller application can be launched by receiving and processing markup language documents associated with the smaller application from, for example, a third-party server 912 via the interactive client 904.

[0169] In response to determining that the external resource is a locally installed application 906, the interactive client 904 instructs the computing system 902 to launch the external resource by executing locally stored code corresponding to the external resource. In response to determining that the external resource is a web-based resource, the interactive client 904 communicates with a third-party server 912 (e.g.) to obtain a markup language document corresponding to the selected external resource. The interactive client 904 then processes the obtained markup language document to present the web-based external resource within the user interface of the interactive client 904.

[0170] Interactive client 904 can notify users of computing system 902 or other users (e.g., "friends") associated with that user of activities occurring in one or more external resources. For example, interactive client 904 can provide participants in a session (e.g., a chat session) within interactive client 904 with notifications related to the current or recent use of external resources by one or more members of a user group. One or more users can be invited to join an active external resource or to activate (in a friend group) a recently used but currently inactive external resource. External resources can provide each participant in a session using the corresponding interactive client 904 with the ability to share items, identities, states, or locations within the external resource in a chat session with one or more members of a group of users. Shared items can be interactive chat cards that chat members can interact with, for example, to activate the corresponding external resource, view specific information within the external resource, or take a chat member to a specific location or state within the external resource. Within a given external resource, response messages can be sent to the user on interactive client 904. Based on the current context of the external resource, the external resource can optionally include different media items in the response.

[0171] Interactive client 904 can present a list of available external resources (e.g., application 906 or applet) to the user to launch or access a given external resource. This list can be presented in a context-sensitive menu. For example, icons representing different applications within application 906 (or applet) can change based on how the user launches the menu (e.g., from a conversational interface or a non-conversational interface).

[0172] System Architecture

[0173] Figure 10 This is a block diagram illustrating further details of an interactive system 900 based on some examples. Specifically, the interactive system 900 is shown as including an interactive client 904 and an interactive server 920. The interactive system 900 comprises multiple subsystems, which are supported on the client side by the interactive client 904 and on the server side by the interactive server 920. Example subsystems are discussed below.

[0174] The image processing system 1002 provides various functions that enable users to capture and enhance (e.g., enhance or otherwise modify or edit) media content associated with a message.

[0175] The camera device system 1004 includes (e.g., in a camera device application) control software that (e.g., directly or via an operating system) interacts with and controls the hardware camera device hardware of the computing system 902 to modify and enhance real-time images captured and displayed via the interactive client 904.

[0176] Enhancement system 1006 provides functionality related to the generation and distribution of enhancements (e.g., media overlays) for images captured in real time by the camera device of computing system 902 or retrieved from the memory of computing system 902. For example, enhancement system 1006 is operable to select, present, and display media overlays (e.g., image filters or image lenses) for interactive client 904 to enhance real-time images received via camera device system 1004 or stored images retrieved from memory 702 of computing system 902. These enhancements are selected and presented to the user of interactive client 904 by enhancement system 1006 using some inputs and data, such as:

[0177] • The geographic location of computing system 902; and

[0178] • Entity relationship information of users of computing system 902.

[0179] Enhancements may include audio and visual content and visual effects. Examples of audio and visual content include images, text, logos, animations, and sound effects. Examples of visual effects include color overlays. Audio and visual content or visual effects may be applied to media content items (e.g., photos or videos) at computing system 902 for transmission in messages, or to video content such as video content streams or feeds sent from interactive client 904. Therefore, image processing system 1002 can interact with various subsystems of communication system 1008 and supports various subsystems of communication system 708, such as messaging system 1010 and video communication system 1012.

[0180] Media overlays may include text or image data that can be superimposed on photographs taken by computing system 902 or video streams produced by computing system 902. In some examples, media overlays may be location overlays (e.g., Venice Beach), names of live events, or names of businesses (e.g., Beach Cafe). In other examples, image processing system 1002 uses the geolocation of computing system 902 to identify media overlays that include the name of a business at the geolocation of computing system 902. Media overlays may include additional tags associated with businesses. Media overlays may be stored in database 924 and accessed through database server 922.

[0181] Image processing system 1002 provides a user-based publishing platform that allows users to select a geographic location on a map and upload content associated with that location. Users can also specify the environment in which a particular media overlay should be provided to other users. Image processing system 1002 generates a media overlay that includes the uploaded content and associates it with the selected geographic location.

[0182] The Augmented Creation System 1014 supports augmented reality developer platforms and includes applications for content creators (e.g., artists and developers) to create and publish interactive clients 904, such as augmented reality experiences. The Augmented Creation System 1014 provides content creators with a library of built-in features and tools, including, for example, custom shaders, tracking technologies, and templates.

[0183] In some examples, the enhancement creation system 1014 provides a merchant-based publishing platform that allows merchants to select specific enhancements associated with geolocation through a bidding process. For example, the enhancement creation system 1014 associates the media overlay of the highest-bidder merchant with a corresponding geolocation for a predefined amount of time.

[0184] Communication system 1008 is responsible for enabling and processing various forms of communication and interaction within interactive system 900, and includes messaging system 1010, audio communication system 1016, and video communication system 1012. Messaging system 1010 is responsible for enabling temporary or time-limited access to content by interactive client 904. Messaging system 1010 includes multiple timers (e.g., within short-lived timer system 1018) that selectively enable access (e.g., for presentation and display) of messages and associated content via interactive client 904 using duration and display parameters associated with a message or set of messages (e.g., a story). Further details regarding the operation of short-lived timer system 1018 are provided below. Audio communication system 1016 enables and supports audio communication (e.g., real-time audio chat) between multiple interactive clients 904. Similarly, video communication system 1012 enables and supports video communication (e.g., real-time video chat) between multiple interactive clients 904.

[0185] The user management system 1020 is operationally responsible for managing user data and profiles, and includes an entity relationship system 1022 that maintains entity relationship information about the relationships between users of the interaction system 900.

[0186] The collection management system 1024 is operationally responsible for managing collections or sets of media (e.g., collections of text, images, video, and audio data). Collections of content (e.g., messages, including images, videos, text, and audio) can be organized into "event galleries" or "event stories." Such collections can be made available for a specified time period (e.g., the duration of the event the content relates to). For example, content related to a concert can be made available as a "story" for the duration of the concert. The collection management system 1024 is also responsible for publishing icons that notify the user interface of the interactive client 904 of the availability of specific collections. The collection management system 1024 includes curatorial functions that enable collection managers to manage and curate specific content collections. For example, a curation interface allows event organizers to curate collections of content related to a specific event (e.g., removing inappropriate content or redundant messages). Additionally, the collection management system 1024 employs machine vision (or image recognition technology) and content rules to automatically curate content collections. In some examples, users may be compensated for including user-generated content in the collection. In such a case, the collection management system 1024 operates to automatically pay such users for access to its content.

[0187] Map system 1026 provides various geolocation functions and supports the presentation of map-based media content and messages by interactive client 904. For example, map system 1026 enables the display (e.g., stored in profile data 802) of user icons or avatars on the map to indicate the current or past locations of the user's "friends" and media content generated by these friends (e.g., a collection of messages including photos and videos) within the map context. For example, on the map interface of interactive client 904, messages posted by a user from a specific geolocation to interactive system 900 can be displayed to the specific user's "friends" within the context of that specific location on the map. Users can also share their location and status information with other users of interactive system 900 via interactive client 904 (e.g., using an appropriate status avatar), where the location and status information is similarly displayed to selected users within the context of the map interface of interactive client 904.

[0188] Game system 1028 provides various game functions within the context of interactive client 904. Interactive client 904 provides a game interface that displays a list of available games that can be initiated by a user within the context of interactive client 904 and played with other users of interactive system 900. Interactive system 900 also enables specific users to invite other users to participate in specific games by sending invitations from interactive client 904. Interactive client 904 also supports sending and receiving audio, video, and text messages (e.g., chat) within the context of playing games, provides leaderboards for games, and supports providing in-game rewards (e.g., game currency and items).

[0189] External resource system 1030 provides interactive client 904 with an interface to communicate with remote servers (e.g., third-party server 912) to launch or access external resources (i.e., applications or applets). Each third-party server 912 hosts applications or smaller versions of applications (e.g., game applications, utility applications, payment applications, or ride-sharing applications) based on markup languages ​​(e.g., HTML5). Interactive client 904 can launch web-based resources (e.g., applications) by accessing HTML5 files from the third-party server 912 associated with the web-based resource. The application hosted by the third-party server 912 is programmed in JavaScript using a software development kit (SDK) provided by interactive server 920. The SDK includes application programming interfaces (APIs) with functions that can be called or activated by the web-based application. Interactive server 920 hosts a JavaScript library that provides access to a given external resource for specific user data of interactive client 904. HTML5 is an example of a technology used for programming games, but applications and resources programmed using other technologies can be used.

[0190] To integrate the SDK's functionality into the web-based resource, the third-party server 912 downloads the SDK from the interactive server 920, or receives the SDK from the third-party server 912 in other ways. Once downloaded or received, the SDK is included as part of the application code of the web-based external resource. The code of the web-based resource can then call or activate certain functions of the SDK to integrate the features of the interactive client 904 into the web-based resource.

[0191] The SDK stored on the interactive server system 910 effectively bridges the gap between external resources (e.g., application 906 or applet) and the interactive client 904. This provides users with a seamless experience communicating with other users on the interactive client 904 while preserving the look and feel of the interactive client 904. To bridge the communication between the external resources and the interactive client 904, the SDK facilitates communication between a third-party server 912 and the interactive client 904. The WebViewJavaScriptBridge running on the computing system 902 establishes two unidirectional communication channels between the external resources and the interactive client 904. Messages are sent asynchronously between the external resources and the interactive client 904 via these communication channels. Each SDK function activation is sent as a message and callback. Each SDK function is implemented by constructing a unique callback identifier and sending a message with that callback identifier.

[0192] By using the SDK, not all information from the interactive client 904 is shared with the third-party server 912. The SDK limits which information is shared based on the needs of the external resources. Each third-party server 912 provides the interactive server 920 with an HTML5 file corresponding to the web-based external resource. The interactive server 920 can add a visual representation (e.g., box design or other graphics) of the web-based external resource to the interactive client 904. Once the user selects the visual representation or instructs the interactive client 904 to access the features of the web-based external resource through the interactive client 904's GUI, the interactive client 904 obtains the HTML5 file and instantiates the resource for accessing the features of the web-based external resource.

[0193] Interactive client 904 presents a graphical user interface (GUI) for an external resource (e.g., a login page or title screen). During, before, or after presenting the login page or title screen, interactive client 904 determines whether the initiated external resource has previously been authorized to access the user data of interactive client 904. In response to determining that the initiated external resource has previously been authorized to access the user data of interactive client 904, interactive client 904 presents another GUI of the external resource, including its functionality and characteristics. In response to determining that the initiated external resource has not previously been authorized to access the user data of interactive client 904, after displaying the login page or title screen of the external resource for a threshold time period (e.g., 3 seconds), interactive client 904 slides up a menu (e.g., animates the menu to appear from the bottom of the screen to the middle of the screen or other parts) to authorize the external resource to access user data. This menu identifies the type of user data that the external resource will be authorized to use. In response to receiving a user selection of the accept option, interactive client 904 adds the external resource to the list of authorized external resources and allows the external resource to access user data from interactive client 904. External resources are authorized by the interactive client (904) to access user data under the OAuth2 framework.

[0194] Interactive client 904 controls the type of user data shared with external resources based on the type of authorized external resource. For example, it provides access to a first type of user data (e.g., a two-dimensional avatar of a user with or without different avatar characteristics) to external resources including full-scale applications (e.g., application 906). As another example, it provides access to a second type of user data (e.g., payment information, a user's two-dimensional avatar, a user's three-dimensional avatar, and avatars with various avatar characteristics) to external resources including smaller versions of an application (e.g., a web-based version of an application). Avatar characteristics include different ways of customizing the appearance and feel of an avatar (e.g., different poses, facial features, clothing, etc.).

[0195] The advertising system 1032 operates by enabling third parties to purchase advertisements to be presented to end users via the interactive client 904, and also handles the delivery and presentation of these advertisements.

[0196] Software Architecture

[0197] Figure 11This is a block diagram 1100 illustrating a software architecture 1102 that can be installed on any or more of the devices described herein. The software architecture 1102 is supported by hardware such as machine 1104, which includes a processor 1106, memory 1108, and I / O components 1110. In this example, the software architecture 1102 can be conceptualized as a stack of layers, where each layer provides specific functionality. The software architecture 1102 includes layers such as an operating system 1112, libraries 1114, frameworks 1116, and applications 1118. Operationally, application 1118 activates API call 1120 via the software stack and receives message 1122 in response to API call 1120.

[0198] Operating system 1112 manages hardware resources and provides public services. Operating system 1112 includes, for example, a kernel 1124, services 1126, and drivers 1128. Kernel 1124 serves as an abstraction layer between hardware and other software layers. For example, kernel 1124 provides memory management, processor management (e.g., scheduling), component management, networking and security settings, and other functions. Services 1126 can provide other public services to other software layers. Driver 1128 is responsible for controlling or interfacing with the underlying hardware. For example, driver 1128 may include a display driver, a camera driver, etc. or Low-power drivers, flash drives, serial communication drivers (e.g., USB drives), Drivers, audio drivers, power management drivers, etc.

[0199] Library 1114 provides common low-level infrastructure used by application 1118. Library 1114 may include system library 1130 (e.g., the C standard library) that provides functions such as memory allocation, string manipulation, and mathematical functions. Additionally, library 1114 may include API library 1132, such as media libraries (e.g., libraries for supporting the rendering and manipulation of various media formats, such as Moving Picture Experts Group-4 (MPEG4), Advanced Video Coding (H.264 or AVC), Moving Picture Experts Group Layer-3 (MP3), Advanced Audio Coding (AAC), Adaptive Multi-Rate (AMR) audio codecs, Joint Picture Experts Group (JPEG or JPG) or Portable Web Graphics (PNG)), graphics libraries (e.g., OpenGL frameworks for rendering graphic content on a display in two-dimensional (2D) and three-dimensional (3D) formats), database libraries (e.g., SQLite providing various relational database functions), web libraries (e.g., WebKit providing web browsing capabilities), etc. Library 1114 may also include various other libraries 1134 to provide many other APIs to application 1118.

[0200] Framework 1116 provides common high-level infrastructure for use by application 1118. For example, framework 1116 provides various graphical user interface (GUI) functions, advanced resource management, and advanced location services. Framework 1116 can provide a wide range of other APIs that can be used by application 1118, some of which may be specific to a particular operating system or platform.

[0201] In the example, application 1118 may include home application 1136, contact application 1138, browser application 1140, book reader application 1142, location application 1144, media application 1146, messaging application 1148, game application 1150, and a wide variety of other applications such as third-party application 1152. Application 1118 is a program that performs the functions defined in the program. One or more applications 1118 can be created using various programming languages, such as object-oriented programming languages ​​(e.g., Objective-C, Java, or C++) or procedural programming languages ​​(e.g., C or assembly language). In a particular example, third-party application 1152 (e.g., an entity other than the vendor of a particular platform using Android) TM or iOS TM Applications developed using a Software Development Kit (SDK) can be mobile operating systems such as iOS. TM ANDROID TM , Mobile software running on a phone or other mobile operating system. In this example, a third-party application 1152 can activate API call 1120 provided by the operating system 1112 to facilitate the functionality described herein.

[0202] in conclusion

[0203] Changes and modifications may be made to the disclosed examples without departing from the scope of this disclosure. Such and other changes or modifications are intended to be included within the scope of this disclosure as set forth in the appended claims.

[0204] Glossary

[0205] "Carrier signal" refers to any intangible medium capable of storing, encoding, or carrying instructions to be executed by a computer machine, including digital or analog communication signals or other intangible media to facilitate the communication of such instructions. Instructions can be sent or received over a network using a transmission medium via a network interface device.

[0206] "Client device" refers to any computer machine that interfaces with a communication network to obtain resources from one or more server systems or other client devices. Client devices can be, but are not limited to, mobile phones, desktop computers, laptop computers, portable digital assistants (PDAs), smartphones, tablet computers, ultrabooks, netbooks, laptop computers, multiprocessor systems, microprocessor-based or programmable consumer electronics, game consoles, set-top boxes, or any other communication device that a user can use to access the network.

[0207] "Communication network" refers to one or more parts of a network, which can be an ad hoc network, intranet, extranet, virtual private network (VPN), local area network (LAN), wireless LAN (WLAN), wide area network (WAN), wireless WAN (WWAN), metropolitan area network (MAN), the Internet, a part of the Internet, a part of the Public Switched Telephone Network (PSTN), a POTS (Plain Old-Style Telephone Service) network, a cellular telephone network, a wireless network, etc. A network, other types of networks, or a combination of two or more such networks. For example, a network or part of a network may include a wireless network or a cellular network, and the coupling may be a Code Division Multiple Access (CDMA) connection, a Global System for Mobile Communications (GSM) connection, or other types of cellular or wireless coupling. In this example, the coupling can implement any data transmission technology of various types, such as Single Carrier Radio Transmission (1xRTT), Evolved Data Optimization (EVDO), General Packet Radio Service (GPRS), Enhanced Data Rate Evolution of GSM (EDGE), the 3rd Generation Partnership Project (3GPP) including 3G, fourth-generation wireless (4G) networks, Universal Mobile Telecommunications System (UMTS), High-Speed ​​Packet Access (HSPA), Global Microwave Access Interoperability (WiMAX), Long Term Evolution (LTE) standards, other data transmission technologies defined by various standards setting organizations, other long-distance protocols, or other data transmission technologies.

[0208] A “component” is a device, physical entity, or logic having boundaries defined by function or subroutine calls, branch points, APIs, or other technologies provided for partitioning or modularizing specific processing or control functions. Components can be combined with other components via their interfaces to perform computer processing. A component can be an encapsulated functional hardware unit designed for use with other components and can be part of a program that typically performs a specific function within a related function. Components can constitute software components (e.g., code implemented on a machine-readable medium) or hardware components. A “hardware component” is a tangible unit capable of performing certain operations and which can be configured or arranged in some physical manner. In various examples, one or more hardware components (e.g., standalone computer systems, client computer systems, or server computer systems) or one or more hardware components (e.g., processors or processor groups) of a computer system can be configured by software (e.g., an application or application portion) to operate to perform certain operations as described herein. Hardware components can also be implemented mechanically, electronically, or in any suitable combination thereof. For example, a hardware component can include a dedicated circuit system or logic permanently configured to perform certain operations. Hardware components can be dedicated processors, such as field-programmable gate arrays (FPGAs) or application-specific integrated circuits (ASICs). Hardware components can also include programmable logic or circuit systems that are temporarily configured by software to perform certain operations. For example, a hardware component may include software executed by a general-purpose processor or other programmable processor. Once configured by such software, the hardware component becomes a particular computing machine (or a specific part of a computing machine), which is uniquely tailored to perform the configured functions and is no longer a general-purpose processor. It will be appreciated that a decision may be made, for cost and time considerations, whether to implement hardware components mechanically in a dedicated and permanently configured circuit system or in a temporarily configured (e.g., configured by software) circuit system. Therefore, the phrase “hardware component” (or “hardware-implemented component”) should be understood to include tangible entities, i.e., entities that are physically constructed, permanently configured (e.g., hardwired), or temporarily configured (e.g., programmed) to operate in a certain way or perform certain operations described herein. Consider the example of hardware components being temporarily configured (e.g., programmed), without needing to configure or instantiate each hardware component at any given time. For example, in cases where the hardware components include a general-purpose processor that can be configured by software to become a dedicated processor, the general-purpose processor can be configured as different dedicated processors (e.g., including different hardware components) at different times. The software accordingly configures one or more specific processors to, for example, constitute a specific hardware component at one time and different hardware components at different times.Hardware components can provide information to and receive information from other hardware components. Therefore, the described hardware components can be considered communicatively coupled. In the presence of multiple hardware components, communication can be achieved through signal transmission between or among two or more hardware components (e.g., via appropriate circuitry and buses). In examples where multiple hardware components are configured or instantiated at different times, such communication between hardware components can be achieved, for example, by storing information in a memory structure accessible to the multiple hardware components and retrieving information from the memory structure. For example, a hardware component can perform an operation and store the output of that operation in a memory device to which it is communicatively coupled. Another hardware component can then access the memory device at a subsequent time to retrieve and process the stored output. Hardware components can also initiate communication with input or output devices and can operate on resources (e.g., collections of information). The various operations of the example methods described herein can be performed, at least in part, by one or more processors configured, either temporarily (e.g., via software) or permanently, to perform the relevant operations. Whether temporarily or permanently configured, such processors can constitute components of a processor implementation that operates to perform one or more operations or functions described herein. As used herein, a “processor-implemented component” refers to a hardware component implemented using one or more processors. Similarly, the methods described herein can be implemented at least in part by processors, where a particular processor or one or more processors are examples of hardware. For example, at least some of the operations of the methods can be performed by one or more processors or processor-implemented components. Furthermore, one or more processors can also operate to support the execution of related operations in a “cloud computing” environment or as “Software as a Service” (SaaS). For example, at least some of the operations can be performed by a group of computers (as an example of a computing machine including processors), where these operations are accessible via a network (e.g., the Internet) and via one or more appropriate interfaces (e.g., APIs). The execution of some operations can be distributed among processors, not residing solely within a single computing machine, but deployed across multiple computing machines. In some examples, the processor or processor-implemented component may reside in a single geographic location (e.g., in a home environment, office environment, or server cluster). In other examples, the processor or processor-implemented component may be distributed across multiple geographic locations.

[0209] "Machine-readable medium" refers to both machine storage media and transmission media. Therefore, these terms encompass both storage devices / media and carrier / modulated data signals. The terms "computer-readable medium," "machine-readable medium," and "device-readable medium" refer to the same thing and can be used interchangeably in this disclosure.

[0210] "Machine-readable storage medium" refers to one or more storage devices and media (e.g., centralized or distributed databases, and associated caches and servers) that store executable instructions, routines, and data. Therefore, this term should be considered to include, but is not limited to, solid-state memory and optical and magnetic media, including memory internal or external to the processor. Specific examples of machine storage media, computer storage media, and device storage media include: non-volatile memory, including, for example, semiconductor memory devices such as erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), FPGAs, and flash memory devices; disks, such as internal hard disks and removable disks; magneto-optical disks; and CD-ROM and DVD-ROM disks. The terms "machine storage medium," "device storage medium," and "computer storage medium" mean the same thing and may be used interchangeably in this disclosure. The terms "machine storage medium," "computer storage medium," and "device storage medium" expressly exclude carrier waves, modulated data signals, and other such media, at least some of which are covered by the term "signal medium."

[0211] "Non-transitory machine-readable storage medium" refers to a tangible medium capable of storing, encoding, or carrying instructions that can be executed by a computer machine.

[0212] "Signal medium" means any intangible medium capable of storing, encoding, or carrying instructions executable by a computer machine, and includes digital or analog communication signals or other intangible media to facilitate the communication of software or data. The term "signal medium" should be considered to include any form of modulated data signal, carrier wave, etc. The term "modulated data signal" means a signal whose characteristics are set or altered in a manner that encodes information in the signal. The terms "transmission medium" and "signal medium" mean the same thing and may be used interchangeably in this disclosure.

Claims

1. A computer-implemented method, comprising: Image data of a hand in a real-world scene is captured by a camera device of an extended reality (XR) system, using one or more processors; The estimated depth data of the hand in the real-world scene is generated by the one or more processors using the image data and a depth estimation model trained with synthetic 2D image data; The XR effect is generated by one or more processors using the estimated depth data and the image data; as well as The XR effect is provided to the user in the user interface by one or more processors.

2. The computer-implemented method according to claim 1, wherein, Generating the estimated depth data includes: The one or more processors use the image data and the detection model to determine the cropping boundary data; and The image data is cropped using the cropping boundary data by one or more processors.

3. The computer-implemented method according to claim 1, in, The image data of the hand includes a set of pixels, and The estimated depth data includes the corresponding depth of each pixel in the pixel set.

4. The computer-implemented method according to claim 1, wherein, Training the depth estimation model includes: Receives 3D data of the measured hand; The second or more processors use the 3D data to generate 3D model data of the measured hand; The second or more processors use the 3D model data to generate synthetic 2D image data including one or more synthetic 2D images; The second or more processors use the synthesized 2D image data and the 3D model data to generate target depth data, the target depth data including one or more depth sets paired with the one or more synthesized 2D images; The depth estimation model is trained by the second or one processor using the synthetic 2D image data and the target depth data.

5. The computer-implemented method according to claim 4, wherein, Generating the synthetic 2D image data includes using a camera device and lighting parameter data.

6. The computer-implemented method according to claim 5, wherein, The camera device and lighting parameter data include randomized values.

7. The computer-implemented method according to claim 4, wherein, Training the depth estimation model also includes: The second or more processors use the synthesized 2D image data and the detection model to determine the cropping boundary data; and The synthesized 2D image data is cropped using the cropping boundary data by a second or more processors.

8. A computing device, comprising: One or more processors; as well as The memory stores instructions that, when executed by the one or more processors, cause the computing device to perform operations, including: The camera device of the extended reality (XR) system captures image data of the hand in a real-world scene; Estimated depth data is generated using the image data and a depth estimation model trained with synthetic 2D image data; The estimated depth data and the image data are used to generate XR effects; and The XR effect is presented to the user in the user interface.

9. The computing device according to claim 8, wherein, The operation also includes: The image data and detection model are used to determine the cropping boundary data; and The image data is cropped using the cropping boundary data.

10. The computing device according to claim 8, in, The image data of the hand includes a set of pixels, and The estimated depth data includes the corresponding depth of each pixel in the pixel set.

11. The computing device according to claim 8, wherein, Training the depth estimation model includes: Receives 3D data of the measured hand; The 3D data is used to generate a 3D model of the measured hand. The 3D model data is used to generate synthetic 2D image data including one or more synthetic 2D images; Target depth data is generated using the synthesized 2D image data and the 3D model data, the target depth data comprising one or more depth sets paired with the one or more synthesized 2D images; The depth estimation model is trained using the synthetic 2D image data and the target depth data.

12. The computing device according to claim 11, wherein, Generating the synthetic 2D image data includes using a camera device and lighting parameter data.

13. The computing device according to claim 12, wherein, The camera device and lighting parameter data include randomized values.

14. The computing device according to claim 11, wherein, Training the depth estimation model also includes: The synthetic 2D image data and detection model are used to determine the cropping boundary data; and The composite 2D image data is cropped using the cropping boundary data.

15. A non-transitory machine-readable storage medium, the machine-readable storage medium comprising instructions that, when executed by a computer, cause the computer to perform an operation, the operation comprising: The XR system uses camera devices to capture image data of hands in real-world scenes; Estimated depth data is generated using the image data and a depth estimation model trained with synthetic 2D image data; The estimated depth data and the image data are used to generate XR effects; as well as The XR effect is presented to the user in the user interface.

16. The non-transitory machine-readable storage medium according to claim 15, wherein, Generating the estimated depth data includes: The image data and detection model are used to determine the cropping boundary data; and The image data is cropped using the cropping boundary data.

17. The non-transitory machine-readable storage medium according to claim 15, in, The image data of the hand includes a set of pixels, and The estimated depth data includes the corresponding depth of each pixel in the pixel set.

18. The non-transitory machine-readable storage medium according to claim 15, wherein, Training the depth estimation model includes: Receives 3D data of the measured hand; The 3D data is used to generate a 3D model of the measured hand. The 3D model data is used to generate synthetic 2D image data including one or more synthetic 2D images; Target depth data is generated using the synthesized 2D image data and the 3D model data, the target depth data comprising one or more depth sets paired with the one or more synthesized 2D images; The depth estimation model is trained using the synthetic 2D image data and the target depth data.

19. The non-transitory machine-readable storage medium according to claim 18, wherein, Generating the synthetic 2D image data includes using a camera device and lighting parameter data.

20. The non-transitory machine-readable storage medium according to claim 18, wherein, Training the depth estimation model also includes: The second or more processors use the synthesized 2D image data and the detection model to determine the cropping boundary data; and The synthesized 2D image data is cropped using the cropping boundary data by a second or more processors.

Images