Method and electronic device for enhancing image visibility

Abstract

A method and an electronic device for enhancing image visibility are disclosed. The method includes obtaining a first image frame of a scene, determining a brightness-related metric indicative of a brightness of the first image frame, based on the brightness-related metric satisfying a predefined condition indicative of low-light, and applying a visibility enhancement model to the first image frame in order to obtain a second image frame having a higher brightness than the brightness of the first image frame.

Description

METHOD AND ELECTRONIC DEVICE FOR ENHANCING IMAGE VISIBILITY

[0001] This disclosure relates generally to image processing systems and processes. More specifically, this disclosure relates to a method and an electronic device for enhancing image visibility.

[0002] Extended reality (XR) systems are becoming increasingly popular, and numerous applications have been and continue to be developed for XR systems. Some XR systems (such as augmented reality (AR) systems and mixed reality (MR) systems) can enhance a user's view of his or her current environment by overlaying digital content (such as information or virtual objects) over the user's view of the current environment. For example, some XR systems can seamlessly blend virtual objects obtained by computer graphics with real-world scenes.

[0003] This disclosure relates to fast low-light image visibility enhancement. According to an embodiment of the present disclosure, there is provided a method for enhancing image visibility. The method may include obtaining, using at least one imaging sensor of an electronic device, a first image frame of a scene. The method may include determining, using at least one processor of the electronic device, a brightness-related metric indicative of a brightness of the first image frame. The method may include, based on the brightness-related metric satisfying a predefined condition indicative of low-light, applying, using the at least one processor, a visibility enhancement model to the first image frame in order to obtain a second image frame having a higher brightness than the brightness of the first image frame. A visibility enhancement model is trained using at least one dataset that includes image frames obtained using at least one imaging sensor.

[0004] According to an embodiment of the present disclosure, there is provided a computer-readable storage medium storing instructions, wherein the instructions, when executed by at least one processor, cause the at least one processor to perform the method for enhancing image visibility.

[0005] According to an embodiment of the present disclosure, there is provided an electronic device for enhancing image visibility. The electronic device may include at least one imaging sensor and at least one processor. The at least one processor may be configured to obtain a first image frame of a scene captured using the at least one imaging sensor. The at least one processor may be configured to determine a brightness-related metric indicative of a brightness of the first image frame. The at least one processor may be configured, based on the brightness-related metric satisfying a predefined condition indicative of low-light, to apply a visibility enhancement model to the first image frame in order to obtain a second image frame having a higher brightness than the brightness of the first image frame. A visibility enhancement model may be trained using at least one dataset that includes image frames obtained using at least one imaging sensor.

[0006] According to an embodiment of the present disclosure, there is provided a method. The method may include obtaining, using at least one imaging sensor of an electronic device, image frames having different exposures. The method may include generating, using at least one processor of the electronic device, at least one training dataset using the image frames. The method may include training at least one low-light visibility enhancement model using the at least one dataset, where each low-light visibility enhancement model is trained to increase brightness in captured image frames. Training the at least one low-light visibility enhancement model includes, for each of the at least one imaging sensor, identifying parameters of a response model and a brightness transform model based on at least part of the at least one dataset and generating an exposure ratio map for adjusting image contrast and visibility. The low-light visibility enhancement model is based on the response model, the brightness transform model, and the exposure ratio map.

[0007] According to an embodiment of the present disclosure, there is provided an electronic device. The electronic device may include at least one processor configured to obtain, using at least one imaging sensor of the electronic device, image frames having different exposures. The at least one processor may be configured to generate at least one training dataset using the image frames. The at least one processor may be configured to train at least one low-light visibility enhancement model using the at least one dataset, wherein each low-light visibility enhancement model is trained to increase brightness in captured image frames.

[0008] Other technical features may be readily apparent to one skilled in the art from the following figures, descriptions, and claims.

[0009] For a more complete understanding of this disclosure and its advantages, reference is now made to the following description taken in conjunction with the accompanying drawings, in which:

[0010] FIG. 1 illustrates a network configuration including an electronic device in accordance with an embodiment of the present disclosure;

[0011] FIG. 2 illustrates a process for enhancing image visibility for video see-through (VST) extended reality (XR) or other applications in accordance with an embodiment of the present disclosure;

[0012] FIGS. 3A and 3B illustrate an architecture for fast low-light image visibility enhancement for VST XR or other applications in accordance with an embodiment of the present disclosure;

[0013] FIG. 4 illustrates a technique for creating a low-light visibility enhancement model in accordance with an embodiment of the present disclosure;

[0014] FIG. 5 illustrates a technique for applying adaptive low-light visibility enhancement in accordance with an embodiment of the present disclosure;

[0015] FIG. 6 illustrates a technique for performing adaptive low-light image frame detection in accordance with an embodiment of the present disclosure;

[0016] FIG. 7 illustrates a method for enhancing image visibility for VST XR or other applications in accordance with an embodiment of the present disclosure; and

[0017] FIG. 8 illustrates a method for training a low-light visibility enhancement model in accordance with an embodiment of the present disclosure.

[0018] It may be advantageous to set forth definitions of certain words and phrases used throughout this patent document. The terms "transmit," "receive," and "communicate," as well as derivatives thereof, encompass both direct and indirect communication. The terms "include" and "comprise," as well as derivatives thereof, mean inclusion without limitation. The term "or" is inclusive, meaning and / or. The phrase "associated with," as well as derivatives thereof, means to include, be included within, interconnect with, contain, be contained within, connect to or with, couple to or with, be communicable with, cooperate with, interleave, juxtapose, be proximate to, be bound to or with, have, have a property of, have a relationship to or with, or the like.

[0019] Moreover, various functions described below can be implemented or supported by one or more computer programs, each of which is formed from computer readable program code and embodied in a computer readable medium. The terms "application" and "program" refer to one or more computer programs, software components, sets of instructions, procedures, functions, objects, classes, instances, related data, or a portion thereof adapted for implementation in a suitable computer readable program code. The phrase "computer readable program code" includes any type of computer code, including source code, object code, and executable code. The phrase "computer readable medium" includes any type of medium capable of being accessed by a computer, such as read only memory (ROM), random access memory (RAM), a hard disk drive, a compact disc (CD), a digital video disc (DVD), or any other type of memory. A "non-transitory" computer readable medium excludes wired, wireless, optical, or other communication links that transport transitory electrical or other signals. A non-transitory computer readable medium includes media where data can be permanently stored and media where data can be stored and later overwritten, such as a rewritable optical disc or an erasable memory device.

[0020] As used here, terms and phrases such as "have," "may have," "include," or "may include" a feature (like a number, function, operation, or component such as a part) indicate the existence of the feature and do not exclude the existence of other features. Also, as used here, the phrases "A or B," "at least one of A and / or B," or "one or more of A and / or B" may include all possible combinations of A and B. For example, "A or B," "at least one of A and B," and "at least one of A or B" may indicate all of (1) including at least one A, (2) including at least one B, or (3) including at least one A and at least one B. Further, as used here, the terms "first" and "second" may modify various components regardless of importance and do not limit the components. These terms are only used to distinguish one component from another. For example, a first user device and a second user device may indicate different user devices from each other, regardless of the order or importance of the devices. A first component may be denoted a second component and vice versa without departing from the scope of this disclosure.

[0021] It will be understood that, when an element (such as a first element) is referred to as being (operatively or communicatively) "coupled with / to" or "connected with / to" another element (such as a second element), it can be coupled or connected with / to the other element directly or via a third element. In contrast, it will be understood that, when an element (such as a first element) is referred to as being "directly coupled with / to" or "directly connected with / to" another element (such as a second element), no other element (such as a third element) intervenes between the element and the other element.

[0022] As used here, the phrase "configured (or set) to" may be interchangeably used with the phrases "suitable for," "having the capacity to," "designed to," "adapted to," "made to," or "capable of" depending on the circumstances. The phrase "configured (or set) to" does not essentially mean "specifically designed in hardware to." Rather, the phrase "configured to" may mean that a device can perform an operation together with another device or parts. For example, the phrase "processor configured (or set) to perform A, B, and C" may mean a generic-purpose processor (such as a CPU or application processor) that may perform the operations by executing one or more software programs stored in a memory device or a dedicated processor (such as an embedded processor) for performing the operations.

[0023] The terms and phrases as used here are provided merely to describe some embodiments of this disclosure but not to limit the scope of other embodiments of this disclosure. It is to be understood that the singular forms "a," "an," and "the" include plural references unless the context clearly dictates otherwise. All terms and phrases, including technical and scientific terms and phrases, used here have the same meanings as commonly understood by one of ordinary skill in the art to which the embodiments of this disclosure belong. It will be further understood that terms and phrases, such as those defined in commonly-used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined here. In some cases, the terms and phrases defined here may be interpreted to exclude embodiments of this disclosure.

[0024] Examples of an "electronic device" according to embodiments of this disclosure may include at least one of a smartphone, a tablet personal computer (PC), a mobile phone, a video phone, an e-book reader, a desktop PC, a laptop computer, a netbook computer, a workstation, a personal digital assistant (PDA), a portable multimedia player (PMP), an MP3 player, a mobile medical device, a camera, or a wearable device (such as smart glasses, a head-mounted device (HMD), electronic clothes, an electronic bracelet, an electronic necklace, an electronic accessory, an electronic tattoo, a smart mirror, or a smart watch). Other examples of an electronic device include a smart home appliance. Examples of the smart home appliance may include at least one of a television, a digital video disc (DVD) player, an audio player, a refrigerator, an air conditioner, a cleaner, an oven, a microwave oven, a washer, a dryer, an air cleaner, a set-top box, a home automation control panel, a security control panel, a TV box (such as SAMSUNG HOMESYNC, APPLETV, or GOOGLE TV), a smart speaker or speaker with an integrated digital assistant (such as SAMSUNG GALAXY HOME, APPLE HOMEPOD, or AMAZON ECHO), a gaming console (such as an XBOX, PLAYSTATION, or NINTENDO), an electronic dictionary, an electronic key, a camcorder, or an electronic picture frame. Still other examples of an electronic device include at least one of various medical devices (such as diverse portable medical measuring devices (like a blood sugar measuring device, a heartbeat measuring device, or a body temperature measuring device), a magnetic resource angiography (MRA) device, a magnetic resource imaging (MRI) device, a computed tomography (CT) device, an imaging device, or an ultrasonic device), a navigation device, a global positioning system (GPS) receiver, an event data recorder (EDR), a flight data recorder (FDR), an automotive infotainment device, a sailing electronic device (such as a sailing navigation device or a gyro compass), avionics, security devices, vehicular head units, industrial or home robots, automatic teller machines (ATMs), point of sales (POS) devices, or Internet of Things (IoT) devices (such as a bulb, various sensors, electric or gas meter, sprinkler, fire alarm, thermostat, street light, toaster, fitness equipment, hot water tank, heater, or boiler). Other examples of an electronic device include at least one part of a piece of furniture or building / structure, an electronic board, an electronic signature receiving device, a projector, or various measurement devices (such as devices for measuring water, electricity, gas, or electromagnetic waves). Note that, according to various embodiments of this disclosure, an electronic device may be one or a combination of the above-listed devices. According to some embodiments of this disclosure, the electronic device may be a flexible electronic device. The electronic device disclosed here is not limited to the above-listed devices and may include any other electronic devices now known or later developed.

[0025] In the following description, electronic devices are described with reference to the accompanying drawings, according to an embodiment of this disclosure. As used here, the term "user" may denote a human or another device (such as an artificial intelligent electronic device) using the electronic device.

[0026] Definitions for other certain words and phrases may be provided throughout this patent document. Those of ordinary skill in the art should understand that in many if not most instances, such definitions apply to prior as well as future uses of such defined words and phrases.

[0027] FIGS. 1 through 8, discussed below, and an embodiment of the present disclosure are described with reference to the accompanying drawings. However, it should be appreciated that the present disclosure is not limited to the embodiment, and all changes and / or equivalents or replacements thereto also belong to the scope of this disclosure. The same or similar reference denotations may be used to refer to the same or similar elements throughout the specification and the drawings.

[0028] In the present disclosure, extended reality (XR) systems are becoming more and more popular over time, and numerous applications have been and are being developed for XR systems. Some XR systems (such as augmented reality (AR) systems and mixed reality (MR) systems) can enhance a user's view of his or her current environment by overlaying digital content (such as information or virtual objects) over the user's view of the current environment. For example, some XR systems can often seamlessly blend virtual objects generated by computer graphics with real-world scenes.

[0029] Optical see-through (OST) XR systems refer to XR systems in which users directly view real-world scenes through head-mounted devices (HMDs). OST XR systems face many challenges that can limit their adoption. Some of these challenges include limited fields of view, limited usage spaces (such as indoor-only usage), failure to display fully-opaque black objects, and usage of complicated optical pipelines that may require projectors, waveguides, and other optical elements. In contrast to OST XR systems, video see-through (VST) XR systems (also called "passthrough" XR systems) present users with generated video sequences of real-world scenes. VST XR systems can be built using virtual reality (VR) technologies and can have various advantages over OST XR systems. For example, VST XR systems can provide wider fields of view and can provide improved contextual augmented reality.

[0030] A VST XR device may include one or more imaging sensors (also called "see-through cameras") that capture high-resolution image frames of a user's surrounding environment. The captured high-resolution image frames may be processed through an image processing pipeline in order to generate or obtain final rendered views of the user's surrounding environment. VST XR devices may suffer from various issues. One such issue is that the image quality of the captured image frames can be affected by conditions in the surrounding environment and properties of the imaging sensors themselves. For example, when inadequate lighting is available in the user's surrounding environment, captured image frames can appear dark and noisy, which makes it difficult for the user to discern content in the captured image frames and can cause user discomfort.

[0031] An embodiment of the present disclosure is directed to a method and an electronic device for enhancing image visibility. An embodiment of the present disclosure may provide a method and an electronic device configured for fast low-light image visibility enhancement.

[0032] The present disclosure provides various techniques supporting fast low-light image visibility enhancement for VST XR or other applications. As described in more detail below, a first image frame of a scene may be obtained using at least one imaging sensor of an electronic device. A brightness-related metric (e.g., a low-light image score) indicative of a brightness of the first image frame may be determined by using at least one processor of the electronic device. The brightness-related metric refers to an indicator representing the brightness of an image frame. The low-light image score may be one type of the brightness-related metric. Based on the brightness-related metric satisfying a predefined condition indicative of low-light (e.g., a low-light image score indicating that the brightness of the first image frame is below a threshold), a visibility enhancement model (e.g., a low-light visibility enhancement model) may be applied to the first image frame in order to obtain (or generate) a second image frame having a higher brightness than the first image frame. The visibility enhancement model may be trained using at least one dataset that includes image frames obtained using the at least one imaging sensor of the electronic device. A visibility enhancement model may be trained using at least one dataset that includes image frames obtained using at least one imaging sensor. The visibility enhancement model may be trained on either an electronic device or a server.

[0033] The visibility enhancement model refers to a model configured to improve the perceptibility or clarity of visual information within an image frame. Such a model may be designed to enhance contrast, brightness, or local details of the image frame so that objects or features within the image become more distinguishable to a user or the electronic device. The low-light visibility enhancement model may be one type of the visibility enhancement model. The low-light visibility enhancement model may be configured to improve visibility under low-light conditions by reducing noise, boosting luminance, and enhancing spatial details in image frames captured in poor lighting. The visibility enhancement model may be executable by at least one processor of an electronic device or a server and may be stored in a memory. The predefined condition indicative of low-light may refer to a threshold or a range that has been previously determined based on one or more brightness-related metrics, such as a luminance value, histogram distribution, or a learned score (e.g., a low-light image score). The predefined condition may indicate that the brightness of an image frame is below a level considered appropriate for clear visibility and therefore requires enhancement.

[0034] As described in more detail below, image frames having different exposures may be obtained using at least one imaging sensor of an electronic device, and at least one training dataset may be generated (or obtained) using the image frames. A low-light visibility enhancement model may be trained using the at least one dataset, where the low-light visibility enhancement model may be trained to increase brightness in captured image frames. Training the low-light visibility enhancement model may include, for each of the at least one imaging sensor, identifying parameters of a response model and a brightness transform model based on at least part of the at least one dataset and generating (or obtaining) an exposure ratio map for adjusting image contrast and visibility (where the exposure ratio map may be based on the response model and the brightness transform model).

[0035] The present disclosure may be used to provide visual enhancement of image frames, including image frames captured indoors or outdoors in low-light environments. For example, the present disclosure may enable improved images to be rendered and displayed to users, even when those images are based on image frames that are noisy and captured in low-light conditions. As a result, this can significantly improve user experience, even in low-light environments. The present disclosure may be used to improve low-light image quality, remove low-light noise, and enhance image visibility, which may lead to the generation of normal-quality image frames captured in low-light environments. This type of functionality may find use in various applications, such as low-light image visibility enhancement for VST XR devices or other devices, low-light noise reduction for VST XR devices or other devices, and low-light image quality enhancement for VST XR devices or other devices.

[0036] FIG. 1 illustrates a network configuration 100 including an electronic device 101 in accordance with an embodiment of the present disclosure. The embodiment of the network configuration 100 shown in FIG. 1 is for illustration only. Other embodiments of the network configuration 100 may be used without departing from the scope of this disclosure.

[0037] According to an embodiment of the present disclosure, the electronic device 101 may be included in the network configuration 100. The electronic device 101 may include at least one of a bus 110, a processor 120, a memory 130, an input / output (I / O) interface 150, a display 160, a communication interface 170, and a sensor 180. In an embodiment, the electronic device 101 may exclude at least one of these components or may add at least one other component. The bus 110 may include a circuit for connecting the components 120-180 with one another and for transferring communications (such as control messages and / or data) between the components.

[0038] The processor 120 may include at least one processor or one or more processing devices, such as one or more microprocessors, microcontrollers, digital signal processors (DSPs), application specific integrated circuits (ASICs), or field programmable gate arrays (FPGAs). In an embodiment, the processor 120 may include at least one circuitry, such as one or more of a central processing unit (CPU), an application processor (AP), a communication processor (CP), a graphics processor unit (GPU), or a neural processing unit (NPU). The processor 120 may be able to perform control on at least one of the other components of the electronic device 101 and / or perform an operation or data processing relating to communication or other functions. As described below, the processor 120 may perform one or more functions related to fast low-light image visibility enhancement for VST XR or other applications. The processor 120 may perform one or more functions related to enhance image visibility for VST XR or other applications.

[0039] The memory 130 may include a volatile and / or non-volatile memory. For example, the memory 130 may store instructions (or processor-executable instructions) or data related to at least one other component of the electronic device 101. According to an embodiment of the present disclosure, the memory 130 may store software and / or a program 140. The program 140 may include, for example, a kernel 141, middleware 143, an application programming interface (API) 145, and / or an application program (or "application") 147. At least a portion of the kernel 141, middleware 143, or API 145 may be denoted an operating system (OS).

[0040] The kernel 141 may control or manage system resources (such as the bus 110, the processor 120, or the memory 130) used to perform operations or functions implemented in other programs (such as the middleware 143, API 145, or application 147). The kernel 141 provides an interface that allows the middleware 143, the API 145, or the application 147 to access the individual components of the electronic device 101 to control or manage the system resources. The application 147 may include one or more applications that, among other things, perform image visibility enhancement, including fast low-light image visibility enhancement, for VST XR or other applications. These functions may be performed by a single application or by multiple applications that each carries out one or more of these functions. The middleware 143 may function as a relay to allow the API 145 or the application 147 to communicate data with the kernel 141, for instance. A plurality of applications 147 may be provided. The middleware 143 is able to control work requests received from the applications 147, such as by allocating the priority of using the system resources of the electronic device 101 (like the bus 110, the processor 120, or the memory 130) to at least one of the plurality of applications 147. The API 145 may be an interface allowing the application 147 to control functions provided from the kernel 141 or the middleware 143. For example, the API 145 may include at least one interface or function (such as a command) for filing control, window control, image processing, or text control.

[0041] The I / O interface 150 may serve as an interface that may, for example, transfer commands or data input from a user or other external devices to other component(s) of the electronic device 101. The I / O interface 150 may output commands or data received from other component(s) of the electronic device 101 to the user or the other external device.

[0042] The display 160 may include, for example, a liquid crystal display (LCD), a light emitting diode (LED) display, an organic light emitting diode (OLED) display, a quantum-dot light emitting diode (QLED) display, a microelectromechanical systems (MEMS) display, or an electronic paper display. The display 160 may be a depth-aware display, such as a multi-focal display. The display 160 may be able to display, for example, various contents (such as text, images, videos, icons, or symbols) to the user. The display 160 may include a touchscreen and may receive, for example, a touch, gesture, proximity, or hovering input using an electronic pen or a body portion of the user.

[0043] The communication interface 170, for example, may be able to set up communication between the electronic device 101 and an external electronic device (such as a first electronic device 102, a second electronic device 104, or a server 106). For example, the communication interface 170 may be connected with a network 162 or 164 through wireless or wired communication to communicate with the external electronic device. The communication interface 170 may be a wired or wireless transceiver or any other component for transmitting and receiving signals.

[0044] The wireless communication may be able to use at least one of, for example, WiFi, long term evolution (LTE), long term evolution-advanced (LTE-A), 5th generation wireless system (5G), millimeter-wave or 60 GHz wireless communication, Wireless USB, code division multiple access (CDMA), wideband code division multiple access (WCDMA), universal mobile telecommunication system (UMTS), wireless broadband (WiBro), or global system for mobile communication (GSM), as a communication protocol. The wired connection may include, for example, at least one of a universal serial bus (USB), high-definition multimedia interface (HDMI), recommended standard 232 (RS-232), or plain old telephone service (POTS). The network 162 or 164 may include at least one communication network, such as a computer network (like a local area network (LAN) or wide area network (WAN)), Internet, or a telephone network.

[0045] The electronic device 101 may include one or more sensors 180 that may meter a physical quantity or detect an activation state of the electronic device 101 and convert metered or detected information into an electrical signal. For example, the sensor(s) 180 may include cameras or other imaging sensors, which may be used to capture image frames of scenes. The sensor(s) 180 may include one or more buttons for touch input, one or more microphones, a depth sensor, a gesture sensor, a gyroscope or gyro sensor, an air pressure sensor, a magnetic sensor or magnetometer, an acceleration sensor or accelerometer, a grip sensor, a proximity sensor, a color sensor (such as a red green blue (RGB) sensor), a bio-physical sensor, a temperature sensor, a humidity sensor, an illumination sensor, an ultraviolet (UV) sensor, an electromyography (EMG) sensor, an electroencephalogram (EEG) sensor, an electrocardiogram (ECG) sensor, an infrared (IR) sensor, an ultrasound sensor, an iris sensor, or a fingerprint sensor. The sensor(s) 180 may include one or more position sensors, such as an inertial measurement unit that may include one or more accelerometers, gyroscopes, and other components. In addition, the sensor(s) 180 may include a control circuit for controlling at least one of the sensors included here. Any of these sensor(s) 180 may be located within the electronic device 101.

[0046] In an embodiment, the electronic device 101 may be a wearable device or an electronic device-mountable wearable device (such as an HMD). For example, the electronic device 101 may represent an XR wearable device, such as a headset or smart eyeglasses. In an embodiment, the first electronic device 102 or the second electronic device 104 may be a wearable device or an electronic device-mountable wearable device (such as an HMD). In an embodiment, when the electronic device 101 is mounted in the electronic device 102 (such as the HMD), the electronic device 101 may communicate with the electronic device 102 through the communication interface 170. The electronic device 101 may be directly connected with the electronic device 102 to communicate with the electronic device 102 without involving with a separate network.

[0047] The first and second electronic devices 102 and 104 and the server 106 each may be a device of the same or a different type from the electronic device 101. According to an embodiment of the present disclosure, the server 106 may include a group of one or more servers. According to an embodiment of the present disclosure, all or some of the operations executed on the electronic device 101 may be executed on another or multiple other electronic devices (such as the first electronic device 102, the second electronic device 104, or the server 106). Further, according to an embodiment of the present disclosure, when the electronic device 101 should perform some function or service automatically or at a request, the electronic device 101, instead of executing the function or service on its own or additionally, may request another device (such as the first electronic device 102, the second electronic device 104, or the server 106) to perform at least some functions associated therewith. The other electronic device (such as the first electronic device 102, the second electronic device 104, or the server 106) may be able to execute the requested functions or additional functions and transfer a result of the execution to the electronic device 101. The electronic device 101 may provide a requested function or service by processing the received result as it is or additionally. To that end, a cloud computing, distributed computing, or client-server computing technique may be used, for example. While FIG. 1 shows that the electronic device 101 includes the communication interface 170 to communicate with the first electronic device 104 or the server 106 via the network 162 or 164, the electronic device 101 may be independently operated without a separate communication function according to an embodiment of the present disclosure.

[0048] The server 106 may include the same or similar components as the electronic device 101 (or a suitable subset thereof). The server 106 may support to drive the electronic device 101 by performing at least one of operations (or functions) implemented on the electronic device 101. For example, the server 106 may include a processing module or processor that may support the processor 120 implemented in the electronic device 101. As described below, the server 106 may perform one or more functions related to image visibility enhancement, including fast low-light image visibility enhancement, for VST XR or other applications.

[0049] FIG. 1 illustrates the network configuration 100 including the electronic device 101, however, various changes may be made to FIG. 1. For example, the network configuration 100 may include any number of each component in any suitable arrangement. In general, computing and communication systems come in a wide variety of configurations, and FIG. 1 does not limit the scope of this disclosure to any particular configuration. Also, while FIG. 1 illustrates one operational environment in which various features may be used, these features may be used in any other suitable system.

[0050] FIG. 2 illustrates a process 200 for enhancing image visibility for VST XR or other applications in accordance with an embodiment of the present disclosure. For ease of explanation, the process 200 shown in FIG. 2 is described as being performed using the electronic device 101 in the network configuration 100 shown in FIG. 1. However, the process 200 shown in FIG. 2 may be performed using any other suitable device(s) and in any other suitable system(s).

[0051] As shown in FIG. 2, the process 200 includes a low-light image enhancement model creation operation 202, which generally operates to create one or more low-light image enhancement models for use. Each low-light image enhancement model may represent a visibility enhancement model (or a low-light visibility enhancement model) that may be applied to captured image frames 204 in order to produce (or obtain) enhanced image frames 206. The enhanced image frames 206 may represent processed versions of the captured image frames 204 in which the brightness levels of the captured image frames 204 have been improved.

[0052] In an embodiment, the low-light image enhancement model creation operation 202 may include a response model generation function 208 and a brightness transform model generation function 210. The response model generation function 208 may operate to identify one or more response models for each imaging sensor 180, wherein each response model may define (or identify) a mathematical representation of how the imaging sensor 180 operates when capturing at least some of the captured image frames 204. A response model may include or represent a response function that defines a mapping of scene irradiance to image brightness or intensity based on the imaging sensor 180 used to obtain the captured image frames 204. The response model generation function 208 may use any suitable technique(s) to identify at least one response model for each imaging sensor 180. In an embodiment, multiple response models may be generated for each imaging sensor 180, wherein different response models may be associated with different scene brightnesses or different ranges of scene brightnesses.

[0053] The brightness transform model generation function 210 may operate to identify one or more brightness models (also called lightness models) for each imaging sensor 180, wherein each brightness model may define (or identify) another mathematical representation of how the imaging sensor 180 operates when capturing at least some of the captured image frames 204. A brightness model may include or represent a brightness transform function that defines how image data captured using the imaging sensor 180 may vary based on the exposure setting of the imaging sensor 180. The brightness transform model generation function 210 may use any suitable technique(s) to identify at least one brightness model for each imaging sensor 180. In an embodiment, multiple brightness models may be generated for each imaging sensor 180, wherein different brightness models may be associated with different scene brightnesses or different ranges of scene brightnesses (which may match the different scene brightnesses or different ranges of scene brightnesses during generation of multiple response models for each imaging sensor 180).

[0054] The low-light image enhancement model creation operation 202 may include a model generation function 212, which may operate to create one or more low-light image enhancement models based on the response model(s) and the brightness transform model(s) generated by the response model generation functions 208 and the brightness transform model generation function 210. For example, the model generation function 212 may combine each response model generated by the response model generation function 208 for an imaging sensor 180 and the corresponding brightness transform model generated by the brightness transform model generation function 210 for the same imaging sensor 180 in order to create (or obtain) a image enhancement model (or a low-light image enhancement model) for that imaging sensor 180. Note that this may be repeated any number of times to create (or obtain) multiple low-light image enhancement models for each imaging sensor 180, where different low-light image enhancement models may be associated with the different scene brightnesses or the different ranges of scene brightnesses. The model generation function 212 may use any suitable technique(s) to identify at least one low-light image enhancement model for each imaging sensor 180. In an embodiment, for instance, the model generation function 212 may integrate each brightness transform model and an associated exposure ratio map to generate an integrated brightness transform model and combine the integrated brightness transform model and the corresponding response model. Each exposure ratio map may represent a map used for adjusting image contrast and visibility of image frames captured using an associated imaging sensor 180.

[0055] A low-light image enhancement model application operation 214 may operate to apply the low-light image enhancement models created by the low-light image enhancement model creation operation 202 to the captured image frames 204 in order to produce the enhanced image frames 206. For example, the low-light image enhancement model application operation 214 may determine a brightness-related metric (e.g., a low-light image score) for each captured image frame 204, where the brightness-related metric is indicative of a brightness of the captured image frame 204. Based on the brightness-related metric satisfying a predefined condition indicative of low-light (for example, the predefined condition may comprise a condition in which the brightness of the first image frame is less than a threshold), a visibility enhancement model (e.g., a low-light visibility enhancement model) may be applied to the captured image frame 204 by the low-light image enhancement model application operation 214 in order to generate (or obtain) an enhanced image frame 206, which has a higher brightness than the brightness of the captured image frame 204. As noted above, there may be multiple low-light visibility enhancement models for each imaging sensor 180, and the low-light image enhancement model application operation 214 may select one of the visibility enhancement models for use with each captured image frame 204. For instance, the visibility enhancement model may be selected based on the brightness of the captured image frame 204, such as by selecting the visibility enhancement model generated using training images having the same or similar brightness. The low-light image enhancement model application operation 214 may use any suitable technique(s) to enhance image frames based on visibility enhancement models. In an embodiment, for instance, the visibility enhancement models may be used to apply brightness gains (positive or negative) at a per-pixel level to the captured image frames 204. In this way, the low-light image enhancement model application operation 214 may generate the enhanced image frames 206, which represent enhanced or improved versions of the captured image frames 204.

[0056] In this way, the process 200 may be used to create one or more low-light image visibility enhancement models with one or more parametric response models and one or more parametric brightness transform models, where the parameters of each low-light image visibility enhancement model may be learned from one or more training datasets captured using an associated imaging sensor 180. The low-light image visibility enhancement model(s) may be used to remove low-light noise or other noise and improve the visibility of captured image frames 204, which may involve selecting the appropriate low-light image visibility enhancement model for each captured image frame 204. In addition, as described below, a criterion may be created (such as by combining a signal-to-noise ratio and image brightness values) and used to quickly detect if each captured image frame 204 actually needs low-light noise removal and visibility enhancement. As a result, captured image frames 204 that are adequately bright need not undergo processing using low-light image visibility enhancement models, which may reduce the computational load on the processor(s) 120 of the electronic device 101.

[0057] FIG. 2 illustrates the process 200 for enhancing image visibility for VST XR or other applications, however, various changes may be made to FIG. 2. For example, various operations or functions in FIG. 2 may be combined, further subdivided, replicated, omitted, or rearranged and additional operations or functions may be added according to particular needs. The process 200 may represent a process for fast low-light image visibility enhancement for VST XR or other applications.

[0058] FIGS. 3A and 3B illustrate an architecture 300 for fast low-light image visibility enhancement for VST XR or other applications in accordance with an embodiment of the present disclosure. For ease of explanation, the architecture 300 shown in FIGS. 3A and 3B is described as being implemented using the electronic device 101 in the network configuration 100 shown in FIG. 1, where the electronic device 101 may implement the process 200 shown in FIG. 2. However, the architecture 300 may be implemented using any other suitable device(s) and in any other suitable system(s), and the architecture 300 may be used to implement any other suitable process(es) designed in accordance with this disclosure.

[0059] As shown in FIG. 3A, one or more imaging sensors 180 may be used to obtain (or generate) image frames. In this example, a decision operation 302 may determine whether the image frames will be used for model training purposes. If so, the architecture 300 may be used to implement the low-light image enhancement model creation operation 202 described above. For example, a dataset building operation 304 may operate to create one or more training datasets for each imaging sensor 180. The dataset building operation 304 may include an image frame capture function 306, an image frame conversion function 308, and a dataset integration function 310. Here, the image frame capture function 306 may operate to obtain a set of image frames using a designated imaging sensor 180, where the set of image frames may be captured using the same or substantially the same exposure setting(s) (such as the same exposure time). Each image frame may optionally be provided to the image frame conversion function 308, which may operate to convert each image frame from a first image format that lacks luminance data into a second image format that includes luminance data. Any suitable image formats may be supported here. As particular examples, the image frames obtained by the image frame capture function 306 may be in RGB format, and the image frames may be converted into YUV or YCbCr format or hue, saturation, and value (HSV) format. In an embodiment in which the image frame conversion function 308 is used, the conversion may allow modification of the contrast of the image frames to enhance visibility, which may reduce computational load. The dataset integration function 310 may operate to combine the image frames (or converted versions thereof) into a training dataset for the designated imaging sensor 180, where that training dataset may be associated with the specific exposure setting(s) used to obtain the captured image frames 204.

[0060] A decision operation 312 may operate to determine if at least one training dataset has been generated for each exposure setting for which training will be performed. For example, training datasets may be produced for a number of exposure settings (such as exposure settings like EV-2, EV-1, EV0, EV+1, EV+2, etc.). If not, the dataset building operation 304 may be used to generate at least one additional training dataset for the same imaging sensor 180 but using one or more different exposure settings. A decision operation 314 may operate to determine if at least one training dataset has been generated for each imaging sensor 180. If not, the dataset building operation 304 may be used to generate at least one training dataset for a different imaging sensor 180 at one or more exposure settings. This approach may be useful, for instance, to collect training datasets for left and right see-through cameras or other stereo imaging sensors 180 of a VST XR device.

[0061] This process results in the generation of one or more training datasets 316, where each training dataset 316 may be associated with a specified imaging sensor 180 and a specified exposure setting. There may be multiple training datasets for each imaging sensor 180, where different training datasets may be associated with different exposure settings. An image enhancement model creation operation 318 may operate to obtain (or create) one or more low-light image enhancement models using the training datasets 316. In an embodiment, for instance, the image enhancement model creation operation 318 may generate a low-light image enhancement model for each exposure setting of each imaging sensor 180.

[0062] In an embodiment, the image enhancement model creation operation 318 may include a response model parameter fitting function 320, a brightness transform model parameter fitting function 322, and an exposure ratio map generation function 324. The response model parameter fitting function 320 may operate to process each training dataset 316 and generate a corresponding response model for the associated imaging sensor 180. Each response model may define (or identify) a mathematical representation of how the associated imaging sensor 180 operates when capturing image frames (at least at the corresponding exposure setting). Here, the response model may include or represent a response function that defines a mapping of scene irradiance to image brightness or intensity based on the imaging sensor 180 used to capture the image frames in the training dataset 316, and the response model parameter fitting function 320 may identify parameters of the response function based on the training dataset 316. The response model parameter fitting function 320 may use any suitable curve-fitting technique or other technique to identify parameters of response models.

[0063] The brightness transform model parameter fitting function 322 may operate to process each training dataset 316 and generate a corresponding brightness transform model for the associated imaging sensor 180. Each brightness transform model may define or identify another mathematical representation of how the imaging sensor 180 operates when capturing image frames (at least at the corresponding exposure setting). Here, the brightness transform model may include or represent a brightness transform function that defines how image data captured using the imaging sensor 180 may vary based on the exposure setting of the imaging sensor 180, and the brightness transform model parameter fitting function 322 may define or identify parameters of the brightness transform function based on the training dataset 316. The brightness transform model parameter fitting function 322 may use any suitable curve-fitting technique or other technique to identify parameters of brightness transform models.

[0064] The exposure ratio map generation function 324 may operate to identify an exposure ratio map for each imaging sensor 180. Each exposure ratio map may represent a mapping that identifies an exposure ratio at each pixel of the image frames captured by the associated imaging sensor 180. As described below, each brightness transform model may be a function of the associated exposure ratio map, and identifying the actual exposure ratio map for each imaging sensor 180 allows each brightness transform model to be integrated with its associated exposure ratio map during creation of low-light image enhancement models. The exposure ratio map generation function 324 may use any suitable technique to identify exposure ratio maps for imaging sensors 180. The image enhancement model creation operation 318 may use the response models, brightness transform models, and exposure ratio maps to create low-light image enhancement models 326. For instance, the image enhancement model creation operation 318 may generate (or create, or obtain) a low-light image enhancement model 326 for each exposure setting of each imaging sensor 180.

[0065] In FIG. 3B, when the decision operation 302 determines that the image frames captured using the imaging sensors 180 are not used for model training purposes, an image frame capture operation 328 may operate to obtain image frames from the one or more imaging sensors 180. A low-light image score calculation operation 330 may operate to identify a low-light image score for each captured image frame, where the low-light image score is indicative of a brightness of the associated image frame. The low-light image score may be determined in any suitable manner, such as when the low-light image score may be based on the signal-to-noise ratio and average brightness of the associated image frame. A decision operation 332 may operate to determine if each image frame represents a low-light image frame, such as by comparing the low-light image score for each image frame to a specified threshold. For each image frame that is a low-light image frame (such as when its low-light image score is below the threshold), the image frame may be provided to a low-light image enhancement model application operation 334, which may represent or implement the low-light image enhancement model application operation 214 described above. For each image frame that is not a low-light image frame, the image frame may be provided to a passthrough transformation operation 338.

[0066] The low-light image enhancement model application operation 334 may apply the low-light image enhancement models 326 generated by the image enhancement model creation operation 318 to the low-light image frames, thereby generating enhanced image frames. For example, for each low-light image frame, the low-light image enhancement model application operation 334 may select one of multiple low-light image enhancement models (such as based on the imaging sensor 180 that captured the low-light image frame and the overall brightness of the low-light image frame) and apply the selected low-light image enhancement model to the low-light image frame. Gains in the selected low-light image enhancement model may be applied to the pixels of the low-light image frame so that the resulting enhanced image frame has a higher brightness than the brightness of the low-light image frame.

[0067] In an embodiment, the low-light image enhancement model application operation 334 may include a conversion of the low-light image frame from a first image format that lacks luminance data to a second image format that includes luminance data. In an embodiment, an image frame conversion operation 336 may optionally be used to convert each enhanced image frame from the second image format back into the first image format or to a third image format. Any suitable image formats may be supported here. For example, the enhanced image frames generated by the low-light image enhancement model application operation 334 may be in YUV, YCbCr, or HSV format, and the enhanced image frames may be converted into RGB format.

[0068] Non-low-light image frames and enhanced image frames may be provided to the passthrough transformation operation 338, which may operate to apply one or more transformations to the image frames in order to generate transformed image frames. For example, the passthrough transformation operation 338 may apply transformations to compensate for things like registration and parallax errors, which may be caused by factors like differences between the positions of the imaging sensor(s) 180 and a user's eyes. That is, the captured image frames 204 are obtained by one or more imaging sensor(s) 180 at one or more locations, but rendered images are viewed by a user's eyes that are at different locations. The passthrough transformation operation 338 may apply one or more transformations in order to compensate for these differences in viewpoints. In an embodiment, the passthrough transformation operation 338 may apply a rotation and / or a translation to each image frame in order to compensate for these or other types of issues. The transformations may give the appearance that the images presented to the user were captured from the locations of the user's eyes, even though the image frames were actually captured from one or more different locations. Oftentimes, the rotation and / or translation may be derived mathematically based on the position and orientation (or angle) of each imaging sensor 180 and the expected or actual positions of the user's eyes. In an embodiment, the transformations may be static (since these positions and orientations (or angles) do not change), allowing passthrough transformations to be applied more quickly.

[0069] A head pose change compensation operation 340 may operate to apply an additional transformation to reproject each of the transformed image frames generated by the passthrough transformation operation 338 based on a head pose change of the user (if necessary). For example, the head pose change compensation operation 340 may obtain inputs from at least one motion sensor (e.g., an Inertial Measurement Unit (IMU)), a head pose tracking camera, or other position sensor(s) 180 of the electronic device 101 while image frames are being captured using the one or more imaging sensors 180. The head pose change compensation operation 340 may use this information to estimate what the user's head pose will likely be when rendered images are actually displayed to the user. In an embodiment, for example, image frames may be captured at one time and rendered images may be subsequently displayed to the user after some delay during which the user may move his or her head. The head pose change compensation operation 340 may be used to estimate, for each image frame, the likely head pose of the user at the time the rendered image based on that image frame is displayed. The head pose change compensation operation 340 may apply a translation, rotation, and / or other transformation to each transformed image frame, which may result in the generation of additional transformed image frames.

[0070] A frame rendering operation 342 may operate to create final views of a scene captured in the transformed image frames. The frame rendering operation 342 may render the final views for presentation to a user of the electronic device 101. For example, the frame rendering operation 342 may process the transformed image frames and perform any additional refinements or modifications needed or desired, and the resulting images may represent the final views of the scene. For example, a 3D-to-2D warping may be used to warp the final views of the scene into 2D images. The frame rendering operation 342 may present the rendered images to the user. For example, the frame rendering operation 342 may render the images into a form suitable for transmission to at least one display 160 and may initiate display of the rendered images, such as by providing the rendered images to one or more displays 160. In an embodiment, there may be a single display 160 on which the rendered images are presented for viewing by the user, such as where each eye of the user views a different portion of the display 160. In an embodiment, there may be separate displays 160 on which the rendered images are presented for viewing by the user, such as one display 160 for each of the user's eyes.

[0071] Although FIGS. 3A and 3B illustrate an architecture 300 for fast low-light image visibility enhancement for VST XR or other applications, various changes may be made to FIGS. 3A and 3B. For example, various components, operations, or functions in FIGS. 3A and 3B may be combined, further subdivided, replicated, omitted, or rearranged and additional components, operations, or functions may be added according to particular needs. Also, this example assumes that response and brightness transform models are used to generate low-light image enhancement models 326, where parameters of the response and brightness transform models are identified using curve fitting. However, other techniques for generating low-light image enhancement models may be used, such as when one or more machine learning models are used to process the training datasets 316 and identify parameters of the low-light image enhancement models 326. In addition, while certain image formats (such as RGB, YUV, YCbCr, and HSV formats) are described above, other image formats may be used. For example, each low-light RGB image frame may be converted into a L-a-b image format, where the L (lightness) component undergoes contrast improvement to enhance the visibility of the low-light image frame (possibly followed by conversion back to the RGB image format or another image format).

[0072] FIG. 4 illustrates a technique 400 for creating a low-light image enhancement model 326 in accordance with an embodiment of the present disclosure. The technique 400 may, for example, be performed as part of the low-light image enhancement model creation operation 202 of FIG. 2 or as part of the image enhancement model creation operation 318 of FIG. 3A. For ease of explanation, the technique 400 shown in FIG. 4 is described as being performed using the electronic device 101 in the network configuration 100 shown in FIG. 1, wherein the electronic device 101 may implement the process 200 shown in FIG. 2 and / or the architecture 300 shown in FIGS. 3A and 3B. However, the technique 400 may be performed using any other suitable device(s) and in any other suitable system(s), and the technique 400 may be used to implement any other suitable process(es) or architecture(s).

[0073] As shown in FIG. 4, the technique 400 may involve the use of at least one training dataset 316, along with one or more imaging sensor properties 402 and one or more image frame exposure properties 404. In an embodiment, the image frames of the training dataset 316 may have been converted into an image format that includes luminance data, such as YUV, YCbCr, HSV, or L-a-b format. The one or more imaging sensor properties 402 are associated with the imaging sensor 180 used to capture the image frames in the training dataset 316, such as one or more intrinsic parameters of the associated imaging sensor 180. Intrinsic parameters may include focal distance (focal length) and coordinates of the center of the imaging sensor 180 in a camera coordinate system. The one or more image frame exposure properties 404 are associated with the exposure setting of the imaging sensor 180 used to capture the image frames in the training dataset 316, such as an exposure time.

[0074] A response model generation operation 406 may operate to process at least some of these inputs in order to generate a response model for the imaging sensor 180 at the exposure setting associated with the training dataset 316. For example, a response function creation operation 408 may be used to generate a response function for the imaging sensor 180, and a parameter estimation operation 410 may be used to estimate parameters of the response function (e.g., via curve fitting). A brightness transform model generation operation 412 may operate to process at least some of these inputs in order to generate a brightness transform model for the imaging sensor 180 at the exposure setting associated with the training dataset 316. For example, a brightness transform function creation operation 414 may be used to generate a brightness transform function for the imaging sensor 180, and a parameter estimation operation 416 may be used to generate parameters of the brightness transform function (e.g., via curve fitting).

[0075] An exposure ratio map estimation operation 418 may operate to process the response and brightness transform functions in order to generate an exposure ratio map for the imaging sensor 180. The exposure ratio map may represent a map used for adjusting image contrast and visibility of image frames captured using the imaging sensor 180. The exposure ratio map and the response and brightness transform functions may be used by an enhancement model generation operation 420, which may generate a low-light image enhancement model 326 based on the training dataset 316.

[0076] In an embodiment, the creation of a low-light image enhancement model 326 may occur as follows. The response function creation operation 408 may generate a response function based on Equation 1 below.

[0077] ... (1)

[0078] Here, represents a pixel value at coordinates , represents image irradiance at coordinates , and represents a nonlinear response function. The parameter estimation operation 410 may estimate the parameters of the function using one or more training datasets 316 generated using the imaging sensor 180 at one or more exposure settings.

[0079] In an embodiment, the response function may be defined according to Equation 2 below.

[0080]

[0081] ... (2)

[0082] Here, represents image irradiance, and represents camera parameters (which, in an embodiment, may be obtained during manufacturing calibration or other types of calibration).

[0083] The brightness transform function creation operation 414 may generate a brightness transform function based on Equation 3 below.

[0084] ... (3)

[0085] Here, represents a pixel value at exposure , represents a pixel value at exposure , represents an exposure ratio map, and represents a brightness transform function. The parameter estimation operation 416 may estimate the parameters of the function using one or more training datasets 316 generated using the imaging sensor 180 at one or more exposure settings. In an embodiment, the brightness transform function may be defined according to Equation 4 below.

[0086] ... (4)

[0087] Here, represents an original image frame, and represents imaging sensor parameters.

[0088] Using the generated response model and brightness transform model, the exposure ratio map estimation operation 418 may estimate the exposure map , which may define an exposure ratio at each pixel of an image to be enhancement. The enhancement model generation operation 420 may integrate the brightness transform model with the estimated exposure ratio map since the brightness transform function is a function of the estimated exposure ratio map, thereby generating an integrated brightness transform model. The low-light image enhancement models 326 may be generated using a combination of the integrated brightness transform model and the response model.

[0089] FIG. 4 illustrates a technique 400 for creating a low-light image enhancement model 326, however, various changes may be made to FIG. 4. For example, a low-light image enhancement model 326 may be generated in any other suitable manner, such as by using one or more trained machine learning models.

[0090] FIG. 5 illustrates a technique 500 for applying adaptive low-light visibility enhancement in accordance with an embodiment of the present disclosure. The technique 500 may, for example, be performed as part of the low-light image enhancement model application operation 214 of FIG. 2 or as part of the low-light image enhancement model application operation 334 of FIG. 3B. For ease of explanation, the technique 500 shown in FIG. 5 is described as being performed using the electronic device 101 in the network configuration 100 shown in FIG. 1, where the electronic device 101 may implement the process 200 shown in FIG. 2 and / or the architecture 300 shown in FIGS. 3A and 3B. However, the technique 500 may be performed using any other suitable device(s) and in any other suitable system(s), and the technique 500 may be used to implement any other suitable process(es) or architecture(s).

[0091] As shown in FIG. 5, the technique 500 may involve the processing of image frames 502, which may be captured using one or more imaging sensors 180 and the image frame capture operation 328. The image frames 502 may optionally be provided to an image frame conversion operation 504, which may convert the image frames 502 from a first image format that lacks luminance data (such as RGB format) into a second image format that includes luminance data (such as YUV, YCbCr, HSV, or L-a-b format). The luminance channel of each image frame 502 may be processed subsequently to provide image enhancement, with or without modifications to other color channels of each image frame 502.

[0092] In an embodiment, the low-light image enhancement models 326 (which are created using response models and brightness transform models based on training datasets 316 as described above) may be provided to a model application operation 506, which may operate to apply a selected low-light image enhancement model 326 to each image frame 502. In an embodiment, the model application operation 506 may include a model parameter extraction function 508, a noise reduction function 510, and an image contrast enhancement function 512.

[0093] The model parameter extraction function 508 may operate to identify the parameters of the selected low-light image enhancement model 326 to be applied to each image frame 502. The noise reduction function 510 may operate to perform noise reduction in order to at least partially remove noise from each image frame 502. For example, the noise reduction function 510 may perform filtering or other suitable noise removal technique(s) in order to remove noise and replace the noise with suitable image data. In an embodiment, the noise reduction function 510 may use the parameters of the low-light image enhancement model 326 selected for each image frame 502 when performing noise reduction. The image contrast enhancement function 512 may operate to perform adaptive image contrast enhancement for each image frame 502 based on the parameters of the low-light image enhancement model 326 selected for use with that image frame 502. For example, the image contrast enhancement function 512 may use the parameters of the selected low-light image enhancement model 326 to identify gains to be applied to at least the luminance data of the associated image frame 502. For each image frame 502, the model application operation 506 may generate an enhanced image frame, which may optionally be provided to the image frame conversion operation 336 for conversion.

[0094] FIG. 5 illustrates a technique 500 for applying adaptive low-light visibility enhancement, however, various changes may be made to FIG. 5. For example, a low-light image enhancement model 326 may be applied in any other suitable manner.

[0095] FIG. 6 illustrates a technique 600 for performing adaptive low-light image frame detection in accordance with an embodiment of the present disclosure. The technique 600 may, for example, be performed as part of the low-light image score calculation operation 330 and the decision operation 332 of FIG. 3B to determine if an image frame represents a low-light image frame. For ease of explanation, the technique 600 shown in FIG. 6 is described as being performed using the electronic device 101 in the network configuration 100 shown in FIG. 1, wherein the electronic device 101 may implement the process 200 shown in FIG. 2 and / or the architecture 300 shown in FIGS. 3A and 3B. However, the technique 600 may be performed using any other suitable device(s) and in any other suitable system(s), and the technique 600 may be used to implement any other suitable process(es) or architecture(s).

[0096] As shown in FIG. 6, each image frame 502 may be provided to a user focus region identification operation 602, which may operate to identify an area of the image frame 502 associated with a region of a scene at which the user appears to be gazing or on which the user appears to be focusing (if any). This may be done in any suitable manner, such as by using one or more eye tracking and gaze estimation techniques, such as one based on gaze direction estimation and focal length estimation. An analysis window identification operation 604 may identify a window within the image frame 502 to be analyzed, where image contents within the window may be used to determine if the image frame 502 represents a low-light image frame. For example, the analysis window identification operation 604 may define a window within each image frame 502 that matches or includes the focus region identified within that image frame 502 by the user focus region identification operation 602.

[0097] A max / min / mean pixel processing operation 606 may operates to identify the largest (maximum) and smallest (minimum) pixel values within the analysis window and the average (mean) pixel value within the analysis window for each image frame 502. In an embodiment, the minimum pixel value , the maximum pixel value , and the average pixel value may be expressed according to Equation 5 below.

[0098] ... (5)

[0099] Here, represents an image frame 502, represents an analysis window within the image frame 502, and represents each pixel in the analysis window . A deviation / error pixel processing operation 608 may operate to identify the standard deviation of the pixel values within the analysis window for each image frame 502. In an embodiment, the standard deviation may be determined according to Equation 6 below.

[0100] ... (6)

[0101] Here, represents the number of the pixels in the analysis window , represents the mean pixel value in the analysis window , represents the standard deviation of the pixel values in the analysis window , and represents each pixel in the analysis window .

[0102] A pixel signal may be defined as equal to , and a noise signal may be defined as equal to . An SRN calculation operation 612 may operate to calculate the SNR of each image frame 502 (or the SNR of the analysis window within each image frame 502) using the pixel and noise signals. For example, the SRN calculation operation 612 may calculate the SNR of each image frame 502 according to Equation 7 below.

[0103] ... (7)

[0104] A low-light criterion identification operation 614 may operate to create a criterion for determining whether each image frame 502 represents a low-light image frame. In an embodiment, the criterion may be based on the average pixel value and the SNR value . For example, the low-light criterion identification operation 614 may use the following criterion to determine whether each image frame 502 represents a low-light image frame.

[0105]

[0106] ... (8)

[0107] Here, represents a threshold of the low-light image value for the image frame 502, and represents a threshold of the signal-to-noise ratio for the image frame 502. A low-light image score may be defined as the average pixel value , optionally in combination with the SNR value .

[0108] FIG. 6 illustrates a technique 600 for performing adaptive low-light image frame detection, however, various changes may be made to FIG. 6. For example, any other suitable low-light criterion based on any other suitable low-light score (which may or may not include average image brightness and / or SNR) may be used.

[0109] FIG. 7 illustrates a method 700 for enhancing image visibility for VST XR or other applications in accordance with an embodiment of the present disclosure. For ease of explanation, the method 700 shown in FIG. 7 is described as being performed using the electronic device 101 in the network configuration 100 shown in FIG. 1, wherein the electronic device 101 may implement the process 200 shown in FIG. 2 and / or the architecture 300 shown in FIGS. 3A and 3B. However, the method 700 may be performed using any other suitable device(s) and in any other suitable system(s), and the method 700 may be implemented using any other suitable process(es) or architecture(s) designed in accordance with this disclosure.

[0110] As shown in FIG. 7, a first image frame of a scene may be obtained at step 702. At step 702, the processor 120 of the electronic device 101 may obtain an image frame 502 captured using at least one imaging sensor 180 of the electronic device 101. A brightness-related metric (e.g., a low-light image score) indicative of a brightness of the first image frame may be determined at step 704. At step 704, the processor 120 of the electronic device 101 may obtain (or calculate) an average pixel value and an SNR value for at least a portion of the image frame 502, such as for pixel values within an analysis window of the image frame 502, and may determine the brightness-related metric of the first image frame by using the obtained average pixel value and / or the obtained SNR value. The analysis window may include or be defined as a portion of the first image frame representing an area in the scene on which a user's eyes are gazing or focused. For example, the processor 120 may determine the brightness-related metric based on a pixel value included in the analysis window. A determination is made whether the brightness represented by the brightness-related metric (e.g., the low-light image score) is less than a specified threshold value at step 706. For example, at step 706, the processor 120 of the electronic device 101 may compare the average pixel value and / or the SNR value with one or more threshold values. For example, at step 706, the processor 120 may compare the brightness-related metric (or the low-light image score) with a predefined threshold value. The determining, in step S706, whether the brightness represented by the brightness-related metric is less than the specific threshold value may correspond to determining whether the brightness represented by the brightness-related metric satisfies a predefined condition (or defined condition). The predefined condition may indicate a low-light situation, such as a condition in which a scene lacks sufficient illumination or the ambient light level is below a defined threshold. The predefined condition indicative of low-light may include a condition in which the brightness of the first image frame is less than the specified threshold value.

[0111] If the brightness represented by the brightness-related metric (or a low-light image score) is less than the specified threshold, the processor 120 may determine that the image frame 502 represents a low-light image frame. In this case, a visibility enhancement model (or a low-light visibility enhancement model) may be selected at step 708. For example, at step 708, the processor 120 of the electronic device 101 may select the low-light image enhancement model 326 that is (i) associated with the imaging sensor(s) 180 used to capture the image frame 502 and (ii) associated with the same or similar average or overall brightness as the image frame 502. The selected low-light visibility enhancement model may be applied to the first image frame in order to generate a second image frame at step 710. For example, at step 710, the processor 120 of the electronic device 101 may apply gains defined by the selected low-light image enhancement model 326 to luminance data of the image frame 502 in order to perform contrast enhancement and generate an enhanced image frame. The enhanced image frame has a higher brightness than the brightness of the original image frame 502. For example, the first image frame may be converted from a first image format that does not include luminance data to a second image format that includes luminance data before the low-light image enhancement model 326 is applied, and the second image frame may be converted from the second image format into the first image format or a third image format after the low-light image enhancement model 326 is applied. If the brightness represented by the brightness-related metric (or the low-light image score) is greater than or equal to the specified threshold, the processor 120 may determine that the image frame 502 does not represent a low-light image frame. In that case, the processor 120 of the electronic device 101 may refrain from applying a low-light image enhancement model 326 to the first image frame.

[0112] An image frame (either the first image frame, if low-light visibility enhancement is not applied, or the second image frame, if low-light visibility enhancement is applied) may be rendered at step 712, and display of the rendered image is initiated at step 714. For example, the processor 120 of the electronic device 101 may apply a passthrough transformation, head pose change compensation transformation, and / or other transformation(s) to the image frame. The processor 120 of the electronic device 101 may render the resulting transformed image frame and display the rendered image on at least one display 160 of the electronic device 101.

[0113] FIG. 7 illustrates a method 700 for enhancing image visibility enhancement for VST XR or other applications, however various changes may be made to FIG. 7. For example, while shown as a series of steps, various steps in FIG. 7 may overlap, occur in parallel, occur in a different order, or occur any number of times (including zero times). Also, the method 700 may be duplicated or repeatedly used in order to process multiple image frames, such as sequences of image frames from left and right see-through cameras or other sets of imaging sensors 180.

[0114] FIG. 8 illustrates a method 800 for training a low-light visibility enhancement model in accordance with an embodiment of the present disclosure. For ease of explanation, the method 800 shown in FIG. 8 is described as being performed using the electronic device 101 in the network configuration 100 shown in FIG. 1, wherein the electronic device 101 may implement the process 200 shown in FIG. 2 and / or the architecture 300 shown in FIGS. 3A and 3B. However, the method 800 may be performed using any other suitable device(s) and in any other suitable system(s), and the method 800 may be implemented using any other suitable process(es) or architecture(s) designed in accordance with this disclosure.

[0115] As shown in FIG. 8, image frames captured using different exposures may be obtained at step 802. For example, the processor 120 of the electronic device 101 may obtain multiple image frames captured using each of one or more imaging sensors 180 of the electronic device 101. The multiple image frames for each imaging sensor 180 may be captured using different exposures, such as different exposure times or other exposure settings. One or more training datasets may be generated (or obtained) using the image frames at step 804. For example, the processor 120 of the electronic device 101 may create (or obtain) a training dataset 316 for each exposure setting of each imaging sensor 180.

[0116] An imaging sensor of the electronic device 101 and an exposure setting (or an exposure value) may be selected at step 806. For example, the processor 120 of the electronic device 101 may select a specified imaging sensor 180 and select one of the exposure settings for that imaging sensor 180 used to capture image frames in at least one of the training datasets 316. For example, the exposure settings may include at least one of International Organization for Standardization (ISO), shutter speed, or aperture. Training of a low-light visibility enhancement model for the selected imaging sensor and the selected exposure setting may be initiated at step 808. For example, the processor 120 of the electronic device 101 may invoke the image enhancement model creation operation 318 for the selected imaging sensor 180 and the selected exposure setting using the training dataset(s) 316 associated with the selected imaging sensor 180 and the selected exposure setting.

[0117] During the training, parameters of a response model and a brightness transform model may be identified at step 810. For example, the processor 120 of the electronic device 101 may identify parameters for a response model associated with the selected imaging sensor 180 based on the images in the associated training dataset(s) 316 and one or more imaging sensor properties 402 for the selected imaging sensor 180. The processor 120 of the electronic device 101 may identify parameters for a brightness transform model associated with the selected imaging sensor 180 based on the images in the associated training dataset(s) 316, the one or more imaging sensor properties 402 for the selected imaging sensor 180, and one or more image frame exposure properties 404. Thus, the parameters of the response model and the brightness transform model may be based on at least part of the training dataset(s) 316. An exposure ratio map for adjusting image contrast and visibility may be generated at step 812. For example, the processor 120 of the electronic device 101 may generate an exposure ratio map as described above. Parameters of a low-light visibility enhancement model may be identified at step 814. For example, the processor 120 of the electronic device 101 may generate the low-light image enhancement model 326 based on the response model, the brightness transform model, and the exposure ratio map. For example, the exposure ratio map may be integrated with the brightness transform model to generate an integrated brightness transform model, and the integrated brightness transform model and the response model may be combined to generate the low-light image enhancement model 326. In an embodiment, the image frames in the training dataset(s) 316 may be converted from a first image format that does not include luminance data into a second image format that includes luminance data before being used to generate the low-light image enhancement model 326.

[0118] A determination may be made whether to repeat the training and generate another low-light visibility enhancement model at step 816. For example, the processor 120 of the electronic device 101 may determine whether a low-light image enhancement model 326 has been generated for each exposure setting of each imaging sensor 180. If not, the process may return to step 806 to select another imaging sensor / exposure setting combination (or a different imaging sensor and exposure setting combination). Depending on the situation, the processor 120 may select another exposure setting for the same imaging sensor 180 selected in the previous iteration, or select an exposure setting for another imaging sensor (or a different imaging sensor) 180.

[0119] FIG. 8 illustrates a method 800 for training a low-light image enhancement model 326, however, various changes may be made to FIG. 8. For example, while shown as a series of steps, various steps in FIG. 8 may overlap, occur in parallel, occur in a different order, or occur any number of times (including zero times).

[0120] It should be noted that the functions shown in or described with respect to FIGS. 2 through 8 may be implemented in the electronic device 101, the first electronic device (or a first external electronic device) 102, the second electronic device (or a second external electronic device) 104, server 106, or other device(s) in any suitable manner. For example, in an embodiment, at least some of the functions shown in or described with respect to FIGS. 2 through 8 may be implemented or supported using one or more software applications or other software instructions that are executed by the processor 120 of the electronic device 101, 102, 104, server 106, or other device(s). In an embodiment, at least some of the functions shown in or described with respect to FIGS. 2 through 8 may be implemented or supported using dedicated hardware components. In general, the functions shown in or described with respect to FIGS. 2 through 8 may be performed using any suitable hardware or any suitable combination of hardware and software / firmware instructions. Also, the functions shown in or described with respect to FIGS. 2 through 8 may be performed by a single device or by multiple devices.

[0121] According to an embodiment of the present disclosure, the visibility enhancement model comprises a specified one of multiple low-light visibility enhancement models, and the method further comprises selecting the specified low-light visibility enhancement model from among the multiple low-light visibility enhancement models based on the brightness of the first image frame, by using the at least one processor (120).

[0122] According to an embodiment of the present disclosure, the predefined condition indicative of low-light comprises a condition in which the brightness of the first image frame is less than a threshold, and the method further comprises, based on the brightness-related metric indicating that the brightness of the first image frame is greater than or equal to the threshold, refraining from applying the visibility enhancement model to the first image frame, by using the at least one processor (120), the visibility enhancement model comprises a low-light visibility enhancement model.

[0123] According to an embodiment of the present disclosure, the method further comprises training the low-light visibility enhancement model using the at least one dataset, by using the at least one processor (120), wherein the training the low-light visibility enhancement model comprises, for each of the at least one imaging sensor, identifying parameters of a response model and a brightness transform model based on at least part of the at least one dataset, obtaining an exposure ratio map for adjusting image contrast and visibility, integrating the brightness transform model and the exposure ratio map to obtain an integrated brightness transform model, and combining the integrated brightness transform model and the response model.

[0124] According to an embodiment of the present disclosure, the brightness-related metric comprises a low-light image score, wherein the low-light image score comprises a signal-to-noise ratio (SNR) and an image brightness value associated with the first image frame.

[0125] According to an embodiment of the present disclosure, the low-light image score is based on image data in a portion of the first image frame, the portion of the first image frame representing an area in the scene on which a user's eyes are gazing or focused.

[0126] According to an embodiment of the present disclosure, the method further comprises prior to application of the visibility enhancement model, converting the first image frame from a first image format that lacks luminance data into a second image format that includes luminance data, by using the at least one processor (120), and after application of the visibility enhancement model to at least some of the luminance data, converting the second image frame from the second image format into the first image format or a third image format, by using the at least one processor (120).

[0127] According to an embodiment of the present disclosure, the method further comprises applying at least one transformation to the second image frame by using the at least one processor (120) in order to obtain a transformed image frame, and rendering the transformed image frame by using the at least one processor (120) for display on a display (160) of the electronic device (101).

[0128] According to an embodiment of the present disclosure, the visibility enhancement model comprises a specified one of multiple low-light visibility enhancement models, and the at least one processor (120) is further configured to select the specified low-light visibility enhancement model from among the multiple low-light visibility enhancement models based on the brightness of the first image frame.

[0129] According to an embodiment of the present disclosure, the predefined condition indicative of low-light comprises a condition in which the brightness of the first image frame is less than a threshold, the at least one processor (120) is further configured, based on the brightness-related metric indicating that the brightness of the first image frame is greater than or equal to the threshold, to refrain from applying the visibility enhancement model to the first image frame, wherein the visibility enhancement model comprises a low-light visibility enhancement model.

[0130] According to an embodiment of the present disclosure, the at least one processor (120) is further configured to train the low-light visibility enhancement model using the at least one dataset, and to train the low-light visibility enhancement model, the at least one processor (120) is configured, for each of the at least one imaging sensor (180), to identify parameters of a response model and a brightness transform model based on at least part of the at least one dataset, obtain an exposure ratio map for adjusting image contrast and visibility, integrate the brightness transform model and the exposure ratio map to obtain an integrated brightness transform model, and combine the integrated brightness transform model and the response model.

[0131] According to an embodiment of the present disclosure, the at least one processor (120) is further configured to, prior to application of the visibility enhancement model, convert the first image frame from a first image format that lacks luminance data into a second image format that includes luminance data; and after application of the visibility enhancement model to at least some of the luminance data, convert the second image frame from the second image format into the first image format or a third image format.

[0132] According to an embodiment of the present disclosure, the at least one processor (120) is further configured to apply at least one transformation to the second image frame in order to obtain a transformed image frame; and render the transformed image frame for display on a display (160) of the electronic device (101).

[0133] According to an embodiment of the present disclosure, the method further includes obtaining multiple exposure ratio maps, wherein each exposure ratio map is used to adjust image contrast and visibility of image frames captured using an associated one of the multiple imaging sensors included in the at least one imaging sensor 180.

[0134] According to an embodiment of the present disclosure, for each of the at least one imaging sensor 180, the parameters of the response model are based on one or more properties of the imaging sensor, and the parameters of the brightness transform model are based on the one or more properties of the imaging sensor and one or more exposure properties of the image frames captured using the imaging sensor.

[0135] According to an embodiment of the present disclosure, for each of the at least one imaging sensor 180, the exposure ratio map is integrated with the brightness transform model to generate an integrated brightness transform model, and the integrated brightness transform model and the response model are combined to generate the low-light visibility enhancement model for the imaging sensor.

[0136] According to an embodiment of the present disclosure, the method further comprises converting the image frames from a first image format that lacks luminance data into a second image format that includes luminance data, wherein, for each of the at least one imaging sensor, the parameters of at least one of the response model or the brightness transform model are identified using the luminance data of the image frames captured using the imaging sensor 180.

[0137] Although this disclosure has been described with example embodiments, various changes and modifications may be suggested to one skilled in the art. It is intended that this disclosure encompass such changes and modifications as fall within the scope of the appended claims.

Claims

1.A method for enhancing image visibility, the method comprising:obtaining, using at least one imaging sensor (180) of an electronic device (101), a first image frame of a scene;determining, using at least one processor (120) of the electronic device (101), a brightness-related metric indicative of a brightness of the first image frame; andbased on the brightness-related metric satisfying a predefined condition indicative of low-light, applying, using the at least one processor (120), a visibility enhancement model to the first image frame in order to obtain a second image frame having a higher brightness than the brightness of the first image frame;wherein a visibility enhancement model is trained using at least one dataset that includes image frames obtained using at least one imaging sensor.2.The method of Claim 1, wherein:the visibility enhancement model comprises a specified one of multiple low-light visibility enhancement models; andthe method further comprises selecting, using the at least one processor (120), the specified low-light visibility enhancement model from among the multiple low-light visibility enhancement models based on the brightness of the first image frame.3.The method of Claim 1 or 2, wherein the predefined condition indicative of low-light comprises a condition in which the brightness of the first image frame is less than a threshold, andthe method further comprises, based on the brightness-related metric indicating that the brightness of the first image frame is greater than or equal to the threshold, refraining, using the at least one processor (120), from applying the visibility enhancement model to the first image frame,wherein the visibility enhancement model comprises a low-light visibility enhancement model.4.The method of Claim 3, further comprising:training, using the at least one processor (120), the low-light visibility enhancement model using the at least one dataset;wherein the training the low-light visibility enhancement model comprises, for each of the at least one imaging sensor:identifying parameters of a response model and a brightness transform model based on at least part of the at least one dataset;obtaining an exposure ratio map for adjusting image contrast and visibility;integrating the brightness transform model and the exposure ratio map to obtain an integrated brightness transform model; andcombining the integrated brightness transform model and the response model.5.The method of any one of Claims 1 to 4, wherein the brightness-related metric comprises a low-light image score, wherein the low-light image score comprises a signal-to-noise ratio (SNR) and an image brightness value associated with the first image frame.6.The method of any one of Claims 1 to 5, further comprising:prior to the applying of the visibility enhancement model, converting, using the at least one processor (120), the first image frame from a first image format that lacks luminance data into a second image format that includes luminance data; andafter the applying of the visibility enhancement model to at least some of the luminance data, converting, using the at least one processor (120), the second image frame from the second image format into the first image format or a third image format.7.The method of any one of Claims 1 to 6, further comprising:applying at least one transformation to the second image frame by using the at least one processor (120) in order to obtain a transformed image frame; andrendering the transformed image frame by using the at least one processor (120) for display on a display (160) of the electronic device (101).8.An electronic device (101) comprising:at least one imaging sensor (180); andat least one processor (120) configured to:obtain a first image frame of a scene captured using the at least one imaging sensor;determine a brightness-related metric indicative of a brightness of the first image frame; andbased on the brightness-related metric satisfying a predefined condition indicative of low-light, apply a visibility enhancement model to the first image frame in order to obtain a second image frame having a higher brightness than the brightness of the first image frame;wherein a visibility enhancement model is trained using at least one dataset that includes image frames obtained using at least one imaging sensor.9.The electronic device (101) of Claim 8, wherein:the visibility enhancement model comprises a specified one of multiple low-light visibility enhancement models; andthe at least one processor (120) is further configured to select the specified low-light visibility enhancement model from among the multiple low-light visibility enhancement models based on the brightness of the first image frame.10.The electronic device (101) of Claim 8 or 9, wherein the predefined condition indicative of low-light comprises a condition in which the brightness of the first image frame is less than a threshold,the at least one processor (120) is further configured, based on the brightness-related metric indicating that the brightness of the first image frame is greater than or equal to the threshold, to refrain from applying the visibility enhancement model to the first image frame,wherein the visibility enhancement model comprises a low-light visibility enhancement model.11.The electronic device (101) of Claim 10, wherein:the at least one processor (120) is further configured to:train the low-light visibility enhancement model using the at least one dataset; andtrain the low-light visibility enhancement model, wherein the at least one processor (120) is further configured, for each of the at least one imaging sensor (180), to:identify parameters of a response model and a brightness transform model based on at least part of the at least one dataset;obtain an exposure ratio map for adjusting image contrast and visibility;integrate the brightness transform model and the exposure ratio map to obtain an integrated brightness transform model; andcombine the integrated brightness transform model and the response model.12.The electronic device (101) of any one of Claims 8 to 11, wherein the brightness-related metric comprises a low-light image score, wherein the low-light image score comprises a signal-to-noise ratio (SNR) and an image brightness value associated with the first image frame.13.The electronic device (101) of any one of Claims 8 to12, wherein the at least one processor (120) is further configured to:prior to application of the visibility enhancement model, convert the first image frame from a first image format that lacks luminance data into a second image format that includes luminance data; andafter application of the visibility enhancement model to at least some of the luminance data, convert the second image frame from the second image format into the first image format or a third image format.14.The electronic device (101) of any one of Claims 8 to 13, wherein the at least one processor (120) is further configured to:apply at least one transformation to the second image frame in order to obtain a transformed image frame; andrender the transformed image frame for display on a display (160) of the electronic device (101).15.A computer-readable storage medium storing instructions, wherein the instructions, when executed by at least one processor (120), cause the at least one processor (120) to perform the method according to any one of claims 1 to 7.

Images