Method and electronic device for multi-dimensional semantic contrast and color enhancement

Abstract

A method includes obtaining, using at least one processing device of an electronic device, an image frame. The method includes performing, using the at least one processing device, semantic segmentation of the image frame to generate semantic segmentation information for the image frame. The semantic segmentation information includes an indexed image representing at least a first semantic class and a second semantic class. The method includes performing, using the at least one processing device, multi-scale local tone mapping of the indexed image using a first weight corresponding to the first semantic class and a second weight corresponding to the second semantic class. The first weight adapts enhancement of the image frame differently from the second weight based on a difference between the first semantic class and the second semantic class.

Description

METHOD AND ELECTRONIC DEVICE FOR MULTI-DIMENSIONAL SEMANTIC CONTRAST AND COLOR ENHANCEMENT

[0001] This disclosure relates generally to image enhancement. More specifically, this disclosure relates to a method and an electronic device for multi-dimensional semantic contrast and color enhancement.

[0002] During image processing, contrast enhancement boosts pixel intensity differences to improve visibility, making details clearer. In general, optimal image contrast enhancement is difficult to perform in all areas of an image without introducing artifacts, such as stains (anomalous discolorations) or halos (bright or dark rims around edges). Oftentimes, different parts of a scene within an image have conflicting contrast enhancement requirements. Tone mapping is an image processing technique that can be used to compress an image's range of light (dynamic range), but tone mapping also often requires different or conflicting color processing for one part of an image scene (such as a face or sky) compared to other parts of the image scene.

[0003] This disclosure relates to multi-dimensional smart semantic contrast and color enhancement.

[0004] According to an aspect of the present disclosure, a method for multi-dimensional semantic contrast and color enhancement is provided. The method may comprise obtaining, using at least one processing device of an electronic device, an image frame. The method may comprise performing, using the at least one processing device, semantic segmentation of the image frame to generate semantic segmentation information for the image frame. The semantic segmentation information may comprise an indexed image representing at least a first semantic class and a second semantic class. The method may comprise performing, using the at least one processing device, multi-scale local tone mapping of the indexed image using a first weight corresponding to the first semantic class and a second weight corresponding to the second semantic class. The first weight may adapt enhancement of the image frame differently from the second weight based on a difference between the first semantic class and the second semantic class.

[0005] According to an aspect of the present disclosure, an electronic device for multi-dimensional semantic contrast and color enhancement is provided. The electronic device may comprise at least one processing device configured to obtain an image frame. The at least one processing device may be configured to perform semantic segmentation of the image frame to generate semantic segmentation information for the image frame. The semantic segmentation information may comprise an indexed image representing at least a first semantic class and a second semantic class. The at least one processing device may be configured to perform multi-scale local tone mapping of the indexed image using a first weight corresponding to the first semantic class and a second weight corresponding to the second semantic class. The first weight may adapt enhancement of the image frame differently from the second weight based on a difference between the first semantic class and the second semantic class.

[0006] According to an aspect of the present disclosure, provided is a computer-readable storage medium storing instructions that, when executed by at least one processing device individually or collectively, cause the at least one processing device of an electronic device to obtain an image frame and perform semantic segmentation of the image frame to generate semantic segmentation information for the image frame. The semantic segmentation information may comprise an indexed image representing at least a first semantic class and a second semantic class. The computer-readable storage medium may store instructions that, when executed, cause the at least one processor to perform multi-scale local tone mapping of the indexed image using a first weight corresponding to the first semantic class and a second weight corresponding to the second semantic class. The first weight may adapt enhancement of the image frame differently from the second weight based on a difference between the first semantic class and the second semantic class.

[0007] Other technical features may be readily apparent to one skilled in the art from the following figures, descriptions, and claims.

[0008] 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:

[0009] FIG. 1 illustrates an example of a network configuration that may be employed for multi-dimensional semantic contrast and color enhancement in accordance with an embodiment of the present disclosure;

[0010] FIG. 2 illustrates a method for multi-dimensional semantic contrast and color enhancement in accordance with an embodiment of the present disclosure;

[0011] FIG. 3 illustrates an example of a multi-frame image processing pipeline for multi-dimensional semantic contrast and color enhancement in accordance with an embodiment of the present disclosure;

[0012] FIG. 4 illustrates an example of a tone mapping operation, as shown in FIG. 3 in accordance with an embodiment of the present disclosure;

[0013] FIG. 5 illustrates an example of a multi-scale tone mapping (MSTM) function, as shown in FIG. 4 in accordance with an embodiment of the present disclosure;

[0014] FIG. 6A illustrates examples of an input luminance image and associated base and detail components derived by the MSTM function, as shown in FIG. 4 in accordance with an embodiment of the present disclosure;

[0015] FIG. 6B is an enlarged view of example first layer detail components, as shown in FIG. 6A in accordance with an embodiment of the present disclosure;

[0016] FIG. 6C is an enlarged view of example second layer detail components, as shown in FIG. 6A in accordance with an embodiment of the present disclosure;

[0017] FIG. 7 illustrates an example of semantic segmentation of pixels of an image, as shown in FIGS. 6A-6C in accordance with an embodiment of the present disclosure;

[0018] FIG. 8 illustrates an application of an example modulation function to the image, as shown in FIGS. 6A-6C in accordance with an embodiment of the present disclosure;

[0019] FIG. 9 illustrates an example graph of a sigmoid-similar function in accordance with an embodiment of the present disclosure;

[0020] FIG. 10 illustrates an example graph of a smooth step function to avoid noise amplification in accordance with an embodiment of the present disclosure;

[0021] FIG. 11 illustrates an application of an example modulation function shown in FIG. 10 to the image shown in FIGS. 6A-6C, in accordance with an embodiment of the present disclosure;

[0022] FIGS. 12A through 13B illustrate an application of example modulation functions to the image shown in FIGS. 6A-6C in accordance with an embodiment of the present disclosure;

[0023] FIG. 14 illustrates an example of a tone mapping operation, as shown in FIG. 3 in accordance with an embodiment of the present disclosure; and

[0024] FIG. 15 illustrates an example of semantic segmentation of pixels of the image shown in FIGS. 6A-6C analogous to FIG. 7 in accordance with an embodiment of the present disclosure.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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, a smart speaker or speaker with an integrated digital assistant, a gaming console, 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.

[0032] In the following description, electronic devices are described with reference to the accompanying drawings, according to various embodiments 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.

[0033] 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.

[0034] None of the description in this application should be read as implying that any particular element, step, operation, or function is an essential element that must be included in the claim scope. The scope of patented subject matter is defined only by the claims. Moreover, none of the claims is intended to limit the interpretation of any term beyond its ordinary and customary meaning as understood by those skilled in the art. Use of any term such as "mechanism," "module," "device," "unit," "component," "element," "member," "apparatus", "electronic device," "machine," "system," "processor," or "controller" is intended to refer to structural or functional components understood by those skilled in the relevant art, and is not intended to invoke any country-specific statutory construction rule requiring means-plus-function interpretation.

[0035] FIGS. 1 through 15, discussed below, and embodiments of this disclosure are described with reference to the accompanying drawings. However, it should be appreciated that this disclosure is not limited to these embodiments, and all changes and / or equivalents or replacements thereto also belong to the scope of this disclosure. The same or similar reference numerals may be used to refer to the same or similar elements throughout the specification and the drawings.

[0036] As noted above, during image processing, contrast enhancement boosts pixel intensity differences to improve visibility, making details clearer. In general, optimal image contrast enhancement is difficult to perform in all areas of an image without introducing artifacts, such as stains (anomalous discolorations) or halos (bright or dark rims around edges). Oftentimes, different parts of a scene within an image have conflicting contrast enhancement requirements. Tone mapping is an image processing technique that can be used to compress an image's range of light (dynamic range), but tone mapping also often requires different or conflicting color processing for one part of an image scene (such as a face or sky) compared to other parts of the image scene.

[0037] This disclosure may provide various techniques for multi-dimensional semantic contrast and color enhancement. As the contrast and color enhancement are adaptively controlled in a semantic-aware manner, the multi-dimensional semantic contrast and color enhancement may be referred to as multi-dimensional smart semantic contrast and color enhancement. As described in more detail below, an image frame may be obtained, and semantic segmentation of the image frame may be performed to generate semantic segmentation information for the image frame. The semantic segmentation information may comprise an indexed image representing at least a first semantic class and a second semantic class. Multi-scale local tone mapping of the indexed image may be performed using a first weight corresponding to the first semantic class and a second weight corresponding to the second semantic class. The first weight may adapt enhancement of the image frame differently from the second weight based on a difference between the first semantic class and the second semantic class.

[0038] In this way, the described techniques may be used to address shortcomings of typical tone mapping operations, such as the problem of conflicting image enhancement requirements in different parts of a scene within an image. As a result, an improved local tone mapping operation may be provided using semantic information. For example, smart semantic contrast enhancement as described here may utilize semantic information and multi-scale, filter bank-based decomposition. This may solve the problem of conflicting contrast enhancement requirements in different parts of a scene. With these approaches, for instance, contrast may be enhanced optimally in one part of an image without introducing stains, halos, or other artifacts in other parts. For example, smart semantic color processing may utilize semantic information to perform optimal color processing for each semantic class in a scene, such as when semantic segmentation allows changing of colors in each semantic region independently based on calibrated or tuned shifts. Thus, for example, color processing may be performed in red-green-blue (RGB); brightness (luma) and color (chroma blue and chroma red) (YUV); hue, saturation, and value (HSV); or other color spaces. Each semantic class may have its own hue shift or saturation boost values (which may be dependent on image metadata), which may be calibrated based on desirable colors in reference images and fine-tuned. With these approaches, colors of different semantic regions of an image may be enhanced independently without conflicting with other semantic regions.

[0039] FIG. 1 illustrates an example of a network configuration 100 that may be employed for multi-dimensional semantic contrast and color enhancement in accordance with an embodiment of the present disclosure. The embodiment of the network configuration 100 shown in FIG. 1 may be for illustration only. Other embodiments of the network configuration 100 may be used without departing from the scope of this disclosure.

[0040] According to an embodiment of this disclosure, an 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, or a sensor 180. In an embodiment, the electronic device 101 may exclude at least one of these components or may include one or more additional components. For example, the electronic device 101 may include the processor 120 and the memory 130. The processor 120 may correspond to at least one processing device. The memory 130 may correspond to at least one memory. The at least one memory may store instructions that, when executed by the at least one processing device, cause the at least one processing device to perform one or more of operations described herein. For example, the electronic device 101 may include the processor 120. The processor 120 may correspond to at least one processing device configured to perform one or more of operations described herein. 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.

[0041] The processor 120 may include at least one processing device, 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 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 in more detail below, the processor 120 may perform various operations related to multi-dimensional smart semantic contrast and color enhancement.

[0042] The memory 130 may include a volatile and / or non-volatile memory. For example, the memory 130 may store commands 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).

[0043] The kernel 141 may control or manage system resources (such as the bus 110, processor 120, or 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 may provide 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 support various functions related to multi-dimensional smart semantic contrast and color enhancement. 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 may be 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 includes at least one interface or function (such as a command) for filing control, window control, image processing, or text control.

[0044] The I / O interface 150 may serve as an interface that can, 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 (e.g., a first electronic device 102, a second electronic device 104, and / or a server 106).

[0045] 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 can 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.

[0046] The communication interface 170, for example, may be able to set up communication between the electronic device 101 and the external electronic device (such as the first electronic device 102, the second electronic device 104, or the 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.

[0047] The wireless communication may be able to use at least one of, for example, Wi-Fi, 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 includes 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.

[0048] The electronic device 101 may further include one or more sensor(s) 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, one or more sensor(s) 180 may include one or more cameras or other imaging sensors for capturing images of scenes. The sensor(s) 180 may also include one or more buttons for touch input, one or more microphones, 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 an 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 further include an inertial measurement unit, which 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.

[0049] In an embodiment, the first external electronic device 102 or the second external electronic device 104 may be a wearable device or an electronic device-mountable wearable device (such as a head mounted display (or "HMD")). When the electronic device 101 is mounted in the first 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 first electronic device 102 to communicate with the first electronic device 102 without involving a separate network. The electronic device 101 may be an extended reality (XR) device, which includes a virtual reality (VR) headset or an augmented reality (AR) wearable device, such as eyeglasses that include one or more imaging sensors.

[0050] The first electronic device 102, the second electronic device 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 disclosure, the server 106 may include a group of one or more servers. According to an embodiment of this 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 may include the communication interface 170 to communicate with the second 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.

[0051] The server 106 may include the same or similar components 110-180 as the electronic device 101 (or a suitable subset thereof). The server 106 may support the electronic device 101 by performing at least one of the 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 in more detail below, the server 106 may perform various operations related to multi-dimensional semantic contrast and color enhancement.

[0052] Although FIG. 1 illustrates one example of a network configuration 100 that may be employed for multi-dimensional semantic contrast and color enhancement, 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 disclosed in this patent document may be used, these features may be used in any other suitable system. The electronic device 101 may be configured to perform the operations in the flowcharts illustrated in FIG. 2.

[0053] For example, the electronic device 101 may comprise at least one processing device 120. The at least one processing device (120) may be configured to obtain an image frame; perform semantic segmentation of the image frame to generate semantic segmentation information for the image frame, the semantic segmentation information including an indexed image representing at least a first semantic class and a second semantic class; and perform multi-scale local tone mapping of the indexed image using a first weight corresponding to the first semantic class and a second weight corresponding to the second semantic class. The first weight adapts enhancement of the image frame differently from the second weight based on a difference between the first semantic class and the second semantic class.

[0054] For example, to perform the semantic segmentation, the at least one processing device (120) may be configured to divide an input luminance image corresponding to the image frame into multiple semantic classes including at least the first semantic class and the second semantic class; apply a first bank of guided filters to the input luminance image to generate first base components and first detail components; and apply a second bank of guided filters to the first base components to generate second base components and second detail components. The at least one processing device (120) may be configured to enhance the image frame based on both the first weight corresponding to the first semantic class and the second weight corresponding to the second semantic class to adjust the first detail components and the second detail components.

[0055] For example, to enhance the image frame, the at least one processing device (120) may be configured to increase or decrease contributions of the first detail components and the second detail components to an enhanced image based on the first semantic class and the second semantic class.

[0056] For example, the at least one processing device (120) may be configured to generate the enhanced image based on Equation (1) described below with reference to FIG. 5.

[0057] For example, the at least one processing device (120) may be configured to enhance sharpness and contrast for the first detail components and the second detail components based on the first semantic class and the second semantic class.

[0058] For example, the at least one processing device (120) may be configured to enhance the first detail components by providing detail enhancement and noise suppression; and the at least one processing device (120) may be configured to enhance the second detail components by providing detail enhancement and bright area negative detail enhancement.

[0059] For example, the at least one processing device (120) may be configured to perform semantic segmentation by dividing the image frame into multiple semantic classes including at least the first semantic class and the second semantic class; applying first color processing to portions of the image frame corresponding to the first semantic class; and applying second color processing to portions of the image frame corresponding to the second semantic class. Color enhancement of the image frame may be performed independently for colors of different semantic regions.

[0060] FIG. 2 illustrates a method 200 for multi-dimensional semantic contrast and color enhancement in accordance with an embodiment of the present disclosure. For ease of explanation, the method 200 of FIG. 2 is described as being performed using the electronic device 101 in the network configuration 100 of FIG. 1. However, the method 200 may be performed using any other suitable device(s) (such as the server 106) and in any other suitable system(s). The method 200 may also be referred to as a process since the method 200 is executed through a series of operations.

[0061] As shown in FIG. 2, the method 200 may include obtaining an image frame (operation 201). In some cases, the image frame may be derived using multiple image frames captured by one or more cameras on the electronic device 101, such as one or more imaging sensors 180 of the electronic device 101. For example, the image frame may be generated by performing image fusion during high dynamic range (HDR) generation, multi-focus fusion, or other image processing operation.

[0062] Semantic segmentation of the image frame may be performed to generate semantic segmentation information for the image frame (operation 202). The semantic segmentation information may include an indexed image representing at least a first semantic class and a second semantic class. In some cases, the semantic segmentation may involve the processor 120 of the electronic device 101 dividing an input luminance image corresponding to the image frame into multiple semantic classes including at least the first semantic class and the second semantic class. For example, during the semantic segmentation, a first bank of guided filters may be applied to an input luminance image to generate first base components and first detail components, and a second bank of guided filters may be applied to the first base components to generate second base components and second detail components.

[0063] Multi-scale local tone mapping of the indexed image may be performed using a first weight corresponding to the first semantic class and a second weight corresponding to the second semantic class (operation 203). The first weight may adapt enhancement of the image frame differently from the second weight based on a difference between the first semantic class and the second semantic class. For example, enhancement of the image frame may employ both the first weight corresponding to the first semantic class and the second weight corresponding to the second semantic class to adjust the first detail components and the second detail components. For example, the enhancement of the first detail components and the second detail components may employ a modulation function that maps each of the first semantic class and the second semantic class to a corresponding modulation strength and a function processing positive details and negative details symmetrically in order to boost or suppress details based on distance from a specified value.

[0064] Although FIG. 2 illustrates one example of the method 200 for multi-dimensional semantic contrast and color enhancement, various changes may be made to FIG. 2. For example, while shown as a series of operations, various steps in FIG. 2 may overlap, occur in parallel, occur in a different order, or occur any number of times (including zero times). Accordingly, according to the present disclosure, it is possible to individually control degrees of contrast enhancement and color enhancement for different semantic classes within an image, thereby enabling image correction suitable for visual characteristics of respective regions. As a result, it is possible to minimize occurrence of artifacts that may arise from an existing uniform tone mapping scheme, while simultaneously improving object-wise and region-wise visual clarity and naturalness.

[0065] FIG. 3 illustrates an example of multi-frame image processing pipeline 300 for multi-dimensional smart semantic contrast and color enhancement in accordance with an embodiment of the present disclosure. For ease of explanation, the pipeline 300 of FIG. 3 may be described as being implemented using the electronic device 101 in the network configuration 100 of FIG. 1, which may implement the method 200 of FIG. 2. However, the pipeline 300 may be implemented within any other suitable device(s) (such as the server 106) and in any other suitable system(s), and the pipeline 300 may be used to implement any other suitable process(es).

[0066] As shown in FIG. 3, the pipeline 300 receives multiple input image frames 301 to be processed, such as image frames captured using the imaging sensor(s) 180 of the electronic device 101. The pipeline 300 may perform one or more image processing operations on the image frames 301, such as a registration and blending operation 302 in which the image frames 301 may be aligned with one another and pixel data from the image frames 301 may be combined in some manner during blending. The output of the registration and blending operation 302 may be processed using a demosaicing operation 303 in which a full color image may be reconstructed and a denoising operation 304 to improve clarity, quality, and detail.

[0067] At the end of the pipeline 300, a tone mapping operation 305 may be performed as described in further detail below to generate a final output image 306. The tone mapping operation 305 may compress a higher dynamic range to a smaller dynamic range, thus yielding a low dynamic range (LDR) final output image 306 that may be suitable for viewing on displays (such as the display 160 of the electronic device 101) and / or print media. For example, the tone mapping operation 305 may be useful because the result of prior operations in the pipeline 330 may include HDR image data having unnatural tones. While local and global tone mapping operations in the tone mapping operation 305 may be adjusted to enhance contrast in the final output image 306, contrast enhancement performed during tone mapping may frequently cause stains, halos, and other artifacts. The techniques described below help to reduce or eliminate these artifacts.

[0068] Although FIG. 3 illustrates one example of the pipeline 300 for multi-frame image processing using multi-dimensional semantic contrast and color enhancement in accordance with this disclosure, various changes may be made to FIG. 3. For example, various components or functions in FIG. 3 may be combined, further subdivided, replicated, omitted, or rearranged and additional components or functions may be added according to particular needs. Also, while shown as a series of operations, image processing may be performed at least partially in parallel, or portions of the image processing may be performed in an integrated fashion.

[0069] FIG. 4 illustrates an example of the tone mapping operation 305, as shown in FIG. 3 in accordance with an embodiment of the present disclosure. For ease of explanation, the tone mapping operation 305 in FIG. 4 may be described as being implemented using the pipeline 300 of FIG. 3 and performed by the processor 120 of the electronic device 101 in the network configuration 100 of FIG. 1. However, the tone mapping operation 305 may be implemented within any other suitable pipeline(s) or device(s).

[0070] As shown in FIG. 4, the tone mapping operation 305 receives a tone map input 401 and performs a series of functions. For example, the tone map input 401 may represent an output of the denoising operation 304 in the pipeline 300 of FIG. 3 or any other suitable image process. Here, the tone map input 401 may be passed to a dynamic scales function 402, which may be implemented using an array of image signal processors 403-405 as shown in FIG. 4. Each of the image signal processors 403-405 may operate using a global tone map (GTM) to provide overall tonal control, a color correction matrix (CCM) to adjust colors to a standard color space, and gamma correction to adjust image brightness (such as midtones) to compensate for non-linear responses of a display device. In an embodiment, the image signal processors 403-405 may respectively correspond to different dynamic scales within the Dynamic Scales block 402, while having substantially the same processing structure including the GTM, the CCM, and the gamma correction.

[0071] An exposure fusion function 406 may receive the outputs of the image signal processors 403-405 and fuse multiple exposures, such as to provide dynamic range compression. A preferential color correction (PCC) function 407 may apply one or more look-up tables (LUTs) to hues and saturation values, such as to shift colors in a desired direction. Each of the dynamic scales function 402, exposure fusion function 406, and PCC function 407 may use any of well-known processes or later-developed processes to perform their respective functions.

[0072] The tone mapping operation 305 shown in FIG. 4 may include a segmentation-based image contrast enhancement function 408, which processes a segmented version of an input image frame 409 provided by a semantic segmentation function 410. The input image frame 409 may correspond to raw image data, RGB image data, processed image data, unprocessed image data, or other suitable image data. Any of a variety of semantic segmentation techniques may be employed by the semantic segmentation function 410, such as "Segment Anything," YOLOv8, and the like. In an embodiment, the semantic segmentation function 410 may classify each pixel in the input image frame 409 into one of a number of predefined categories, such as "sky," "face," etc., attaching an associated semantic class.

[0073] The semantic classes 411 output by the semantic segmentation function 410 may be employed by a local multi-scale tone map (MSTM) function 412 of the image contrast enhancement function 408. The MSTM function 412 may perform tone mapping on an RGB input image 413 (such as RGB or other image data) that is output from the PCC function 407. A specific example implementation of the MSTM function 412 is described below in connection with FIG. 5.

[0074] The segmentation-based image contrast enhancement function 408 may perform a smart semantic-based contrast enhancement that utilizes semantic information and multi-scale filter bank-based or other decomposition. This approach may solve problems related to conflicting contrast enhancement requirements in different parts of a scene. Example benefits may include allowing contrast to be enhanced differently (such as optimally) in one part of an image frame without introducing artifacts (such as stains, halos, etc.) in other parts of the image frame. The output of the MSTM function 412 may represent the final output image 306 of the pipeline 300 in FIG. 3.

[0075] Although FIG. 4 illustrates one example of the tone mapping operation 305 in FIG. 3, various changes may be made to FIG. 4. For example, various components or functions in FIG. 4 may be combined, further subdivided, replicated, omitted, or rearranged and additional components or functions may be added according to particular needs. Also, any suitable number of image signal processors may operate in parallel on a tone map input, such as when each operates on a different region of the tone map input or each operates on a different logical portion (such as color) of the tone map input.

[0076] FIG. 5 illustrates an example of a MSTM function 412, as shown in FIG. 4 in accordance with an embodiment of the present disclosure. For ease of explanation, the MSTM function 412 of FIG. 5 is described as being implemented as part of the tone mapping operation 305 within the pipeline 300 of FIG. 3, which may be implemented using the processor 120 of the electronic device 101 in the network configuration 100 of FIG. 1. However, the MSTM function 412 may be implemented within any other suitable operation(s), pipeline(s), device(s), or system(s).

[0077] As shown in FIG. 5, the MSTM function 412 may represent a local tone mapping operation that uses multi-dimensional decomposition based on filter banks and semantic segmentation. In this example, a converter function 501 converts (if necessary) the RGB input image 413 to another image format, such as the YUV format, to obtain an input luminance image . The semantic segmentation function 410 may be employed to divide the input luminance image into multiple class instances of semantic classes 411.

[0078] A first guided filter bank 502 (GF1) and a second guided filter bank 503 (GF2) may be used to generate different hierarchical components. For example, the guided filter bank 502 may generate base components from the input luminance image , and the guided filter bank 503 may generate base components from the base components . The input luminance image and the base components generated by the guided filter bank 502 may be used to generate detail components as . The base components generated by the guided filter bank 502 and the base components generated by the guided filter bank 503 may be used to generate detail components .

[0079] A detail enhancement boost function 504 and a noise suppression function 505 may use semantic segmentation information from the semantic segmentation function 410 to enhance sharpness and contrast of the detail components . Similarly, a detail enhancement boost function 506 and a bright area boost function 507 may use semantic segmentation information from the semantic segmentation function 410 to enhance sharpness and contrast of the detail components . In some cases, the functions 504-507 may include adjustments of sharpness and contrast strength settings for each of the semantic classes 411, base components and , and detail components and . Contrast and sharpness enhancement for each component may be based on these sharpness and contrast strength settings, producing enhanced detail components and .

[0080] An image synthesizer function 508 may determine a weighted sum of the base components and and the enhanced detail components and . In some cases, weights used to calculate the weighted sum may be a function of the semantic classes 411 within the semantic segmentation map and may be selected to increase / decrease the contributions of the enhanced detail components and based on the semantic classes 411 to produce a final output image 306. In an embodiment, the final output image( ) 306 may be defined as in Equation (1).

[0081]

[0082] Here, indicates pointwise multiplication, and represents the enhanced image generated according to Equation (1). represents the second base components, represents the first detail components enhanced based on the first semantic class and the second semantic class, and represents the second detail components enhanced based on the first semantic class and the second semantic class. represents an indexed image 411 identifying different semantic classes, and represents a first weight corresponding to the first detail components and represents a second weight corresponding to the second detail components, where and may be functions of the semantic classes identified by the indexed image . For example, "sky" and "grass" semantic classes may have higher weights, whereas a "face" semantic class may have a lower weight, which can be done to maximize contrast for "sky" and "grass" image content and keep contrast lower for "face" image content. Accordingly, Equation (1) may define a semantic-aware image synthesis operation in which base components and enhanced detail components are combined using semantic-dependent weights to generate the enhanced image.

[0083] With respect to the guided filter bank 502 and the guided filter bank 503, each guided filter may represent an edge-preserving filter that may filter out noise and details in an input image while preserving strong edges in the image. Any suitable guided filter operation can be used here. In this disclosure, may be used to represent a guided filtering operation, where and are parameters that decide the filter size and blur degree of the guided filter, is a guide image, and is an input image to the guided filter. Decomposition may include a coarse and low-pass version of an image ( in FIG. 5), along with a sequence of difference images capturing details at progressively finer scales ( , in FIG. 5).

[0084] As an example of how the guided filter bank 502 or the guided filter bank 503 may operate, assume that is an input luminance image. Let denote progressively coarser versions of the input luminance image generated by guided filter operation , which may be defined in Equation (2). Accordingly, Equation (2) may define a guided filtering operation that generates progressively coarser base components from the input luminance image, thereby forming a multi-scale base representation for subsequent detail extraction.

[0085]

[0086] With the coarsest base components serving as the base layer, the detail layers could be defined as in Equation (3).

[0087]

[0088] In the specific implementation in FIG. 5, . Example values of other parameters may include and . Increasing and may result in a detail component that has more high-frequency details and thus more detail enhancement. Increasing and may result in a detail component that has more high-frequency details and thus more detail / contrast enhancement. To obtain more contrast enhancement, and can be increased. In particular embodiments, a good choice for sharpening and contrast enhancement in typical images may be to make and . Accordingly, Equation (3) may define a multi-scale decomposition in which detail components at different scales are extracted as differences between successive base components, thereby enabling scale-dependent detail and contrast enhancement.

[0089] For example, the detail components may capture finer details and noise, thus providing the ability to suppress noise amplification in this layer. Also, for example, the detail components may include larger-scale details (such as local tone information), which may be suitable for contrast enhancement.

[0090] Although FIG. 5 illustrates one example of the MSTM function 412 in FIG. 4, various changes may be made to FIG. 5. For example, various components or functions in FIG. 5 may be combined, further subdivided, replicated, omitted, or rearranged and additional components or functions may be added according to particular needs. Also, while FIG. 5 includes two guided filter banks, any number of guided filters may be used, and the description here provides generalizations that contemplate the use of any number of guided filters to perform multi-dimensional decomposition.

[0091] FIG. 6A illustrates examples of an input luminance image and associated base and detail components - , - derived by the MSTM function 412, as shown in FIG. 4 in accordance with an embodiment of the present disclosure. In particular, the input luminance image is decomposed into a first base component and a first detail component at a first scale, and the first base component is further decomposed into a second base component and a second detail component at a second scale, such that may be represented as a combination of the base and detail components across multiple scales. FIG. 6B is an enlarged view of example first layer detail components in FIG. 6A in accordance with an embodiment of the present disclosure, and FIG. 6C is an enlarged view of example second layer detail components in FIG. 6A in accordance with an embodiment of the present disclosure.

[0092] Referring back to FIG. 5, the detail enhancement boost functions 504 and 506 may use semantic segmentation information to enhance sharpness and contrast of respective component images (first layer detail components and second layer detail components ). In some embodiments, the detail enhancement boost functions 504 and 506 may modify fine-scale details using a sigmoid-similar function, which may be expressed in Equation (4).

[0093]

[0094] Here, represents the indexed image 411 identifying different semantic classes 411, is a modulation function that maps each of the semantic classes 411 to a corresponding modulation strength , and is a function that symmetrically processes positive and negative details (such as by boosting details around zero and suppressing details close to one). In particular embodiments, the modulation function can be arbitrary and can be tuned to meet visual or image quality requirements. Accordingly, Equation (4) may define a semantic-aware non-linear detail enhancement function for the first detail components , in which the enhancement strength is adaptively controlled based on semantic classes identified by the indexed image .

[0095] As shown in FIGS. 6A-6C, an input luminance image captures a scene including a person (whose face is obscured for privacy). The input luminance image may be used to generate a base layer and a detail layer . The base layer may be used to generate a base layer and a detail layer . Additional decompositions may be possible to generate additional base layers and detail layers.

[0096] FIG. 7 illustrates an example of semantic segmentation of pixels of an image, as shown in FIGS. 6A-6C in accordance with an embodiment of the present disclosure. As can be seen here, the semantic segmentation may divide the image into multiple semantic classes 411, such as person, sky, foliage, building / construction structure, and background. Note that the specific semantic classes 411 shown here are examples only and may vary depending on the implementation. As illustrated in FIGS. 7 and 8, the semantic segmentation map identifying the semantic classes may be used as an input to the modulation function to assign different modulation strengths to different semantic classes. FIG. 8 illustrates an application of an example modulation function to the image, as shown in FIGS. 6A-6C in accordance with an embodiment of the present disclosure. The modulation strength for different semantic classes 411 is shown on the right in FIG. 8.

[0097] FIG. 9 illustrates an example graph 900 of a sigmoid-similar function in accordance with an embodiment of the present disclosure. The sigmoid-similar function (denoted in Equation (4)) can be defined as a plot of enhanced details as a function of image details. In the graph 900, a curve 901 represents a straight line with a slope of one, while a curve 902 represents the sigmoid-similar function. In some cases, the sigmoid-similar function may be defined as in Equation (5).

[0098]

[0099] A curve 903 illustrates that an amplitude of the sigmoid-similar function may be made larger or smaller by making larger or smaller. Accordingly, Equation (5) may provide an example implementation of the sigmoid-similar function used in Equation (4), in which the non-linearity and enhancement strength are controlled by the parameter .

[0100] FIG. 10 illustrates an example graph 1000 of a smooth step function to avoid noise amplification in accordance with an embodiment of the present disclosure. One characteristic of using a sigmoid-similar function is that other functions could make noise and artifacts more visible. This issue can be mitigated by limiting the smallest details that are amplified, for example, by using a sigmoid-similar function defined in Equation (6).

[0101]

[0102] Here, is a smooth step function equal to zero if is less than a first threshold and equal to one if is more than a second threshold , where a smooth linear transition is between the two. A modulation function may map each of the semantic classes 411 to a modulation strength for . With reference to FIG. 5, may represent the input to the detail enhancement boost function 504, may represent the output of the detail enhancement boost function 504 and the input to the noise suppression function 505, and may represent the output of the noise suppression function 505. One particular example expression for a smooth step function may be defined as in Equation (7).

[0103]

[0104] In particular embodiments, example values of the parameters may include , , and . For example, these parameters may be chosen so that , with the understanding that a larger results in less noise enhancement. One example smooth step function to avoid noise amplification is shown in FIG. 10, with and . FIG. 11 illustrates application of an example modulation function in FIG. 10 to the image in FIGS. 6A-6C in accordance with this disclosure. Again, modulation strength for different semantic classes 411 are shown on the right in FIG. 11.

[0105] Referring back to FIG. 5, in an embodiment, contrast and local tone of an image may be enhanced by manipulating the layer of detail components . In some cases, the detail components could include large-scale edges and some flat regions. Contrast and local tone enhancement of the detail components could occur using a similar function , which could be expressed as in Equation (8).

[0106]

[0107] Here, represents the indexed image 411 identifying different sematic classes, is a modulation function that maps each of the semantic classes to a corresponding modulation strength , and is a function that symmetrically processes positive and negative details (such as by boosting details around zero and suppressing details close to one). For example, the function may represent a sigmoid-similar function. With reference to FIG. 5, may represent the input to the detail enhancement boost function 506, may represent the output of the detail enhancement boost function 506 and the input to the bright area boost function 507, and may represent the output of the bright area boost function 507. In an embodiment, the modulation function may be arbitrary and can be tuned to meet visual or image quality requirements.

[0108] In this example, the parameter may control the contrast level. If is too small, the entire image may look flat. If is too large, the entire image may be over-contrasted, and halo artifacts may be more severe. Often times, bright areas within an image may suffer from low contrast issues giving a hazy appearance more than darker areas, so the bright area boost function 507 may be used to increase the contrast of bright areas. As boosting the positive details of bright areas may lead to a loss of saturation details, only negative details in the base components may be enhanced. In some cases, a bright area may be identified as in Equations (9) and (10).

[0109]

[0110]

[0111] In an embodiment, an example parameter selection may be , , and .

[0112] FIGS. 12A through 13B illustrate an application of example modulation functions to the image shown in FIGS. 6A-6C in accordance with an embodiment of the present disclosure. More specifically, FIG. 12A illustrates the detail component , and FIG. 12B illustrates the enhanced detail components . Similarly, FIG. 13A illustrates the detail component , and FIG. 13B illustrates the enhanced detail components .

[0113] Although FIGS. 6A-6C through 13B illustrate examples of images and processing results, various changes may be made to FIGS. 6A-6C through 13B. For example, the specific images being processed can vary widely based on the circumstances. Also, the specific processing results shown here are examples only and are merely meant to illustrate how various operations or functions may be performed.

[0114] FIG. 14 illustrates an example of a tone mapping operation 305, as shown in FIG. 3 in accordance with an embodiment of the present disclosure. For ease of explanation, the tone mapping operation 305 in FIG. 14 is described as being implemented using the pipeline 300 of FIG. 3 and performed by the processor 120 of the electronic device 101 in the network configuration 100 of FIG. 1. However, the tone mapping operation 305 may be implemented within any other suitable pipeline(s) or device(s).

[0115] The tone mapping operation 305 of FIG. 14 is similar to the tone mapping operation 305 of FIG. 4. However, in FIG. 14, a segmentation-based image contrast enhancement function 1408 may include both a dynamic scales function 1402 and a PCC function 1407 that operate based on semantic classes. Here, the dynamic scales function 1402 may include image signal processors 1403-1405. The image signal processors 1403-1405 and the PCC function 1407 may operate utilizing semantic information to perform optimal color processing for each semantic class in a scene. For instance, semantic segmentation may be used to support a color correction matrix used by the image signal processors 1403-1405 and the PCC function 1407 to change colors in each semantic region independently based on calibrated or tuned shifts.

[0116] As shown in FIG. 4, color processing in FIG. 14 may be performed in the RGB, YUV, HSV, or other color spaces. However, in FIG. 14, each semantic class 411 may have its own hue shift or saturation boost values (which could be dependent on image metadata), which may be calibrated based on desirable colors in reference images and fine-tuned. One benefit of this approach is that the colors of different semantic regions of an image may be enhanced independently without conflicting with other semantic regions.

[0117] For example, tone mapping in FIG. 14 may be performed using semantic segmentation to change the color of each semantic region independently. For example, assume the following. A hue look-up table (LUT) is a look-up table that transforms points in hue, saturation coordinates to new hue values for a semantic class . A saturation look-up table is a look-up table that transforms points in hue, saturation coordinates to new saturation values for a semantic class . For processing in the HSV color space, hue / saturation may be obtained directly. For processing in the YUV color space, approximate hue may be obtained by , and approximate saturation may be obtained by , where U and V are the YUV chroma values. For processing in other color spaces, similar approximate hue / saturation may be obtained.

[0118] Based on the above, given an image the following may be performed by the PCC function 1407. Hue / saturation values and may be determined for each pixel location , and the segmentation map may be determined. For each pixel location , transformed hue / saturation values and may be calculated, and transformed hue / saturation values may be combined with original luminance values to generate a final image. Further, to obtain a smooth transition in color appearance between pixels that fall across the boundary of different semantic classes, interpolation or other techniques may be used.

[0119] Note that hue / saturation adjustments using one or more LUTs may add extra computational overhead. In an embodiment, semantic color processing with minimal extra computational overhead may be achieved, such as by modulating the application of the CCM using the semantic segmentation. Accordingly, in FIG. 14, for CCM by the image signal processors 1403-1405, the following may be introduced. Hue CCM matrices may each represent a 3Х3 or other CCM for semantic class . Based on the above, given an image , the following may be performed by each of the image signal processors 1403-1405. A segmentation map may be determined, and a CCM operation may be performed for each pixel location . Further, to obtain a smooth transition in color appearance between pixels that fall across the boundary of different semantic classes, interpolation or other techniques may be used.

[0120] Although FIG. 14 illustrates an example of the tone mapping operation 305 shown in FIG. 3, various changes may be made to FIG. 14. For example, various components or functions in FIG. 14 may be combined, further subdivided, replicated, omitted, or rearranged and additional components or functions may be added according to particular needs. Also, any suitable number of image signal processors may operate in parallel on a tone map input, such as when each operates on a different region of the tone map input or each operates on a different logical portion (such as color) of the tone map input.

[0121] FIG. 15 illustrates an example of semantic segmentation of pixels of the image in FIGS. 6A-6C analogous to FIG. 7 in accordance with an embodiment of the present disclosure. Here, class labels zero through four may be used to denote different semantic classes 411. For segmentation-based CCM and PCC as shown in FIG. 14, Table 1 may be used based on the segmentation map.

[0122] [Table 1]

[0123]

[0124] In other words, there may be different PCC tables and / or different CCM matrices for different semantic classes 411.

[0125] In an embodiment, operations within the tone mapping operation 305 of FIG. 14 may occur in the following manner. For segmentation-based CCM without interpolation, the following may be performed:

[0126]

[0127] For segmentation-based PCC without interpolation, the following may be performed:

[0128]

[0129] For segmentation-based PCC with interpolation, using the first two columns of the Table 1 above, the following may be performed:

[0130]

[0131] Semantic control of contrast can provide improved results, such as better background contrast or reduced face stains, relative to traditional contrast enhancement. Semantic control of color enhancement may also provide improved results, such as reduced occurrences of issues like reddishness of facial features, while retaining other aspects of enhanced color.

[0132] Although FIG. 15 illustrates one example of a semantic segmentation of pixels of the image in FIGS. 6A-6C analogous to FIG. 7, various changes may be made to FIG. 15. For example, the specific semantic segmentation of pixels may easily vary depending on the images being processed. Also, each image could have any suitable number of semantic classes. In addition, any suitable identifiers may be used to differentiate semantic classes.

[0133] According to an embodiment of the present disclosure, the method 200 comprises obtaining, using at least one processing device of an electronic device, an image frame; performing, using the at least one processing device, semantic segmentation of the image frame to generate semantic segmentation information for the image frame, the semantic segmentation information including an indexed image representing at least a first semantic class and a second semantic class; and performing, using the at least one processing device, multi-scale local tone mapping of the indexed image using a first weight corresponding to the first semantic class and a second weight corresponding to the second semantic class; wherein the first weight adapts enhancement of the image frame differently from the second weight based on a difference between the first semantic class and the second semantic class.

[0134] According to an embodiment of the present disclosure, the performing the semantic segmentation comprises dividing an input luminance image corresponding to the image frame into multiple semantic classes including at least the first semantic class and the second semantic class; applying a first bank of guided filters to the input luminance image to generate first base components and first detail components; and applying a second bank of guided filters to the first base components to generate second base components and second detail components; wherein enhancement of the image frame is performed by employing both the first weight corresponding to the first semantic class and the second weight corresponding to the second semantic class to adjust the first detail components and the second detail components.

[0135] According to an embodiment of the present disclosure, the enhancement of the image frame comprises one of increasing or decreasing contributions of the first detail components and the second detail components to an enhanced image based on the first semantic class and the second semantic class.

[0136] According to an embodiment of the present disclosure, the enhanced image is determined based on Equation (1).

[0137] According to an embodiment of the present disclosure, the sharpness and contrast are enhanced for the first detail components and the second detail components based on the first semantic class and the second semantic class.

[0138] According to an embodiment of the present disclosure, the method 200 may include enhancement of the first detail components comprises detail enhancement and noise suppression; and enhancement of the second detail components comprises detail enhancement and bright area negative detail enhancement.

[0139] According to an embodiment of the present disclosure, the enhancement of the first detail components and the second detail components employs a modulation function that maps each of the first semantic class and the second semantic class to a corresponding modulation strength and a function processing positive details and negative details symmetrically in order to boost or suppress details based on distance from a specified value.

[0140] According to an embodiment of the present disclosure, the modulation function maps each of the first semantic class and the second semantic class to a modulation strength applied to the first detail components, where represents the indexed image as indexed based on the first semantic class and the second semantic class.

[0141] According to an embodiment of the present disclosure, the modulation function maps each of the first semantic class and the second semantic class to a modulation strength applied to the second detail components, where represents the indexed image as indexed based on the first semantic class and the second semantic class.

[0142] According to an embodiment of the present disclosure, the modulation function maps each of the first semantic class and the second semantic class to a modulation strength applied to the first detail components as a smooth step function with first and second thresholds, where represents the indexed image as indexed based on the first semantic class and the second semantic class.

[0143] According to an embodiment of the present disclosure, the performing the semantic segmentation comprises dividing the image frame into multiple semantic classes including at least the first semantic class and the second semantic class; applying first color processing to portions of the image frame corresponding to the first semantic class; and applying second color processing to portions of the image frame corresponding to the second semantic class; wherein color enhancement of the image frame is performed independently for colors of different semantic regions.

[0144] According to an embodiment of the present disclosure, the first color processing is associated with first hue shift or saturation boost values; and the second color processing is associated with second hue shift or saturation boost values.

[0145] According to an embodiment of the present disclosure, the multiple semantic classes include semantic classes in addition to the first semantic class and the second semantic class.

[0146] According to an embodiment of the present disclosure, an electronic device 101 may comprise at least one processing device 120 configured to obtain an image frame; perform semantic segmentation of the image frame to generate semantic segmentation information for the image frame, the semantic segmentation information including an indexed image representing at least a first semantic class and a second semantic class; and perform multi-scale local tone mapping of the indexed image using a first weight corresponding to the first semantic class and a second weight corresponding to the second semantic class; wherein the first weight adapts enhancement of the image frame differently from the second weight based on a difference between the first semantic class and the second semantic class.

[0147] According to an embodiment of the present disclosure, to perform the semantic segmentation, the at least one processing device 120 may be configured to divide an input luminance image corresponding to the image frame into multiple semantic classes including at least the first semantic class and the second semantic class; apply a first bank of guided filters to the input luminance image to generate first base components and first detail components; and apply a second bank of guided filters to the first base components to generate second base components and second detail components; wherein the at least one processing device 120 is configured to enhance the image frame based on both the first weight corresponding to the first semantic class and the second weight corresponding to the second semantic class to adjust the first detail components and the second detail components.

[0148] According to an embodiment of the present disclosure, to enhance the image frame, the at least one processing device 120 may be configured to increase or decrease contributions of the first detail components and the second detail components to an enhanced image based on the first semantic class and the second semantic class.

[0149] According to an embodiment of the present disclosure, the at least one processing device 120 may be configured to generate the enhanced image based on Equation (1).

[0150] According to an embodiment of the present disclosure, the at least one processing device 120 may be configured to enhance sharpness and contrast for the first detail components and the second detail components based on the first semantic class and the second semantic class.

[0151] According to an embodiment of the present disclosure, the at least one processing device may be configured to enhance the first detail components by providing detail enhancement and noise suppression; and the at least one processing device 120 may be configured to enhance the second detail components by providing detail enhancement and bright area negative detail enhancement.

[0152] According to an embodiment of the present disclosure, a computer-readable storage medium stores instructions that, when executed, cause at least one processor 120 of an electronic device 101 to obtain an image frame; perform semantic segmentation of the image frame to generate semantic segmentation information for the image frame, the semantic segmentation information including an indexed image representing at least a first semantic class and a second semantic class; and perform multi-scale local tone mapping of the indexed image using a first weight corresponding to the first semantic class and a second weight corresponding to the second semantic class, wherein the first weight adapts enhancement of the image frame differently from the second weight based on a difference between the first semantic class and the second semantic class.

[0153] It should be noted that the functions shown in the figures or described above may be implemented in an electronic device 101, 102, 104, server 106, or other device(s) in any suitable manner. For example, in an embodiment, at least some of the functions shown in the figures or described above 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 the figures or described above may be implemented or supported using dedicated hardware components. In general, the functions shown in the figures or described above may be performed using any suitable hardware or any suitable combination of hardware and software / firmware instructions. Also, the functions shown in the figures or described above may be performed by a single device or by multiple devices.

[0154] Although this disclosure has been described with reference to various example embodiments, various changes and modifications may be suggested to one skilled in the art. It is intended that this disclosure encompasses such changes and modifications as fall within the scope of the appended claims.

Claims

1.A method for multi-dimensional semantic contrast and color enhancement, the method comprising:obtaining (201), using at least one processing device (120) of an electronic device (101), an image frame;performing (202), using the at least one processing device (120), semantic segmentation of the image frame to generate semantic segmentation information for the image frame, the semantic segmentation information including an indexed image representing at least a first semantic class and a second semantic class; andperforming (203), using the at least one processing device (120), multi-scale local tone mapping of the indexed image using a first weight corresponding to the first semantic class and a second weight corresponding to the second semantic class;wherein the first weight adapts enhancement of the image frame differently from the second weight based on a difference between the first semantic class and the second semantic class.2.The method of Claim 1, wherein the performing (202) the semantic segmentation comprises:dividing an input luminance image corresponding to the image frame into multiple semantic classes including at least the first semantic class and the second semantic class;applying a first bank of guided filters to the input luminance image to generate first base components and first detail components; andapplying a second bank of guided filters to the first base components to generate second base components and second detail components;wherein the enhancement of the image frame is performed by employing both the first weight corresponding to the first semantic class and the second weight corresponding to the second semantic class to adjust the first detail components and the second detail components.3.The method of Claim 2, wherein the enhancement of the image frame comprises one of increasing or decreasing contributions of the first detail components and the second detail components to an enhanced image based on the first semantic class and the second semantic class.4.The method of Claim 3, wherein the enhanced image is determined based on:whererepresents the enhanced image,represents the second base components,represents the indexed image,represents the first weight corresponding to the first detail component,represents the second weight corresponding to the second detail component,represents the first detail components enhanced based on the first semantic class and the second semantic class, andrepresents the second detail components enhanced based on the first semantic class and the second semantic class.5.The method of any one of Claim 2 to 4, wherein the enhancement of the first detail components and the second detail components employs a modulation function that maps each of the first semantic class and the second semantic class to a corresponding modulation strength and a function processing positive details and negative details symmetrically in order to boost or suppress details based on a distance from a specified value.6.The method of any one of Claims 1 to 5, wherein the performing the semantic segmentation comprises:dividing the image frame into multiple semantic classes including at least the first semantic class and the second semantic class;applying first color processing to portions of the image frame corresponding to the first semantic class; andapplying second color processing to portions of the image frame corresponding to the second semantic class;wherein color enhancement of the image frame is performed independently for colors of different semantic regions.7.The method of Claim 6, wherein:the first color processing is associated with first hue shift or saturation boost values; andthe second color processing is associated with second hue shift or saturation boost values.8.An electronic device (101) comprising:at least one processing device (120) configured to:obtain an image frame;perform semantic segmentation of the image frame to generate semantic segmentation information for the image frame, the semantic segmentation information including an indexed image representing at least a first semantic class and a second semantic class; andperform multi-scale local tone mapping of the indexed image using a first weight corresponding to the first semantic class and a second weight corresponding to the second semantic class;wherein the first weight adapts enhancement of the image frame differently from the second weight based on a difference between the first semantic class and the second semantic class.9.The electronic device (101) of Claim 8, wherein, to perform the semantic segmentation, the at least one processing device (120) is configured to:divide an input luminance image corresponding to the image frame into multiple semantic classes including at least the first semantic class and the second semantic class;apply a first bank of guided filters to the input luminance image to generate first base components and first detail components; andapply a second bank of guided filters to the first base components to generate second base components and second detail components;wherein the at least one processing device (120) is configured to enhance the image frame based on both the first weight corresponding to the first semantic class and the second weight corresponding to the second semantic class to adjust the first detail components and the second detail components.10.The electronic device (101) of Claim 9, wherein, to enhance the image frame, the at least one processing device (120) is configured to perform one of increasing or decreasing contributions of the first detail components and the second detail components to an enhanced image based on the first semantic class and the second semantic class.11.The electronic device of Claim 10, wherein the at least one processing device (120) is configured to generate the enhanced image based on:whererepresents the enhanced image,represents the second base components,represents the indexed image,represents the first weight corresponding to the first detail component,represents the second weight corresponding to the second detail component,represents the first detail components enhanced based on the first semantic class and the second semantic class, andrepresents the second detail components enhanced based on the first semantic class and the second semantic class.12.The electronic device (101) of Claim 9, wherein the at least one processing device (120) is configured to enhance sharpness and contrast for the first detail components and the second detail components based on the first semantic class and the second semantic class.13.The electronic device (101) of Claim 9, wherein:the at least one processing device (120) is configured to enhance the first detail components by providing detail enhancement and noise suppression; andthe at least one processing device (120) is configured to enhance the second detail components by providing detail enhancement and bright area negative detail enhancement.14.The electronic device (101) of any one of Claims 8 to 13, wherein the at least one processing device (120) is configured to perform semantic segmentation by:dividing the image frame into multiple semantic classes including at least the first semantic class and the second semantic class;applying first color processing to portions of the image frame corresponding to the first semantic class; andapplying second color processing to portions of the image frame corresponding to the second semantic class;wherein color enhancement of the image frame is performed independently for colors of different semantic regions.15.A computer-readable storage medium storing instructions that, when executed by at least one processing device (120) individually or collectively, cause the at least one processing device (120) to perform the method of any one of claims 1-7.

Images