Method and apparatus for saliency-based frame color enhancement

Abstract

The present disclosure relates to a method and device for display processing, including an apparatus, e.g., a DPU. The apparatus can detect at least one of a scene change between consecutive frames of the plurality of frames or a threshold number of received frames of the plurality of frames. The apparatus can also generate at least one of a saliency map, an object segmentation map, or a depth map based on a downsampled image of the first frame. The apparatus can also apply a CMF for a color space associated with the plurality of frames to a plurality of pixels in one or more subsequent frames of the plurality of frames, the CMF being applied until at least one of a subsequent scene change or a threshold number of subsequent received frames.

Description

[Technical Field]

[0001] The present disclosure relates generally to processing systems, and more particularly to one or more techniques for display or image processing. [Background technology]

[0002] Computing devices often perform graphics processing and / or display processing (e.g., utilizing a graphics processing unit (GPU), a central processing unit (CPU), a display processor, etc.) to render and display visual content. Such computing devices may include, for example, computer workstations, mobile phones such as smartphones, embedded systems, personal computers, tablet computers, and video game consoles. A GPU is configured to execute a graphics processing pipeline including one or more processing stages that work together to execute graphics processing commands and output frames. A central processing unit (CPU) can control the operation of the GPU by issuing one or more graphics processing commands to the GPU. Modern CPUs are typically capable of simultaneously executing multiple applications, each of which may require the use of the GPU during execution. A display processor is configured to convert digital information received from the CPU into analog values ​​and can issue commands to a display panel to display the visual content. A device that provides content for visual presentation on a display may utilize a GPU and / or a display processor.

[0003]

[0003] A GPU of a device may be configured to execute processes in a graphics processing pipeline. Additionally, a display processor or display processing unit (DPU) may be configured to execute processes for display processing. However, with the advent of wireless communications and small handheld devices, there has been an increasing need for improved graphics or display processing. Summary of the Invention

[0004] The following presents a simplified summary of one or more aspects in order to provide a basic understanding of such aspects. This summary is not an exhaustive overview of all contemplated aspects, nor is it intended to identify key or critical elements of all aspects, nor to delineate the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to the more detailed description that is presented later.

[0005] In one aspect of the present disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus may be a display processing unit (DPU) or any apparatus capable of performing display processing or image processing. The apparatus may detect at least one of a scene change between consecutive frames of a plurality of frames or a threshold number of received frames of the plurality of frames, each of the plurality of frames including a plurality of pixels, and a first frame of the plurality of frames corresponding to the scene change between consecutive frames or the threshold number of received frames. The apparatus may also downsample the image of the first frame to generate a downsampled image of the first frame, the downsampled image being generated upon detecting at least one of the scene change between consecutive frames or the threshold number of received frames. The apparatus may also generate at least one of a saliency map or a depth map based on the downsampled image of the first frame, the first frame including a plurality of first pixels, and the downsampled image including a plurality of downsampled pixels. Additionally, the device may apply a color mapping function (CMF) for a color space associated with the plurality of frames to a plurality of pixels in one or more subsequent frames of the plurality of frames, the CMF being applied until at least one of a subsequent scene change in the plurality of frames or a subsequent threshold number of received frames of the plurality of frames. The device may also adjust at least one of one or more low-saliency colors, one or more high-saliency colors, or depth information of the plurality of downsampled pixels, the depth information corresponding to one or more colors including depths within a depth range or one or more colors including depths outside the depth range.

[0006] The details of one or more examples of this disclosure are set forth in the accompanying drawings and the description below. Other features, objects, and advantages of the present disclosure will become apparent from the description and drawings, and from the claims. [Brief explanation of the drawings]

[0007] [Figure 1]

[0007] A block diagram illustrating an example content generation system in accordance with one or more techniques of this disclosure. [Figure 2]

[0008] 1 is a diagram of an exemplary GPU in accordance with one or more techniques of this disclosure. [Figure 3]

[0009] FIG. 1 is a diagram of display or image processing components in accordance with one or more techniques of this disclosure. [Figure 4]

[0010] 1 is a diagram of an example saliency map in accordance with one or more techniques of this disclosure. [Figure 5]

[0011] FIG. 1 is a diagram of components for a color conversion process in accordance with one or more techniques of this disclosure. [Figure 6]

[0012] 1 is a communication flow diagram illustrating exemplary communications between a GPU / CPU, a DPU, and a display, in accordance with one or more techniques of this disclosure. [Figure 7]

[0013] 1 is a flowchart of an example method of display processing in accordance with one or more techniques of this disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0008]

[0014] Some aspects of display processing utilize visualization techniques, such as saliency maps, to compute images. Saliency maps utilize the concept of saliency within an image, where saliency can refer to certain features of an image or frame in the context of display processing, such as pixels, resolution, etc. These features can describe visually appealing, or “salient,” locations within an image or frame. A saliency map is a topographical representation of these visually appealing or salient locations within an image or frame. For example, a saliency map can help highlight the foreground of an image compared to its background. Photographic images can accurately depict the exact colors of objects and scenes within an image. However, photographic images cannot easily depict the depth of objects within an image or the depth of visually appealing locations within an image. In contrast, certain painting techniques can depict depth within an image based on aerial perspective, which refers to the effect the atmosphere has on the appearance of an object when viewed from a distance. For example, as the distance between an object in an image and the viewer increases, the contrast between the object and its background decreases, as does the contrast of any markings or details within the object. To portray this aerial or atmospheric perspective in an image, distant objects may be depicted in cool colors, i.e., colors with a bluish tint, while closer objects may be depicted in warm colors, i.e., colors with a reddish tint. Furthermore, when utilizing aerial or atmospheric perspective, the colors of objects in the image may also be less saturated and shift toward the background color, which may correspond to the bluish tint of the color. However, there may be other objects or colors in the image that would benefit from creating the illusion of depth. Aspects of the present disclosure can detect regions of interest in a particular image, e.g., a photographic image, and focus on these regions of interest by creating the illusion of depth. For example, aspects of the present disclosure can create the illusion of depth for regions of interest in an image through aerial or atmospheric perspective.Additionally, aspects of the present disclosure can adaptively adjust pixel colors in an image based on pixel saliency information, such as via a saliency map. By doing so, aspects of the present disclosure can generate atmospheric or aerial perspective in an image. Additionally, aspects of the present disclosure can reduce color saturation in the background of an image and increase color saturation in the foreground of an image.

[0009]

[0015] Various aspects of the systems, devices, computer program products, and methods are described more fully below with reference to the accompanying drawings. However, the present disclosure may be embodied in many different forms and should not be construed as limited to any specific structure or function presented throughout this disclosure. Rather, these aspects are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art. Based on the teachings herein, those skilled in the art should appreciate that the scope of the present disclosure covers any aspect of the systems, devices, computer program products, and methods disclosed herein, whether implemented independently of or in combination with other aspects of the present disclosure. For example, an apparatus may be implemented or a method may be practiced using any number of the aspects described herein. Additionally, the scope of the present disclosure is intended to cover such devices or methods practiced using other structure, functions, or structure and functions in addition to or other than the various aspects of the present disclosure described herein. Any aspect disclosed herein may be embodied by one or more elements of a claim.

[0010]

[0016] While various aspects are described herein, many variations and permutations of these aspects fall within the scope of the present disclosure. Some potential benefits and advantages of aspects of the present disclosure are described, but the scope of the present disclosure is not limited to any particular benefit, use, or purpose. Rather, aspects of the present disclosure are broadly applicable to different wireless technologies, system configurations, networks, and transmission protocols, some of which are shown by way of example in the figures and description below. The detailed description and drawings are merely illustrative rather than limiting of the present disclosure, the scope of which is defined by the appended claims and their equivalents.

[0011]

[0017] Several aspects are presented with respect to various apparatus and methods. These apparatus and methods are described in the detailed description that follows and illustrated in the accompanying drawings by various blocks, components, circuits, processes, algorithms, etc. (collectively referred to as "elements"). These elements may be implemented using electronic hardware, computer software, or any combination thereof. Whether such elements are implemented as hardware or software depends on the particular application and design constraints imposed on the overall system.

[0012]

[0018] As an example, an element, or any portion of an element, or any combination of elements, may be implemented as a "processing system" including one or more processors (which may also be referred to as processing units). Examples of processors include microprocessors, microcontrollers, graphics processing units (GPUs), general-purpose GPUs (GPGPUs), central processing units (CPUs), application processors, digital signal processors (DSPs), reduced instruction set computing (RISC) processors, systems-on-chips (SOCs), baseband processors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), programmable logic devices (PLDs), state machines, gate logic, discrete hardware circuits, and other suitable hardware configured to perform various functions described throughout this disclosure. One or more processors in a processing system may execute software. Software may be broadly interpreted to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software components, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise. The term application may refer to software. As described herein, one or more techniques may refer to an application, i.e., software configured to perform one or more functions. In such examples, the application may be stored in memory, e.g., on-chip memory of a processor, system memory, or any other memory. Hardware described herein, such as a processor, may be configured to execute the application. For example, an application may be described as including code that, when executed by the hardware, causes the hardware to perform one or more techniques described herein.As an example, hardware may access code from memory and execute the code accessed from memory to perform one or more techniques described herein. In some examples, components are identified in this disclosure. In such examples, the components may be hardware, software, or a combination thereof. The components may be separate components or subcomponents of a single component.

[0013]

[0019] Thus, in one or more examples described herein, the functions described may be implemented in hardware, software, or any combination thereof. If implemented in software, the functions may be stored on or encoded as one or more instructions or code on a computer-readable medium. Computer-readable media includes computer storage media. A storage medium may be any available medium that can be accessed by a computer. By way of example, and not limitation, such computer-readable media may comprise random access memory (RAM), read-only memory (ROM), electrically erasable programmable ROM (EEPROM), optical disk storage, magnetic disk storage, other magnetic storage devices, combinations of the aforementioned types of computer-readable media, and any other medium that can be used to store computer-executable code in the form of instructions or data structures that can be accessed by a computer.

[0014]

[0020] Generally, this disclosure describes techniques for improving the rendering of graphical content and / or reducing the load on a processing unit, i.e., any processing unit configured to perform one or more techniques described herein, such as a GPU, having a graphics processing pipeline within a single device or multiple devices. For example, this disclosure describes techniques for graphics processing in any device that utilizes graphics processing. Other exemplary benefits are described throughout this disclosure.

[0015]

[0021] Instances of the term “content” as used herein may refer to “graphical content,” “image,” and vice versa. This is true whether the term is used as an adjective, a noun, or other part of speech. In some examples, the term “graphical content” as used herein may refer to content generated by one or more processes of a graphics processing pipeline. In some examples, the term “graphical content” as used herein may refer to content generated by a processing unit configured to perform graphics processing. In some examples, the term “graphical content” as used herein may refer to content generated by a graphics processing unit.

[0016]

[0022] In some examples, the term "display content" as used herein may refer to content generated by a processing unit configured to perform display processing. In some examples, the term "display content" as used herein may refer to content generated by a display processing unit. Graphical content may be processed to become display content. For example, a graphics processing unit may output graphical content such as a frame to a buffer (which may be referred to as a frame buffer). The display processing unit may read graphical content such as one or more frames from the buffer and perform one or more display processing techniques on them to generate display content. For example, the display processing unit may be configured to perform compositing on one or more rendered layers to generate a frame. As another example, the display processing unit may be configured to composite, blend, or otherwise combine two or more layers together into a single frame. The display processing unit may be configured to perform scaling, e.g., upscaling or downscaling, on a frame. In some examples, a frame may refer to a layer. In other examples, a frame may refer to two or more layers that have already been blended together to form a frame; i.e., a frame includes two or more layers, and a frame including two or more layers may then be blended.

[0017]

[0023] FIG. 1 is a block diagram illustrating an example content generation system 100 configured to implement one or more techniques of the present disclosure. The content generation system 100 includes a device 104. The device 104 may include one or more components or circuits for performing various functions described herein. In some examples, one or more components of the device 104 may be components of a system-on-chip (SOC). The device 104 may include one or more components configured to perform one or more techniques of the present disclosure. In the illustrated example, the device 104 may include a processing unit 120, a content encoder / decoder 122, and a system memory 124. In some aspects, the device 104 may include several optional components, such as a communication interface 126, a transceiver 132, a receiver 128, a transmitter 130, a display processor 127, and one or more displays 131. References to the display 131 may refer to one or more displays 131. For example, the display 131 may include a single display or multiple displays. The display 131 may include a first display and a second display. The first display may be a left-eye display, and the second display may be a right-eye display. In some examples, the first and second displays may receive different frames for presentation thereon. In other examples, the first and second displays may receive the same frames for presentation thereon. In further examples, the results of the graphics processing may not be displayed on the device, e.g., the first and second displays may not receive any frames for presentation thereon. Instead, the frames or the graphics processing results may be transferred to another device. In some aspects, this may be referred to as split rendering.

[0018]

[0024] Processing unit 120 may include internal memory 121. Processing unit 120 may be configured to perform graphics processing, such as in graphics processing pipeline 107. Content encoder / decoder 122 may include internal memory 123. In some examples, device 104 may include a display processor, such as display processor 127, to perform one or more display processing techniques on one or more frames generated by processing unit 120 before presentation by one or more displays 131. Display processor 127 may be configured to perform display processing. For example, display processor 127 may be configured to perform one or more display processing techniques on one or more frames generated by processing unit 120. One or more displays 131 may be configured to display or otherwise present frames processed by display processor 127. In some examples, one or more displays 131 may include one or more of a liquid crystal display (LCD), a plasma display, an organic light-emitting diode (OLED) display, a projection display device, an augmented reality display device, a virtual reality display device, a head-mounted display, or any other type of display device.

[0019]

[0025] Memory external to the processing unit 120 and the content encoder / decoder 122, such as system memory 124, may be accessible by the processing unit 120 and the content encoder / decoder 122. For example, the processing unit 120 and the content encoder / decoder 122 may be configured to read from and / or write to external memory, such as the system memory 124. The processing unit 120 and the content encoder / decoder 122 may be communicatively coupled to the system memory 124 via a bus. In some examples, the processing unit 120 and the content encoder / decoder 122 may be communicatively coupled to each other via a bus or a different connection.

[0020]

[0026] The content encoder / decoder 122 may be configured to receive graphical content from any source, such as the system memory 124 and / or the communication interface 126. The system memory 124 may be configured to store the received encoded or decoded graphical content. The content encoder / decoder 122 may be configured to receive the encoded or decoded graphical content in the form of coded pixel data, for example, from the system memory 124 and / or the communication interface 126. The content encoder / decoder 122 may be configured to encode or decode any graphical content.

[0021]

[0027] The internal memory 121 or the system memory 124 may include one or more volatile or non-volatile memory or storage devices. In some examples, the internal memory 121 or the system memory 124 may include RAM, SRAM, DRAM, erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, magnetic or optical data media, or any other type of memory.

[0022]

[0028] Internal memory 121 or system memory 124 may be a non-transitory storage medium, according to some examples. The term "non-transitory" may indicate that the storage medium is not embodied in a carrier wave or propagating signal. However, the term "non-transitory" should not be interpreted to mean that internal memory 121 or system memory 124 is non-movable or that its contents are static. As one example, system memory 124 may be removed from device 104 and moved to another device. As another example, system memory 124 may not be removable from device 104.

[0023]

[0029] Processing unit 120 may be a central processing unit (CPU), a graphics processing unit (GPU), a general-purpose GPU (GPGPU), or any other processing unit that may be configured to perform graphics processing. In some examples, processing unit 120 may be integrated into the motherboard of device 104. In some examples, processing unit 120 may reside on a graphics card installed in a port in the motherboard of device 104, or may be otherwise integrated into a peripheral device configured to interoperate with device 104. Processing unit 120 may include one or more processors, such as one or more microprocessors, GPUs, application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), arithmetic logic units (ALUs), digital signal processors (DSPs), discrete logic, software, hardware, firmware, other equivalent integrated circuits or discrete logic circuits, or any combination thereof. If the techniques are implemented partially in software, processing unit 120 may store instructions for the software in a suitable non-transitory computer-readable storage medium, such as internal memory 121, and may execute the instructions in hardware using one or more processors to perform the techniques of the present disclosure. Any of the above, including hardware, software, a combination of hardware and software, etc., may be considered to be one or more processors.

[0024]

[0030] The content encoder / decoder 122 may be any processing unit configured to perform content decoding. In some examples, the content encoder / decoder 122 may be integrated into the motherboard of the device 104. The content encoder / decoder 122 may include one or more processors, such as one or more microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), arithmetic logic units (ALUs), digital signal processors (DSPs), video processors, discrete logic, software, hardware, firmware, other equivalent integrated or discrete logic circuitry, or any combination thereof. If the techniques are implemented partially in software, the content encoder / decoder 122 may store instructions for the software in a suitable non-transitory computer-readable storage medium, e.g., internal memory 123, and may execute the instructions in hardware using one or more processors to perform the techniques of this disclosure. Any of the above, including hardware, software, a combination of hardware and software, etc., may be considered to be one or more processors.

[0025]

[0031] In some aspects, the content generation system 100 may include an optional communication interface 126. The communication interface 126 may include a receiver 128 and a transmitter 130. The receiver 128 may be configured to perform any receiving function described herein with respect to the device 104. Additionally, the receiver 128 may be configured to receive information, e.g., eye or head location information, rendering commands, or position information, from another device. The transmitter 130 may be configured to perform any transmitting function described herein with respect to the device 104. For example, the transmitter 130 may be configured to transmit information, which may include a request for content, to another device. The receiver 128 and the transmitter 130 may be combined into a transceiver 132. In such an example, the transceiver 132 may be configured to perform any receiving and / or transmitting functions described herein with respect to the device 104.

[0026]

[0032] 1 , in some aspects, display processor 127 may include a determination component 198 configured to detect at least one of a scene change between consecutive frames of a plurality of frames or a threshold number of received frames of a plurality of frames, each of the plurality of frames including a plurality of pixels, and a first frame of the plurality of frames corresponding to the scene change between consecutive frames or the threshold number of received frames. Determination component 198 may also be configured to downsample the image of the first frame to generate a downsampled image of the first frame, the downsampled image being generated upon detecting at least one of the scene change between consecutive frames or the threshold number of received frames. Determination component 198 may also be configured to generate at least one of a saliency map or a depth map based on the downsampled image of the first frame, the first frame including a plurality of first pixels, and the downsampled image including a plurality of downsampled pixels. The determination component 198 may also be configured to apply a color mapping function (CMF) for a color space associated with the plurality of frames to the plurality of pixels in one or more subsequent frames of the plurality of frames, where the CMF is applied until at least one of a subsequent scene change in the plurality of frames or a subsequent threshold number of received frames of the plurality of frames. The determination component 198 may also be configured to adjust at least one of one or more low-saliency colors, one or more high-saliency colors, or depth information of the plurality of downsampled pixels, where the depth information corresponds to one or more colors including depths within a depth range or one or more colors including depths outside a depth range. While the following description may focus on display processing or image processing, the concepts described herein may be applicable to other similar processing techniques.

[0027]

[0033] As described herein, a device, such as device 104, may refer to any device, apparatus, or system configured to perform one or more techniques described herein. For example, a device may be a server, a base station, a user equipment, a client device, a station, an access point, a computer, e.g., a personal computer, a desktop computer, a laptop computer, a tablet computer, a computer workstation, or a mainframe computer, an end product, an apparatus, a telephone, a smartphone, a server, a video game platform or console, a handheld device, e.g., a portable video game device or personal digital assistant (PDA), a wearable computing device, e.g., a smartwatch, an augmented reality device, or a virtual reality device, a non-wearable device, a display or display device, a television, a television set-top box, an intermediate network device, a digital media player, a video streaming device, a content streaming device, an in-car computer, any mobile device, any device configured to generate graphical content, or any device configured to perform one or more techniques described herein. While processes herein may be described as being performed by particular components (e.g., a GPU), further embodiments may be performed using other components (e.g., a CPU) consistent with disclosed embodiments.

[0028]

[0034] A GPU can process multiple types of data or data packets in a GPU pipeline. For example, in some aspects, a GPU can process two types of data or data packets, e.g., context register packets and draw call data. A context register packet can be a set of global state information, e.g., information about global registers, shading programs, or constant data, that can adjust how a graphics context is processed. For example, a context register packet can include information about a color format. In some aspects of a context register packet, there can be a bit that indicates which workload belongs to a context register. Also, there can be multiple functions or programming running simultaneously and / or in parallel. For example, a function or programming can describe a particular operation, e.g., a color mode or color format. Thus, a context register can define multiple states of the GPU.

[0029]

[0035] The context state may be utilized to determine how individual processing units, e.g., a vertex fetcher (VFD), a vertex shader (VS), a shader processor, or a geometry processor, function and / or in which mode the processing units function. To do so, the GPU may use context registers and programming data. In some aspects, the GPU may generate workloads, e.g., vertex or pixel workloads, in a pipeline based on the context register definition of a mode or state. Some processing units, e.g., VFDs, may use these states to determine some functions, e.g., how vertices are assembled. Because these modes or states can change, the GPU may need to modify the corresponding context. Furthermore, the workload corresponding to a mode or state may follow the changing mode or state.

[0030]

[0036] FIG. 2 illustrates an exemplary GPU 200 in accordance with one or more techniques of the present disclosure. As illustrated in FIG. 2, the GPU 200 includes a command processor (CP) 210, a draw call packet 212, a VFD 220, a VS 222, a vertex cache (VPC) 224, a triangle setup engine (TSE) 226, a rasterizer (RAS) 228, a Z process engine (ZPE) 230, a pixel interpolator (PI) 232, a fragment shader (FS) 234, a render backend (RB) 236, a level 2 (L2) cache (UCHE) 238, and a system memory 240. While FIG. 2 illustrates the GPU 200 as including processing units 220-238, the GPU 200 may include several additional processing units. Furthermore, the processing units 220-238 are merely an example, and any combination or order of processing units may be used by a GPU in accordance with the present disclosure. The GPU 200 also includes a command buffer 250 , a context register packet 260 , and a context state 261 .

[0031]

[0037] 2, the GPU can utilize a CP, e.g., CP 210, or a hardware accelerator, to parse the command buffer into context register packets, e.g., context register packet 260, and / or draw call data packets, e.g., draw call packet 212. CP 210 can then send context register packet 260 or draw call data packet 212 to processing units or processing blocks within the GPU through separate paths. Furthermore, command buffer 250 can alternate between different states of context registers and draw calls. For example, the command buffer can be structured in the following manner: context register for context N, draw call for context N, context register for context N+1, and draw call for context N+1.

[0032]

[0038] In display or image processing aspects, several different objects or colors may be adjusted or highlighted within an image or frame. Doing so may enhance the objects or colors within the image, which may improve the overall appearance of the image. In order to adjust or highlight objects or colors within an image, the objects or colors may need to be identified prior to adjustment or highlighting. In some cases, this process may be performed in an image processing pipeline or a display processing pipeline. Furthermore, this process may be referred to as an object or color identification process.

[0033]

[0039] FIG. 3 illustrates a diagram 300 of components for display or image processing. For example, FIG. 3 illustrates an exemplary structure for an object or color classification process. As illustrated in FIG. 3, diagram 300 may include an input 310, an image downscaler 320, a frame selection step 322, a pixel classifier 330, and a multiplexer (MUX) 340. Diagram 300 may also include a content source, which may include a GPU 350 and / or a video decoder 352. Furthermore, diagram 300 may include an artificial intelligence (AI) processor or AI processing unit 360, CPU software 370, memory 380, an image post-processing unit 390, and an output 392. The input 310 of diagram 300 may include an image or image sequence. Additionally, the output 392 of diagram 300 may include a processed image or image sequence.

[0034]

[0040] As shown in FIG. 3 , input 310 can communicate with image downscaler 320, pixel classifier 330, and image post-processing unit 390. Image downscaler 320 can also communicate with frame selection step 322, for example, to select a frame or image. Frame selection step 322 can also communicate, for example, a reduced-resolution image with AI processor 360 and / or CPU software 370, for example, via memory 380. AI processor 360 can also communicate with CPU software 370 via memory 380. GPU 350 and video decoder 352 can communicate with MUX 340, for example, via memory 380. MUX 340 can also communicate with input 310. CPU software 370 can also communicate, for example, configuration updates to pixel classifier 330 and / or image post-processing unit 390. Pixel classifier 330 can also communicate with image post-processing unit 390. The image post-processing unit 390 may then communicate the image or image sequence to an output 392, for example.

[0035]

[0041] As further depicted in FIG. 3 , the image post-processing unit 390 may be pre-frame composite or post-frame composite. In some aspects, the diagram 300 may include a low-power real-time pixel processing pipeline, which may include the input 310, the image downscaler 320, the pixel classifier 330, and / or the image post-processing unit 390. The diagram 300 may also include non-real-time processing, which may be performed on selected images or frames. This non-real-time processing may include a frame selection step 322, a MUX 340, a GPU 350, a video decoder 352, an AI processor 360, CPU software 370, and memory 380. In some aspects, the AI ​​processor 360 may be referred to as a neural network processor. The CPU software 370 may also be utilized for statistical analysis.

[0036]

[0042] Some aspects of display processing utilize several visualization techniques, such as saliency maps, to compute an image. A saliency map utilizes the concept of saliency within an image, where saliency can refer to certain features of an image or frame in the context of display processing, such as pixels, resolution, etc. These features can describe visually appealing or "salient" locations within an image or frame. A saliency map is a topographical representation of these visually appealing or salient locations within an image or frame. For example, a saliency map can help highlight the foreground of an image compared to its background. In some instances, a neural network (NN) or a convolutional neural network (CNN) may be utilized to generate the saliency map. Aspects of the present disclosure may also utilize an object segmentation map. An object segmentation map includes a binary classification for each pixel, where each pixel is classified as being in either the foreground or background of the image. Figure 4 below is an example object segmentation map, which may be another term used for foreground / background segmentation within an image or frame.

[0037]

[0043] FIG. 4 is an exemplary saliency map or object segmentation map 400 for display or image processing. As shown in FIG. 4, the saliency / object segmentation map 400 corresponds to a respective image or photographic image. For example, FIG. 4 is a saliency / object segmentation map 400 for a photographic image including a cat 410 and a moon 420. As shown in FIG. 4, the saliency map highlights objects of interest, i.e., salient objects, in the image. As depicted by the saliency / object segmentation map 400, the cat 410 and the moon 420 are objects of interest, i.e., salient objects, in the corresponding photographic image.

[0038]

[0044] Photographic images can accurately depict the exact colors of objects and scenes within an image. However, they cannot easily depict the depth of objects within an image or the depth of visually appealing locations within an image. In contrast, certain painting techniques can depict depth within an image based on aerial perspective, which refers to the effect that the atmosphere has on the appearance of an object when viewed from a distance. For example, as the distance between an object and the viewer in an image increases, the contrast between the object and its background decreases, as does the contrast of any markings or details within the object.

[0039]

[0045] To portray this aerial or atmospheric perspective in an image, distant objects may be depicted in cool colors, i.e., colors with a bluish tint, while closer objects may be depicted in warm colors, i.e., colors with a reddish tint. Furthermore, when utilizing aerial or atmospheric perspective, the colors of objects in the image may also be shifted toward the background color, which may be less saturated and correspond to a bluish tint. However, there may be other objects or colors in the image that would benefit from creating the illusion of depth. Based on the above, it may be advantageous to detect regions of interest in a particular image, for example, a photographic image. It may also be advantageous to focus on these regions of interest by creating the illusion of depth. Furthermore, it may be advantageous to create the illusion of depth for regions of interest in the image through aerial or atmospheric perspective.

[0040]

[0046] Aspects of the present disclosure can detect regions of interest in a particular image, e.g., a photographic image, and focus on these regions of interest by creating the illusion of depth. For example, aspects of the present disclosure can create the illusion of depth for regions of interest in an image via aerial or atmospheric perspective. Additionally, aspects of the present disclosure can adaptively adjust pixel colors in an image based on pixel saliency information, such as via a saliency map. By doing so, aspects of the present disclosure can create an atmospheric or aerial perspective in an image. Additionally, aspects of the present disclosure can reduce color saturation in the background of an image and increase color saturation in the foreground of an image.

[0041]

[0047] In some cases, such as after detecting a scene change in an image, aspects of the present disclosure may downscale or downsample the image. The aspects of the present disclosure may feed the downsampled image to a neural network (NN) processor, such as a convolutional neural network (CNN) or an artificial intelligence (AI) analyzer. As a result, the neural network processor may produce or generate a saliency map or object segmentation map. The saliency map or object segmentation map may then be compared to the downsampled image using, for example, software, and aspects of the present disclosure may analyze the colors of the downsampled image compared to the salient objects in the saliency map. Thus, aspects of the present disclosure may determine which colors are part of a salient group in the saliency map and which colors are not part of a salient group. Based on the analysis of the salient colors, the saliency map may be converted into a set of high-saliency colors and a set of low-saliency colors.

[0042]

[0048] After analyzing the salient colors, embodiments of the present disclosure may utilize a color mapping function (CMF) or color processing engine, e.g., a three-dimensional (3D) look-up table (LUT), to adjust or remap colors in an image. In some cases, the color mapping function, e.g., a 3D LUT, may remap high-salience colors to more saturated high-salience colors and low-salience colors to less saturated low-salience colors. For example, the color mapping function, e.g., a 3D LUT, may remap foreground objects to more saturated high-salience colors and background objects to less saturated low-salience colors. To do so, embodiments of the present disclosure may increase the saturation of the foreground objects or shift the colors of the foreground objects toward warmer colors (i.e., redder colors). Also, embodiments of the present disclosure may decrease the saturation of the background objects or shift the colors of the background objects toward cooler colors (i.e., bluish colors).

[0043]

[0049] Furthermore, embodiments of the present disclosure may reduce the amount of power utilized in, for example, a DPU to shift the saturation of colors within each frame. For example, analyzing a saliency map or object segmentation map upon detecting a scene change and utilizing a color mapping function, e.g., a 3D LUT, to remap high-saliency and low-saliency colors may reduce the amount of power utilized to shift the saturation of colors within each frame. For example, configuring a color mapping function, e.g., a 3D LUT, may not be used for several frames after a detected scene change, such that, for example, analysis of a new saliency map by a neural network may not be utilized on a frame-by-frame basis. Rather, embodiments of the present disclosure may perform saliency and neural network analysis for several frames after a scene change or a threshold amount of frames, e.g., N frames, to reduce the amount of power utilized for these frames. Thus, embodiments of the present disclosure may conserve power, for example, in a DPU, by utilizing saliency and neural network analysis for several frames within a particular scene, since the colors within that scene may not change significantly. Thus, aspects of the present disclosure can utilize the same saliency analysis until there is another scene change or up to a threshold amount of frames, eg, N frames.

[0044]

[0050] In some cases, aspects of the present disclosure may utilize a neural network to compute a spatial map, such as a depth map, an object segmentation map, or a saliency map. This spatial map may identify objects of interest within a frame, i.e., foreground / background objects and / or salient objects. For example, aspects of the present disclosure may perform statistical analysis to determine which objects are in the foreground or background of an image and which objects are salient objects. Aspects of the present disclosure may then convert the spatial map, such as a depth map or a saliency map, into a color map. The color map may then be utilized to adjust colors in each frame within a scene, or until a threshold amount of frames is reached. Furthermore, this color map may be resistant to movement within a frame, so a new color map may not be needed for frames within the same scene, thereby saving power.

[0045]

[0051] FIG. 5 is a diagram 500 of components for a color conversion process in accordance with one or more techniques of this disclosure. As shown in FIG. 5, diagram 500 includes a color conversion section 502, an artificial intelligence (AI) analysis section 504, an input image 510, a downsampled image 520, a neural network or AI analyzer 530, a saliency / object segmentation map 540, a saliency / object segmentation map analysis and color mapping function (CMF) generator 550, a color mapping function 560, and an output image 570. More specifically, diagram 500 of FIG. 5 includes a color conversion process that utilizes a saliency / object segmentation map analysis and a CMF, e.g., a three-dimensional (3D) look-up table (LUT). The color conversion process of FIG. 5 may be utilized to adjust high or low salience colors of an image.

[0046]

[0052] As shown in FIG. 5 , embodiments of the present disclosure can downsample an input image 510 to generate a downsampled image 520. This downsampled image 520 may then be used to generate a saliency / object segmentation map 540, such as via a neural network 530. Next, embodiments of the present disclosure can perform a saliency / object segmentation map analysis 550 of the saliency / object segmentation map 540, as well as include a CMF generator. Further, the saliency / object segmentation map analysis 550 may be combined with a CMF 560 to determine low or high salience colors for the image. Finally, the present disclosure can adjust the low or high salience colors of the image to generate an output image 570. As shown in FIG. 5 , embodiments of the present disclosure can adjust the low or high salience colors of the image to create an atmospheric or aerial perspective within the image.

[0047]

[0053] In some embodiments, upon detecting a scene change in an image, as shown in FIG. 5 , embodiments of the present disclosure utilize components within AI analysis section 504, such as downsampled image 520, neural network 530, saliency / object segmentation map 540, and saliency / object segmentation map analysis 550. Embodiments of the present disclosure may not perform steps within AI analysis section 504 for the remaining frames in the scene or until there is another scene change. That is, after performing steps within AI analysis section 504, each image or frame in the scene may be processed by components within color conversion section 502, such as CMF 560. Thus, embodiments of the present disclosure may utilize the same saliency analysis, such as steps within color conversion section 502, until there is another scene change or up to a threshold amount of frames, such as N frames. As such, the steps within color conversion section 502 may be real-time analysis. By doing so, embodiments of the present disclosure may reduce the amount of power utilized to perform a color conversion process for each frame in the scene. Upon detecting another scene change, aspects of the present disclosure may perform steps within the AI ​​analysis section 504.

[0048]

[0054] As shown above, embodiments of the present disclosure can analyze a saliency / object segmentation map to detect high-salience or low-salience pixels in an image. These high-salience or low-salience pixels may then be analyzed along with a color histogram or CMF to determine high-salience or low-salience colors in the image. For example, embodiments of the present disclosure can analyze statistical data indicating the relative probability that a particular color is associated with a high-salience or low-salience pixel in a frame. In one example, a particular color may be identified as a high-salience color if the color is associated with a high-salience pixel in a certain rate, e.g., 90%, of instances in which pixels having that color appear in a scene. Also, a color may be identified as a low-salience color if the color is associated with a low-salience pixel in a certain percentage of instances. These high-salience and low-salience colors may be adjusted to generate an output image.

[0049]

[0055] In some instances, aspects of the present disclosure may detect a scene change among consecutive frames or identify a threshold number of received frames (e.g., N frames), whichever occurs first. Aspects of the present disclosure may then generate a saliency / object segmentation map for a particular frame, e.g., a frame that triggers the detection of a scene change among consecutive frames or the identification of the threshold number of received frames. Additionally, the saliency map may be generated based on a downsampled image of the frame, such as by utilizing artificial intelligence (AI) analysis or a neural network (NN), e.g., a convolutional neural network (CNN).

[0050]

[0056] Additionally, aspects of the present disclosure may identify low or high salience colors for a particular frame. These colors may be identified based on an analysis of the frame's saliency / object segmentation map and the downsampled image. To do so, aspects of the present disclosure may compare the frame's saliency / object segmentation map with the downsampled image, such as by detecting colors associated with high salience regions within the frame, i.e., high salience colors. Aspects of the present disclosure may also compare the saliency map with the downsampled image, such as by detecting colors associated with low salience regions within the frame, i.e., low salience colors.

[0051]

[0057] As indicated above, embodiments of the present disclosure may also generate a color mapping function (CMF), e.g., a 3D look-up table (LUT), based on an analysis of the saliency / object segmentation map compared to a downsampled image of the frame. Furthermore, embodiments of the present disclosure may adjust low-saliency colors and / or high-saliency colors, such as via a CMF or 3D LUT. For example, embodiments of the present disclosure may decrease the color saturation of low-saliency colors, i.e., objects in the background of the image, and increase the color saturation of high-saliency colors, i.e., objects in the foreground of the image. Embodiments of the present disclosure may also generate a configuration of the CMF, e.g., a 3D LUT, such that high-saliency colors may undergo increased saturation and / or a shift toward warmer colors (i.e., redder colors). The generated configuration of the CMF, e.g., a 3D LUT, may also result in low-saliency colors undergoing decreased saturation and a shift toward cooler colors (i.e., bluish colors). Embodiments of the present disclosure may also update the CMF, e.g., a 3D LUT, with the newly generated color configuration.

[0052]

[0058] Aspects of the present disclosure can input an initial image and output an adjusted image based on the aforementioned techniques. The adjusted image may be generated based on a saliency-based color adjustment of pixels in the initial image. As illustrated herein, the output image can undergo increased saturation and / or a warm color shift for highly salient colors in the image. Additionally, the output image can undergo decreased saturation and / or a cool color shift for less salient colors in the image.

[0053]

[0059] Aspects of the present disclosure may include several benefits or advantages. For example, aspects of the present disclosure may include a low-power method for enhanced display using artificial intelligence (AI) analysis or neural networks (NNs). In some cases, the AI ​​analysis may be performed on a small number of input frames, e.g., frames corresponding to scene changes. Also, the NN or convolutional NN (CNN) may operate on a downsampled version of the input frame. Pixels may be processed at full resolution using a low-power color conversion block. Thus, aspects of the present disclosure may reduce the amount of power utilized for image processing, for example, in a DPU. Moreover, pixels may be processed using hardware based on a CMF, e.g., a 3D LUT. Aspects of the present disclosure may detect regions of interest within an image or frame and focus on them by creating the illusion of depth. As previously mentioned, this technique of the present disclosure may correspond to a technique called atmospheric perspective or aerial perspective.

[0054]

[0060] 6 is a communication flow diagram 600 of display processing in accordance with one or more techniques of this disclosure. As shown in FIG. 6, diagram 600 includes example communications between a DPU / AI analyzer 602, a GPU / CPU 604, and a display 606 in accordance with one or more techniques of this disclosure.

[0055]

[0061] At 610, the DPU 602 can detect at least one of a scene change between consecutive frames of a plurality of frames, e.g., frames 612, or a threshold number of received frames of a plurality of frames, each of the plurality of frames including a plurality of pixels, and a first frame of the plurality of frames corresponding to the scene change between consecutive frames or the threshold number of received frames. Also, each of the plurality of frames, e.g., frames 612, may be received at the DPU, e.g., DPU 602, from a GPU or a CPU, e.g., GPU / CPU 604.

[0056]

[0062] At 620, the DPU 602 may downsample the image of the first frame to generate a downsampled image of the first frame, the downsampled image being generated upon detecting at least one of a scene change between consecutive frames or a threshold number of received frames.

[0057]

[0063] At 630, the DPU / AI analyzer 602 may generate at least one of a saliency map, an object segmentation map, or a depth map based on a downsampled image of a first frame, where the first frame includes a plurality of first pixels and the downsampled image includes a plurality of downsampled pixels. At least one of the saliency map, the object segmentation map, or the depth map may be generated using a neural network (NN), a convolutional neural network (CNN), or an artificial intelligence (AI) analysis. In some aspects, at least one of the saliency map, the object segmentation map, or the depth map may be based on at least one of saliency information of the first frame, depth information of the first frame, or object information of the first frame. Data 632 may also be transferred between the DPU / AI analyzer 602 and the GPU / CPU 604.

[0058]

[0064] At 640, the CPU 604 may analyze one or more pixels in the downsampled image and one or more pixels in at least one of the saliency map, the object segmentation map, or the depth map. In some cases, the DPU 602 may perform statistical analysis on the downsampled image and at least one of the saliency map or the depth map. For example, analyzing one or more pixels in the downsampled image and one or more pixels in the at least one of the saliency map or the depth map may comprise performing statistical analysis on the downsampled image and at least one of the saliency map, the object segmentation map, or the depth map.

[0059]

[0065] At 650, the CPU 604 may identify at least one of a first group of colors of the plurality of downsampled pixels or a second group of colors of the plurality of downsampled pixels based on the downsampled image and at least one of the saliency map or the depth map. In some aspects, the first group of colors may be one or more low-saliency colors or one or more colors including depths within a depth range, and the second group of colors may be one or more high-saliency colors or one or more colors including depths outside the depth range.

[0060]

[0066] At 660, the CPU 604 may determine a color mapping function (CMF) for a color space associated with the multiple frames based on the downsampled image and at least one of a saliency map, an object segmentation map, or a depth map. In some cases, at least one of a saliency value, an object segmentation classification, or a depth value may correspond to each color of the color space associated with the multiple frames, and the CMF may be determined based on at least one of the saliency value or the depth value for each color of the color space. Furthermore, the CMF may be a polynomial or a three-dimensional (3D) look-up table (LUT). Data 662 may be transferred between the DPU / AI analyzer 602 and the GPU / CPU 604.

[0061]

[0067] At 670, the DPU 602 can apply the CMF to a plurality of pixels in one or more subsequent frames of the plurality of frames, the CMF being applied until at least one of a subsequent scene change in the plurality of frames or a subsequent threshold number of received frames of the plurality of frames.

[0062]

[0068] At 680, the DPU 602 may adjust at least one of the one or more low salience colors or the one or more high salience colors, where the depth information of the plurality of downsampled pixels corresponds to one or more colors having a depth within the depth range or one or more colors having a depth outside the depth range. After adjusting at least one of the one or more low salience colors or the one or more high salience colors, the DPU 602 may transmit one or more adjusted frames, e.g., frame 682, to a display, e.g., the display 606.

[0063]

[0069] Aspects of the present disclosure can analyze depth information to determine which depth values ​​are correlated with pixels having low or high salience in a given scene. For each downsampled pixel, aspects of the present disclosure can determine depth information, saliency information, and a foreground / background classification. Based on this, aspects of the present disclosure can analyze statistical data of which depth values ​​are associated with low or high salience. Once the depth (or depth range) associated with high salience is determined, aspects of the present disclosure can use this information to clean up the saliency map. For example, if a particular depth is likely to have a highly salient object, aspects of the present disclosure can reassign saliency to pixels having that particular depth to achieve greater consistency across pixels representing that object.

[0064]

[0070] In some aspects, the DPU 602 can decrease the saturation of one or more low salience colors, decrease the luminance of one or more low salience colors, and / or shift the color temperature of one or more low salience colors toward a cooler color temperature. For example, adjusting one or more low salience colors may comprise at least one of decreasing the saturation of one or more low salience colors, decreasing the luminance of one or more low salience colors, or shifting the color temperature of one or more low salience colors toward a cooler color temperature. Furthermore, the DPU 602 can increase the saturation of one or more high salience colors, increase the luminance of one or more high salience colors, and / or shift the color temperature of one or more high salience colors toward a warmer color temperature. For example, adjusting one or more high salience colors may comprise at least one of increasing the saturation of one or more high salience colors, increasing the luminance of one or more high salience colors, or shifting the color temperature of one or more high salience colors toward a cooler color temperature.

[0065]

[0071] Moreover, at least one of the one or more low salience colors or the one or more high salience colors may be adjusted based on depth information of the plurality of downsampled pixels. Further, the DPU 602 may adjust one or more pixels associated with at least one of the saliency map, the object segmentation map, or the depth map. For example, adjusting at least one of the one or more low salience colors or the one or more high salience colors may comprise adjusting one or more pixels associated with at least one of the saliency map, the object segmentation map, or the depth map.

[0066]

[0072] 7 is a flowchart 700 of an example method of graphics processing in accordance with one or more techniques of this disclosure. The method may be performed by an apparatus such as a display or image processing device, a DPU, a display or image processor, a display pipeline, a wireless communication device, and / or any apparatus capable of performing the display or image processing used in connection with the examples of FIGS. 1-6.

[0067]

[0073] In 702, the device can detect at least one of a scene change between consecutive frames of a plurality of frames or a threshold number of received frames of a plurality of frames, each of the plurality of frames including a plurality of pixels, and a first frame of the plurality of frames corresponding to the scene change between consecutive frames or the threshold number of received frames, as described with respect to the examples of Figures 1-6. For example, the DPU 602 can detect at least one of a scene change between consecutive frames of a plurality of frames or a threshold number of received frames of a plurality of frames, each of the plurality of frames including a plurality of pixels, and a first frame of the plurality of frames corresponding to the scene change between consecutive frames or the threshold number of received frames. Further, the display processor 127 can execute 702. Also, each of the plurality of frames can be received in the DPU from a GPU or a CPU.

[0068]

[0074] At 704, the device can downsample the image of the first frame to generate a downsampled image of the first frame, as described with respect to the examples of Figures 1-6, where the downsampled image is generated upon detecting at least one of a scene change between consecutive frames or a threshold number of received frames. For example, the DPU 602 can downsample the image of the first frame to generate a downsampled image of the first frame, where the downsampled image is generated upon detecting at least one of a scene change between consecutive frames or a threshold number of received frames. Further, the display processor 127 can perform 704.

[0069]

[0075] At 706, the device may generate at least one of a saliency map or a depth map based on a downsampled image of a first frame, as described with respect to the examples of FIGS. 1-6 , where the first frame includes a plurality of first pixels and the downsampled image includes a plurality of downsampled pixels. For example, the DPU 602 may generate at least one of a saliency map or a depth map based on a downsampled image of a first frame, where the first frame includes a plurality of first pixels and the downsampled image includes a plurality of downsampled pixels. Further, the display processor 127 may execute 706. At least one of the saliency map, the object segmentation map, or the depth map may be generated using a neural network (NN), a convolutional neural network (CNN), or artificial intelligence (AI) analysis. In some aspects, at least one of the saliency map, the object segmentation map, or the depth map may be based on at least one of saliency information of the first frame, depth information of the first frame, or object information of the first frame.

[0070]

[0076] Additionally, one or more pixels in the downsampled image and one or more pixels in at least one of the saliency map, object segmentation map, or depth map may be analyzed as described with respect to the examples of Figures 1-6. In some cases, statistical analysis may be performed on the downsampled image and at least one of the saliency map, object segmentation map, or depth map.

[0071]

[0077] Furthermore, at least one of the colors of the first group of the plurality of downsampled pixels or the colors of the second group of the plurality of downsampled pixels may be identified based on the downsampled image and at least one of a saliency map, an object segmentation map, or a depth map, as described with respect to the examples of Figures 1-6. In some aspects, the first group of colors may be one or more low-saliency colors or one or more colors including depths within a depth range, and the second group of colors may be one or more high-saliency colors or one or more colors including depths outside the depth range.

[0072]

[0078] In some cases, at least one of a saliency value, an object segmentation classification, or a depth value may correspond to each color of a color space associated with the plurality of frames, and a color mapping function (CMF) for the color space associated with the plurality of frames may be determined based on at least one of the saliency value or the depth value for each color of the color space. Further, the CMF may be a polynomial or a three-dimensional (3D) look-up table (LUT).

[0073]

[0079] At 708, the device may apply a color mapping function (CMF) for a color space associated with the plurality of frames to a plurality of pixels in one or more subsequent frames of the plurality of frames, as described with respect to the examples of Figures 1-6, where the CMF is applied until at least one of a subsequent scene change within the plurality of frames or a threshold number of subsequent received frames of the plurality of frames. For example, the DPU 602 may apply a color mapping function (CMF) for a color space associated with the plurality of frames to a plurality of pixels in one or more subsequent frames of the plurality of frames, where the CMF is applied until at least one of a subsequent scene change within the plurality of frames or a threshold number of subsequent received frames of the plurality of frames. Additionally, the display processor 127 may perform 708.

[0074]

[0080] At 710, the device may adjust at least one of one or more low salience colors or one or more high salience colors, as described with respect to the examples of FIGS. 1-6 , where the depth information of the plurality of downsampled pixels corresponds to one or more colors having depths within a depth range or one or more colors having depths outside the depth range. For example, the DPU 602 may adjust at least one of one or more low salience colors, one or more high salience colors, or depth information of the plurality of downsampled pixels, where the depth information corresponds to one or more colors having depths within a depth range or one or more colors having depths outside the depth range. Further, the display processor 127 may execute 710. After adjusting at least one of the one or more low salience colors, one or more high salience colors, or depth information of the plurality of downsampled pixels, the device may transmit one or more adjusted frames to the display.

[0075]

[0081] In some aspects, the device can decrease the saturation of one or more low salience colors, decrease the luminance of one or more low salience colors, and / or shift the color temperature of one or more low salience colors toward cooler color temperatures. For example, adjusting one or more low salience colors may comprise at least one of decreasing the saturation of one or more low salience colors, decreasing the luminance of one or more low salience colors, or shifting the color temperature of one or more low salience colors toward cooler color temperatures. Furthermore, the device can increase the saturation of one or more high salience colors, increase the luminance of one or more high salience colors, and / or shift the color temperature of one or more high salience colors toward warmer color temperatures. For example, adjusting one or more high salience colors may comprise at least one of increasing the saturation of one or more high salience colors, increasing the luminance of one or more high salience colors, or shifting the color temperature of one or more high salience colors toward warmer color temperatures.

[0076]

[0082] Further, at least one of the one or more low salience colors or the one or more high salience colors may be adjusted based on depth information of the plurality of downsampled pixels. Moreover, the apparatus may adjust one or more pixels associated with at least one of the saliency map, the object segmentation map, or the depth map. For example, adjusting at least one of the one or more low salience colors or the one or more high salience colors may comprise adjusting one or more pixels associated with at least one of the saliency map, the object segmentation map, or the depth map.

[0077]

[0083] In one embodiment, a method or apparatus for display processing is provided. The apparatus may be a DPU, a display or image processor, or some other processor capable of performing display or image processing. In an aspect, the apparatus may be display processor 127 in device 104, or some other hardware in device 104 or another device. The apparatus, for example, display processor 127, includes: means for detecting a scene change between consecutive frames of a plurality of frames or at least one of a threshold number of received frames of the plurality of frames; means for generating at least one of a saliency map or a depth map based on a downsampled image of a first frame, each of the plurality of frames including a plurality of pixels, where a first frame of the plurality of frames corresponds to the scene change between consecutive frames or the threshold number of received frames; means for determining a color mapping function (CMF) for a color space associated with the plurality of frames based on the downsampled image and at least one of the saliency map or the depth map, where the first frame includes a plurality of first pixels and the downsampled image includes a plurality of downsampled pixels; and means for generating a color mapping function (CMF) for one or more of the subsequent frames of the plurality of frames based on the downsampled image and the saliency map or the depth map. means for applying a CMF to a plurality of pixels in a subsequent frame; means for identifying at least one of colors of a first group of the plurality of downsampled pixels or colors of a second group of the plurality of downsampled pixels based on the downsampled image and at least one of a saliency map or a depth map, wherein the CMF is applied until a subsequent scene change in the plurality of frames or at least one of a subsequent threshold number of received frames of the plurality of frames; means for adjusting at least one of one or more low salience colors, one or more high salience colors, or depth information of the plurality of downsampled pixels, wherein the depth information corresponds to one or more colors including a depth within a depth range or one or more colors including a depth outside the depth range;means for increasing the saturation of one or more high salience colors; means for increasing the luminance of one or more high salience colors; means for shifting the color temperature of one or more low salience colors toward a cooler color temperature; means for increasing the luminance of one or more high salience colors; means for shifting the color temperature of one or more high salience colors toward a warmer color temperature; means for increasing depth information corresponding to one or more colors having a depth within a depth range; means for increasing depth information corresponding to one or more colors having a depth outside the depth range; means for decreasing depth information corresponding to one or more colors having a depth within the depth range; means for decreasing depth information corresponding to one or more colors having a depth outside the depth range; may include means for adjusting at least one of a plurality of pixels or one or more pixels in the depth map; means for analyzing one or more pixels in the downsampled image and one or more pixels in at least one of the saliency map or the depth map; means for performing statistical analysis on the downsampled image and at least one of the saliency map or the depth map; and means for downsampling the image of the first frame to generate a downsampled image of the first frame, wherein the downsampled image is generated upon detecting at least one of a scene change between successive frames or a threshold number of received frames.

[0078]

[0084] The subject matter described herein may be implemented to realize one or more benefits or advantages. For example, the described display processing techniques may be used by a DPU, a display processor, or any other processor capable of performing display or image processing to implement the saliency-based color enhancement techniques described herein. This may also be achieved at a low cost compared to other display processing techniques. Moreover, the display processing techniques herein may improve or accelerate data processing or execution. Furthermore, the display processing techniques herein may improve resource or data utilization and / or resource efficiency. Furthermore, aspects of the present disclosure may utilize saliency-based color enhancement techniques to reduce power consumption, improve memory bandwidth, and / or reduce performance overhead in a DPU.

[0079]

[0085] It should be understood that the specific order or hierarchy of blocks in the disclosed processes / flowcharts is a description of an example approach. Based on design preferences, it should be understood that the specific order or hierarchy of blocks in the processes / flowcharts may be rearranged. Additionally, some blocks may be combined or omitted. The accompanying method claims present elements of the various blocks in a sample order and are not limited to the specific order or hierarchy presented.

[0080]

[0086] The previous description is provided to enable any person skilled in the art to practice the various aspects described herein. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects. Accordingly, the claims are not limited to the aspects set forth herein but are to be accorded the full scope consistent with the claim language, and references to elements in the singular do not mean "one and only," unless so expressly stated, but rather "one or more." The word "exemplary" is used herein to mean "serving as an example, instance, or illustration." Any aspect described herein as "exemplary" should not necessarily be construed as preferred or advantageous over other aspects.

[0081]

[0087] Unless otherwise specified, the term "some" refers to one or more, and the term "or" may be interpreted as "and / or" unless the context dictates otherwise. Combinations such as "at least one of A, B, or C," "one or more of A, B, or C," "at least one of A, B, and C," "one or more of A, B, and C," and "A, B, C, or any combination thereof" include any combination of A, B, and / or C and may include multiple As, multiple Bs, or multiple Cs. Specifically, combinations such as "at least one of A, B, or C," "one or more of A, B, or C," "at least one of A, B, and C," "one or more of A, B, and C," and "A, B, C, or any combination thereof" may be A only, B only, C only, A and B, A and C, B and C, or A and B and C, and any such combination may include one or more members of A, B, or C. All structural and functional equivalents to the elements of the various embodiments described throughout this disclosure, known or later known to those skilled in the art, are expressly incorporated herein by reference and encompassed by the claims. Moreover, nothing disclosed herein is made available to the public, regardless of whether such disclosure is expressly recited in the claims. The words "module," "mechanism," "element," "device," and the like may not be substitutes for the word "means." Therefore, no claim element should be construed as a means-plus-function unless the element is expressly recited using the phrase "means for."

[0082]

[0088] In one or more examples, the functions described herein may be implemented in hardware, software, firmware, or any combination thereof. For example, although the term "processing unit" is used throughout this disclosure, such processing unit may be implemented in hardware, software, firmware, or any combination thereof. If any function, processing unit, technique, or other module described herein is implemented in software, the function, processing unit, technique, or other module described herein may be stored on or transmitted over as one or more instructions or code on a computer-readable medium.

[0083]

[0089] According to the present disclosure, the term "or" may be interpreted as "and / or" unless the context dictates otherwise. Furthermore, phrases such as "one or more" or "at least one" may be used with some features disclosed herein but not with other features, and features for which such language is not used may be interpreted to have such implied meaning unless the context dictates otherwise.

[0084]

[0090] In one or more examples, the functions described herein may be implemented in hardware, software, firmware, or any combination thereof. For example, although the term “processing unit” is used throughout this disclosure, such a processing unit may be implemented in hardware, software, firmware, or any combination thereof. If any function, processing unit, technique, or other module described herein is implemented in software, the function, processing unit, technique, or other module described herein may be stored on or transmitted via a computer-readable medium as one or more instructions or code. Computer-readable media may include computer data storage media or communication media, including any medium that facilitates transfer of a computer program from one place to another. In this manner, computer-readable media may generally correspond to (1) tangible computer-readable storage media that are non-transitory, or (2) a communication medium such as a signal or carrier wave. Data storage media may be any available medium that can be accessed by one or more computers or one or more processors to retrieve instructions, code, and / or data structures for implementing the techniques described in this disclosure. By way of example and not limitation, such computer-readable media may comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices. As used herein, disk and disc include compact discs (CDs), laser discs, optical discs, digital versatile discs (DVDs), floppy discs, and Blu-ray discs, where disks typically reproduce data magnetically and discs reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media. A computer program product may include a computer-readable medium.

[0085]

[0091] The code may be executed by one or more processors, such as one or more digital signal processors (DSPs), general-purpose microprocessors, application-specific integrated circuits (ASICs), arithmetic logic units (ALUs), field-programmable logic arrays (FPGAs), or other equivalent integrated or discrete logic circuitry. Accordingly, the term "processor," as used herein, may refer to any of the above structures or any other structure suitable for implementing the techniques described herein. Also, the techniques may be implemented entirely within one or more circuits or logic elements.

[0086]

[0092] The techniques of the present disclosure may be implemented in a wide variety of devices or apparatuses, including wireless handsets, integrated circuits (ICs), or sets of ICs, e.g., chipsets. Various components, modules, or units have been described in this disclosure to highlight functional aspects of devices configured to perform the disclosed techniques, but they do not necessarily require realization by different hardware units. Rather, as described above, the various units may be combined in any hardware unit, or provided by a collection of interoperable hardware units, including one or more processors described above along with appropriate software and / or firmware. Thus, the term "processor" as used herein may refer to any of the above structures or any other structure suitable for implementing the techniques described herein. The techniques may also be implemented entirely within one or more circuits or logic elements.

[0087]

[0093] The following aspects are exemplary only and may be combined with, but not limited to, other aspects or teachings described herein.

[0088]

[0094] Aspect 1 is a method of display processing or image processing, the method including: detecting a scene change between consecutive frames of a plurality of frames or at least one of a threshold number of received frames of the plurality of frames; generating at least one of a saliency map, an object segmentation map, or a depth map based on a downsampled image of a first frame, each of the plurality of frames including a plurality of pixels, where a first frame of the plurality of frames corresponds to the scene change between the consecutive frames or the threshold number of received frames; applying a color mapping function (CMF) for a color space associated with the plurality of frames to a plurality of pixels in one or more subsequent frames of the plurality of frames, where the first frame includes the plurality of first pixels and the downsampled image includes a plurality of downsampled pixels; and applying the CMF to a subsequent scene change within the plurality of frames or at least one of the subsequent threshold number of received frames of the plurality of frames.

[0089]

[0095] Aspect 2 is the method of aspect 1, wherein at least one of the colors of the first group of the plurality of downsampled pixels or the colors of the second group of the plurality of downsampled pixels is identified based on the downsampled image and at least one of a saliency map, an object segmentation map, or a depth map.

[0090]

[0096] Aspect 3 is a method according to any of aspects 1 and 2, wherein the first group of colors is one or more low salience colors or one or more colors including depths within the depth range, and the second group of colors is one or more high salience colors or one or more colors including depths outside the depth range.

[0091]

[0097] Example 4 is the method of any of Examples 1 to 3, further comprising adjusting at least one of the one or more low salience colors or the one or more high salience colors, wherein the depth information of the plurality of downsampled pixels corresponds to one or more colors having depths within the depth range or one or more colors having depths outside the depth range.

[0092]

[0098] Example 5 is a method described in any of Examples 1 to 4, wherein adjusting the one or more low salience colors comprises at least one of decreasing the saturation of the one or more low salience colors, decreasing the brightness of the one or more low salience colors, or shifting the color temperature of the one or more low salience colors toward a cooler color temperature.

[0093]

[0099] Example 6 is a method described in any of Examples 1 to 5, wherein adjusting the one or more high salience colors comprises at least one of increasing the saturation of the one or more high salience colors, increasing the brightness of the one or more high salience colors, or shifting the color temperature of the one or more high salience colors toward a warmer color temperature.

[0094]

[0100] Example 7 is a method according to any of Examples 1 to 6, wherein at least one of the one or more low salience colors or the one or more high salience colors is adjusted based on depth information of the plurality of downsampled pixels.

[0095]

[0101] Example 8 is a method of any of examples 1 to 7, wherein adjusting at least one of the one or more low salience colors or the one or more high salience colors comprises adjusting one or more pixels associated with at least one of a saliency map, an object segmentation map, or a depth map.

[0096]

[0102] Example 9 is a method described in any of Examples 1 to 8, wherein at least one of a saliency value, an object segmentation classification, or a depth value corresponds to each color in a color space associated with the multiple frames, and the CMF is determined based on at least one of the saliency value or the depth value for each color in the color space.

[0097]

[0103] Example 10 is a method according to any of Examples 1 to 9, wherein one or more pixels in the downsampled image and one or more pixels in at least one of a saliency map, an object segmentation map, or a depth map are analyzed.

[0098]

[0104] Example 11 is the method of any of Examples 1 to 10, wherein the statistical analysis is performed on the downsampled image and at least one of the saliency map, the object segmentation map, or the depth map.

[0099]

[0105] Example 12 is a method of any of Examples 1 to 11, wherein at least one of the saliency map, the object segmentation map, or the depth map is based on at least one of the saliency information of the first frame, the depth information of the first frame, or the object information of the first frame.

[0100]

[0106] Example 13 is a method of any of Examples 1 to 12, wherein at least one of the saliency map, the object segmentation map, or the depth map is generated using a neural network (NN), a convolutional neural network (CNN), or an artificial intelligence (AI) analysis.

[0101]

[0107] Example 14 is the method of any of Examples 1 to 13, wherein the CMF is a polynomial or a three-dimensional (3D) look-up table (LUT).

[0102]

[0108] Example 15 is the method of any of Examples 1 to 14, further comprising downsampling the image of the first frame to generate a downsampled image of the first frame, wherein the downsampled image is generated upon detecting at least one of a scene change between consecutive frames or a threshold number of received frames.

[0103]

[0109] Example 16 is the method of any of Examples 1 to 15, wherein each of the plurality of frames is received at a display processing unit (DPU).

[0104]

[0110] Aspect 17 is an apparatus for display processing, including at least one processor coupled to a memory and configured to perform the method of any of aspects 1-16.

[0105]

[0111] An embodiment 18 is an apparatus for display processing, including means for performing the method according to any one of embodiments 1 to 16.

[0106]

[0112] Aspect 19 is a computer-readable medium storing computer-executable code that, when executed by at least one processor, causes the at least one processor to perform a method according to any of aspects 1 to 16. The inventions described in the claims of the present application as originally filed are set forth below. [C1] A display processing method, comprising: detecting at least one of a scene change between consecutive frames of a plurality of frames or a threshold number of received frames of the plurality of frames, each of the plurality of frames including a plurality of pixels, a first frame of the plurality of frames corresponding to the scene change between consecutive frames or the threshold number of received frames; generating at least one of a saliency map, an object segmentation map, or a depth map based on a downsampled image of the first frame, the first frame comprising a plurality of first pixels and the downsampled image comprising a plurality of downsampled pixels; applying a color mapping function (CMF) for a color space associated with the plurality of frames to the plurality of pixels in one or more subsequent frames of the plurality of frames, the CMF being applied until at least one of a subsequent scene change within the plurality of frames or a subsequent threshold number of received frames of the plurality of frames. A method comprising: [C2] The method of [C1], wherein at least one of the colors of the first group of the plurality of downsampled pixels or the colors of the second group of the plurality of downsampled pixels is identified based on the downsampled image and at least one of the saliency map, the object segmentation map, or the depth map. [C3] The method described in [C2], wherein the first group of colors is one or more low salience colors or one or more colors including depths within a depth range, and the second group of colors is one or more high salience colors or one or more colors including depths outside a depth range. [C4] adjusting at least one of the one or more low salience colors or the one or more high salience colors, wherein depth information of the plurality of the downsampled pixels corresponds to the one or more colors with depths within the depth range or the one or more colors with depths outside the depth range; The method according to [C3], further comprising: [C5] adjusting the one or more low salience colors reducing the saturation of said one or more low salience colors; reducing the luminance of said one or more low salience colors; or Shifting the color temperature of said one or more low salience colors towards cooler color temperatures. The method according to [C4], comprising at least one of: [C6] adjusting the one or more high saliency colors increasing the saturation of said one or more high salience colors; increasing the luminance of said one or more high salience colors; or Shifting the color temperature of said one or more high salience colors toward a warmer color temperature. The method according to [C4], comprising at least one of: [C7] The method of [C4], wherein at least one of the one or more low salience colors or the one or more high salience colors is adjusted based on the depth information of the downsampled pixels. [C8] adjusting at least one of the one or more low salience colors or the one or more high salience colors; The method of [C4], comprising adjusting one or more pixels associated with at least one of the saliency map, the object segmentation map, or the depth map. [C9] The method of [C1], wherein at least one of a saliency value, an object segmentation classification, or a depth value corresponds to each color of the color space associated with the plurality of frames, and the CMF is determined based on at least one of the saliency value or the depth value for each color of the color space. [C10] The method of [C1], wherein one or more pixels in the downsampled image and one or more pixels in at least one of the saliency map, the object segmentation map, or the depth map are analyzed. [C11] The method of [C10], wherein a statistical analysis is performed on the downsampled image and at least one of the saliency map, the object segmentation map, or the depth map. [C12] The method of [C1], wherein at least one of the saliency map, the object segmentation map, or the depth map is based on at least one of saliency information of the first frame, depth information of the first frame, or object information of the first frame. [C13] The method of [C1], wherein at least one of the saliency map, the object segmentation map, or the depth map is generated using a neural network (NN), a convolutional neural network (CNN), or artificial intelligence (AI) analysis. [C14] The method according to [C1], wherein the CMF is a polynomial or a three-dimensional (3D) look-up table (LUT). [C15] downsampling the image of the first frame to generate the downsampled image of the first frame, wherein the downsampled image is generated upon detecting at least one of the scene change between consecutive frames or the threshold number of received frames. The method according to [C1], further comprising: [C16] The method of [C1], wherein each of the plurality of frames is received at a display processing unit (DPU). [C17] An apparatus for display processing, comprising: Memory and coupled to the memory; detecting at least one of a scene change between consecutive frames of a plurality of frames or a threshold number of received frames of the plurality of frames, each of the plurality of frames including a plurality of pixels, a first frame of the plurality of frames corresponding to the scene change between consecutive frames or the threshold number of received frames; generating at least one of a saliency map, an object segmentation map, or a depth map based on a downsampled image of the first frame, the first frame comprising a plurality of first pixels and the downsampled image comprising a plurality of downsampled pixels; applying a color mapping function (CMF) for a color space associated with the plurality of frames to the plurality of pixels in one or more subsequent frames of the plurality of frames, the CMF being applied until at least one of a subsequent scene change within the plurality of frames or a subsequent threshold number of received frames of the plurality of frames. at least one processor configured to perform An apparatus comprising: [C18] The apparatus of [C17], wherein at least one of the colors of the first group of the plurality of downsampled pixels or the colors of the second group of the plurality of downsampled pixels is identified based on the downsampled image and at least one of the saliency map, the object segmentation map, or the depth map. [C19] The device described in [C18], wherein the first group of colors is one or more low salience colors or one or more colors including depths within a depth range, and the second group of colors is one or more high salience colors or one or more colors including depths outside a depth range. [C20] the at least one processor: adjusting at least one of the one or more low salience colors or the one or more high salience colors, wherein depth information of the plurality of the downsampled pixels corresponds to the one or more colors with depths within the depth range or the one or more colors with depths outside the depth range; The apparatus according to [C19], further configured to: [C21] adjusting the one or more low salience colors reducing the saturation of said one or more low salience colors; reducing the luminance of said one or more low salience colors; or Shifting the color temperature of said one or more low salience colors towards cooler color temperatures. The apparatus of [C20], comprising the at least one processor further configured to perform at least one of the following: [C22] adjusting the one or more high saliency colors increasing the saturation of said one or more high salience colors; increasing the luminance of said one or more high salience colors; or Shifting the color temperature of said one or more high salience colors toward a warmer color temperature. The apparatus of [C20], comprising the at least one processor further configured to perform at least one of the following: [C23] The apparatus of [C20], wherein at least one of the one or more low salience colors or the one or more high salience colors is adjusted based on the depth information of the downsampled pixels. [C24] adjusting at least one of the one or more low salience colors or the one or more high salience colors; adjusting one or more pixels associated with at least one of the saliency map, the object segmentation map, or the depth map; The apparatus of [C20], comprising the at least one processor further configured to: [C25] The apparatus described in [C17], wherein at least one of a saliency value, an object segmentation classification, or a depth value corresponds to each color of the color space associated with the plurality of frames, and the CMF is determined based on at least one of the saliency value or the depth value for each color of the color space. [C26] The apparatus of [C17], wherein one or more pixels in the downsampled image and one or more pixels in at least one of the saliency map, the object segmentation map, or the depth map are analyzed. [C27] The apparatus of [C26], wherein a statistical analysis is performed on the downsampled image and at least one of the saliency map, the object segmentation map, or the depth map. [C28] The apparatus of [C26], wherein at least one of the saliency map, the object segmentation map, or the depth map is based on at least one of saliency information of the first frame, depth information of the first frame, or object information of the first frame. [C29] The apparatus of [C17], wherein at least one of the saliency map, the object segmentation map, or the depth map is generated using a neural network (NN), a convolutional neural network (CNN), or artificial intelligence (AI) analysis. [C30] The apparatus according to [C17], wherein the CMF is a polynomial or a three-dimensional (3D) look-up table (LUT). [C31] the at least one processor: downsampling the image of the first frame to generate the downsampled image of the first frame, wherein the downsampled image is generated upon detecting at least one of the scene change between consecutive frames or the threshold number of received frames. The apparatus according to [C17], further configured to: [C32] The apparatus of [C17], wherein each of the plurality of frames is received at a display processing unit (DPU). [C33] An apparatus for display processing, comprising: means for detecting at least one of a scene change between successive frames of a plurality of frames or a threshold number of received frames of said plurality of frames, each of said plurality of frames comprising a plurality of pixels, a first frame of said plurality of frames corresponding to said scene change between successive frames or said threshold number of received frames; means for generating at least one of a saliency map, an object segmentation map, or a depth map based on a downsampled image of the first frame, the first frame comprising a plurality of first pixels, and the downsampled image comprising a plurality of downsampled pixels; means for applying a color mapping function (CMF) for a color space associated with the plurality of frames to the plurality of pixels in one or more subsequent frames of the plurality of frames, the CMF being applied until at least one of a subsequent scene change within the plurality of frames or a subsequent threshold number of received frames of the plurality of frames; An apparatus comprising: [C34] 1. A computer-readable medium storing computer-executable code for a display process, the code, when executed by a processor, detecting at least one of a scene change between consecutive frames of a plurality of frames or a threshold number of received frames of the plurality of frames, each of the plurality of frames including a plurality of pixels, a first frame of the plurality of frames corresponding to the scene change between consecutive frames or the threshold number of received frames; generating at least one of a saliency map, an object segmentation map, or a depth map based on a downsampled image of the first frame, the first frame comprising a plurality of first pixels and the downsampled image comprising a plurality of downsampled pixels; applying a color mapping function (CMF) for a color space associated with the plurality of frames to the plurality of pixels in one or more subsequent frames of the plurality of frames, the CMF being applied until at least one of a subsequent scene change within the plurality of frames or a subsequent threshold number of received frames of the plurality of frames. a computer-readable medium for causing the processor to execute the

Claims

1. A display processing method, comprising: detecting at least one of a scene change between consecutive frames of a plurality of frames or a threshold number of received frames of the plurality of frames, each of the plurality of frames including a plurality of pixels, a first frame of the plurality of frames corresponding to the scene change between consecutive frames or the threshold number of received frames; generating at least one of a saliency map or a depth map based on a downsampled image of the first frame, the first frame including a plurality of first pixels, and the downsampled image including a plurality of downsampled pixels; applying a color mapping function (CMF) for a color space associated with the plurality of frames to the plurality of pixels in one or more subsequent frames of the plurality of frames, the CMF being applied until at least one of a subsequent scene change within the plurality of frames or a subsequent threshold number of received frames of the plurality of frames. adjusting at least one of one or more low salience colors of the plurality of downsampled pixels, one or more high salience colors of the plurality of downsampled pixels, or depth information of the plurality of downsampled pixels; A method comprising:

2. 2. The method of claim 1 , wherein at least one of the colors of the first group of the plurality of downsampled pixels or the colors of the second group of the plurality of downsampled pixels is identified based on the downsampled image and at least one of the saliency map or the depth map.

3. 3. The method of claim 2, wherein the first group of colors is one or more high salience colors or one or more colors that include depths within a depth range associated with high salience, and the second group of colors is one or more low salience colors or one or more colors that include depths outside the depth range.

4. 4. The method of claim 3, wherein depth information of the plurality of the downsampled pixels corresponds to the one or more colors with a depth within the depth range or the one or more colors with a depth outside the depth range.

5. adjusting the one or more low salience colors reducing the saturation of said one or more low salience colors; reducing the luminance of said one or more low salience colors; or Shifting the color temperature of said one or more low salience colors towards cooler color temperatures. The method of claim 1 , comprising at least one of:

6. adjusting the one or more high saliency colors increasing the saturation of said one or more high salience colors; increasing the luminance of said one or more high salience colors; or Shifting the color temperature of the one or more high salience colors toward warmer color temperatures. The method of claim 1 , comprising at least one of:

7. The method of claim 1 , wherein at least one of the one or more low salience colors or the one or more high salience colors is adjusted based on the depth information of the downsampled pixels.

8. adjusting at least one of the one or more low salience colors or the one or more high salience colors; The method of claim 1 , comprising adjusting one or more pixels associated with at least one of the saliency map or the depth map.

9. 2. The method of claim 1 , wherein at least one of a saliency value, an object segmentation classification, or a depth value corresponds to each color in the color space associated with the plurality of frames, and the CMF is determined based on at least one of the saliency value or the depth value for each color in the color space.

10. The method of claim 1 , wherein one or more pixels in the downsampled image and one or more pixels in at least one of the saliency map or the depth map are analyzed.

11. The method of claim 10 , wherein a statistical analysis is performed on the downsampled image and at least one of the saliency map or the depth map.

12. 2. The method of claim 1 , wherein at least one of the saliency map or the depth map is based on at least one of saliency information of the first frame, depth information of the first frame, or object information of the first frame.

13. 10. The method of claim 1, wherein at least one of the saliency map or the depth map is generated using a neural network (NN), a convolutional neural network (CNN), or an artificial intelligence (AI) analysis.

14. The method of claim 1 , wherein the CMF is a polynomial or a three-dimensional (3D) look-up table (LUT).

15. downsampling the image of the first frame to generate the downsampled image of the first frame, wherein the downsampled image is generated upon detecting at least one of the scene change between successive frames or the threshold number of received frames. The method of claim 1 further comprising:

16. The method of claim 1 , wherein each of the plurality of frames is received at a display processing unit (DPU).

17. An apparatus for display processing, comprising: Memory and coupled to the memory; detecting at least one of a scene change between consecutive frames of a plurality of frames or a threshold number of received frames of the plurality of frames, each of the plurality of frames including a plurality of pixels, a first frame of the plurality of frames corresponding to the scene change between consecutive frames or the threshold number of received frames; generating at least one of a saliency map or a depth map based on a downsampled image of the first frame, the first frame including a plurality of first pixels, and the downsampled image including a plurality of downsampled pixels; applying a color mapping function (CMF) for a color space associated with the plurality of frames to the plurality of pixels in one or more subsequent frames of the plurality of frames, the CMF being applied until at least one of a subsequent scene change within the plurality of frames or a subsequent threshold number of received frames of the plurality of frames. adjusting at least one of one or more low salience colors of the plurality of downsampled pixels, one or more high salience colors of the plurality of downsampled pixels, or depth information of the plurality of downsampled pixels; at least one processor configured to perform An apparatus comprising:

18. 18. The apparatus of claim 17, wherein at least one of the colors of the first group of downsampled pixels or the colors of the second group of downsampled pixels is identified based on the downsampled image and at least one of the saliency map or the depth map.

19. 20. The device of claim 18, wherein the first group of colors is one or more high salience colors or one or more colors that include depths within a depth range associated with high salience, and the second group of colors is one or more low salience colors or one or more colors that include depths outside the depth range.

20. 20. The apparatus of claim 19, wherein depth information of the plurality of the downsampled pixels corresponds to the one or more colors with a depth within the depth range or the one or more colors with a depth outside the depth range.

21. adjusting the one or more low salience colors reducing the saturation of said one or more low salience colors; reducing the luminance of said one or more low salience colors; or Shifting the color temperature of said one or more low salience colors towards cooler color temperatures.

20. The apparatus of claim 17, comprising the at least one processor further configured to perform at least one of:

22. adjusting the one or more high saliency colors increasing the saturation of said one or more high salience colors; increasing the luminance of said one or more high salience colors; or Shifting the color temperature of the one or more high salience colors toward warmer color temperatures.

20. The apparatus of claim 17, comprising the at least one processor further configured to perform at least one of:

23. 20. The apparatus of claim 17, wherein at least one of the one or more low salience colors or the one or more high salience colors is adjusted based on the depth information of the downsampled pixels.

24. adjusting at least one of the one or more low salience colors or the one or more high salience colors; Adjusting one or more pixels associated with at least one of the saliency map or the depth map.

20. The apparatus of claim 17, comprising the at least one processor further configured to:

25. 20. The apparatus of claim 17, wherein at least one of a saliency value, an object segmentation classification, or a depth value corresponds to each color in the color space associated with the plurality of frames, and the CMF is determined based on at least one of the saliency value or the depth value for each color in the color space.

26. The apparatus of claim 17 , wherein one or more pixels in the downsampled image and one or more pixels in at least one of the saliency map or the depth map are analyzed.

27. The apparatus of claim 26 , wherein a statistical analysis is performed on the downsampled image and at least one of the saliency map or the depth map.

28. 20. The apparatus of claim 17, wherein at least one of the saliency map or the depth map is based on at least one of saliency information of the first frame, depth information of the first frame, or object information of the first frame.

29. 20. The apparatus of claim 17, wherein at least one of the saliency map or the depth map is generated using a neural network (NN), a convolutional neural network (CNN), or an artificial intelligence (AI) analysis.

30. 18. The apparatus of claim 17, wherein the CMF is a polynomial or a three-dimensional (3D) look-up table (LUT).

31. the at least one processor: downsampling the image of the first frame to generate the downsampled image of the first frame, wherein the downsampled image is generated upon detecting at least one of the scene change between successive frames or the threshold number of received frames.

20. The apparatus of claim 17, further configured to:

32. 20. The apparatus of claim 17, wherein each of the plurality of frames is received at a display processing unit (DPU).

33. An apparatus for display processing, comprising: means for detecting at least one of a scene change between successive frames of a plurality of frames or a threshold number of received frames of said plurality of frames, each of said plurality of frames comprising a plurality of pixels, a first frame of said plurality of frames corresponding to said scene change between successive frames or said threshold number of received frames; means for generating at least one of a saliency map or a depth map based on a downsampled image of the first frame, the first frame comprising a plurality of first pixels, and the downsampled image comprising a plurality of downsampled pixels; means for applying a color mapping function (CMF) for a color space associated with the plurality of frames to the plurality of pixels in one or more subsequent frames of the plurality of frames, the CMF being applied until at least one of a subsequent scene change within the plurality of frames or a subsequent threshold number of received frames of the plurality of frames; means for adjusting at least one of one or more low salience colors of the plurality of downsampled pixels, one or more high salience colors of the plurality of downsampled pixels, or depth information of the plurality of downsampled pixels; An apparatus comprising:

34. 1. A computer-readable medium storing computer-executable code for a display process, the code, when executed by a processor, detecting at least one of a scene change between consecutive frames of a plurality of frames or a threshold number of received frames of the plurality of frames, each of the plurality of frames including a plurality of pixels, a first frame of the plurality of frames corresponding to the scene change between consecutive frames or the threshold number of received frames; generating at least one of a saliency map or a depth map based on a downsampled image of the first frame, the first frame including a plurality of first pixels, and the downsampled image including a plurality of downsampled pixels; applying a color mapping function (CMF) for a color space associated with the plurality of frames to the plurality of pixels in one or more subsequent frames of the plurality of frames, the CMF being applied until at least one of a subsequent scene change within the plurality of frames or a subsequent threshold number of received frames of the plurality of frames. adjusting at least one of one or more low salience colors of the plurality of downsampled pixels, one or more high salience colors of the plurality of downsampled pixels, or depth information of the plurality of downsampled pixels; a computer-readable medium for causing the processor to execute the

Images