Energy-aware neural network post filter

Abstract

Specific syntax elements define an energy reduction ratio for an energy reduction neural network post-processing filter. An encoded video bitstream carries such syntax elements from an encoding device to a decoding device, thus allowing the encoding device to specify an amount of energy reduction to be achieved and the decoding device to apply the energy reduction neural network post-processing filter for reducing the energy consumption when displaying the decoded video. Additional syntax elements specify a minimum quality target and an associated quality metric.

Description

[0001] ENERGY- AWARE NEURAL NETWORK POST FILTER

[0002] CROSS REFERENCE TO RELATED APPLICATIONS

[0003] This application claims the priority to European Application No. 24305320.4 filed 1stof March 2024, which is incorporated herein by reference in their entirety.

[0004] TECHNICAL FIELD

[0005] At least one of the present embodiments generally relates to a video encoding and decoding method and device, and more particularly to syntax elements defining an energy reduction ratio for an energy reduction neural network post-processing filter.

[0006] BACKGROUND ART

[0007] To achieve high compression efficiency, image and video coding schemes usually employ prediction and transform to leverage spatial and temporal redundancy in the video content. Generally, intra or inter prediction is used to exploit the intra or inter frame correlation, then the differences between the original image block and the predicted image block, often denoted as prediction errors or prediction residuals, are transformed, quantized and entropy coded. During encoding the original image block is usually parti honed / split into sub-blocks for example using quad-tree partitioning. To reconstruct the video, the compressed data is decoded by inverse processes corresponding to the prediction, transform, quantization and entropy coding.

[0008] Reducing energy consumption of electronic devices has become a requirement not only for manufacturers of electronic devices but also to limit, as much as possible, the environmental impact and to contribute to the emergence of a sustainable display industry. The increase in display resolution from SD to HD, then to 4K and soon to 8K and beyond, as well as the introduction of high dynamic range imaging, has brought about a corresponding increase in energy requirements of display devices. This is not consistent with the global need to reduce energy consumption knowing that a huge number of devices has a display (i.e. , TV, Mobile phones, tablets, etc.). Indeed, displays are the most important source of energy consumption, for consumer electronic devices, either battery-powered (e.g., smartphones, tablets, headmounted displays, car display screens) or not (e.g., television sets, advertisement display panels). Different display technologies have been developed in the recent years. Although modem displays consume energy in a more controllable and efficient manner than older displays, they remain the most important source of energy consumption in a video chain. Organic Light Emitting Diode (OLED) is one example of display technology that is finding increasingly widespread use because of numerous advantages compared to former technologies such as Thin-Film Transistor Liquid Crystal Displays (TFT-LCDs). Rather than using a uniform backlight, OLED displays, as well as mini LEDS, are composed of individual directly emissive image pixels. OLEDs power consumption is therefore highly correlated to the image content and the power consumption for a given input image can be estimated by considering the values of the displayed image pixels. It is therefore interesting to elaborate energy-aware images or videos, i.e., images or videos that will need less energy when displayed, notably on consumer electronics OLED displays.

[0009] An example of such an elaboration is proposed in European patent applications EP22306719.0 and EP23305185.3 that disclose techniques to generate energy-aware images from original images by using a so-called dimming map that will decrease pixel values of an image to reduce the energy needed for displaying them. The dimming map is designed to ensure good properties such as smoothness and scalability. Another example if proposed in European patent application EP23305294.3 that introduce the notion of self-contained invertible energy- aware image. Such kind of energy-aware image can be obtained using an invertible energy- aware network in a forward manner to map an original image into an energy-aware image. The neural-network based solution of EP23305294.3 allows to reconstruct the exact original image by using the same invertible energy-aware network in a backward manner on an energy-aware image and without significant losses.

[0010] SUMMARY

[0011] According to a first aspect of at least one embodiment, a method comprises obtaining video data, determining energy reduction network post-processing filter characteristics, determining a supplemental enhancement information message comprising a target energy reduction ratio for an energy reduction network post-processing filter, encode video data, generate bitstream comprising encoded video and supplemental enhancement information message, and providing the bitstream.

[0012] According to a second aspect of at least one embodiment, a method comprises obtaining a bitstream comprising encoded video data and a supplemental enhancement information message comprising a target energy reduction ratio for an energy reduction network postprocessing filter, decoding video, applying to the decoded video the energy reduction neural network post-processing filter with the target energy reduction ratio and providing energy- reduced video.

[0013] According to a third aspect of at least one embodiment, an apparatus comprises one or more processors configured to obtain video data, determining energy reduction network postprocessing filter characteristics, determining a supplemental enhancement information message comprising a target energy reduction ratio for an energy reduction network postprocessing filter, encode video data, generate bitstream comprising encoded video and supplemental enhancement information message, and providing the bitstream.

[0014] According to a fourth aspect of at least one embodiment, an apparatus comprises one or more processors configured to obtain a bitstream comprising encoded video data and a supplemental enhancement information message comprising a target energy reduction ratio for an energy reduction network post-processing filter, decoding video, apply to the decoded video the energy reduction neural network post-processing filter with the target energy reduction ratio, and provide energy-reduced video.

[0015] One or more of the present embodiments also provide a computer readable storage medium having stored thereon instructions according to at least part of any of the methods described above. One or more embodiments also provide a computer readable storage medium having stored thereon a bitstream generated according to the encoding methods described above. One or more embodiments also provide a computer program product including instructions for performing at least part of any of the methods described above.

[0016] BRIEF SUMMARY OF THE DRAWINGS

[0017] Figure 1 illustrates a block diagram of an example of a system in which various aspects and embodiments are implemented.

[0018] Figure 2 describes an example of a context in which following embodiments can be implemented.

[0019] Figure 3 illustrates a block diagram of an example of video encoder.

[0020] Figure 4 illustrates a block diagram of an example of video decoder. Figure 5 illustrates an example of partitioning undergone by an image of an original video sequence.

[0021] Figure 6 illustrates a block diagram of an example of video coding system according to embodiments.

[0022] Figure 7 illustrates an example process for encoding a bitstream comprising an energy reduction NNPFC SEI message according to embodiments.

[0023] Figure 8 illustrates an example process for decoding a bitstream comprising an energy reduction NNPFC SEI message according to embodiments.

[0024] DETAILED DESCRIPTION

[0025] Various embodiments relate to specific syntax elements that define a target energy reduction ratio for an energy reduction neural network post-processing filter. An encoded video bitstream carry such syntax elements from an encoding device to a decoding device, thus allowing the encoding device to specify an amount of energy reduction to be achieved and the decoding device to apply the energy reduction neural network post-processing filter for reducing the energy consumption when displaying the decoded video. Additional syntax elements specify a minimum quality target and an associated quality metric.

[0026] The present aspects, although describing principles in the context of VVC (Versatile Video Coding) or HEVC (High Efficiency Video Coding) specifications, are not limited to these video coding standards, and can be applied, for example, to other standards and recommendations and extensions of any such standards and recommendations (including VVC and HEVC). Unless indicated otherwise, or technically precluded, the aspects described in this application can be used individually or in combination.

[0027] Figure 1 illustrates a block diagram of an example of a system in which various aspects and embodiments are implemented. System 1000 can be embodied as a device or apparatus including the various components described below and is configured to perform one or more of the aspects described in this document. Examples of such devices include, but are not limited to, various electronic devices such as computers, smartphones, tablets, digital multimedia set top boxes, digital television receivers, personal video recording systems, connected home appliances, vehicle entertainment systems, vehicle control systems, drones, video surveillance cameras, and more generally data servers. Elements of system 1000, singly or in combination, can be embodied in a single integrated circuit (IC), multiple Ics, and / or discrete components. For example, in at least one embodiment, the processing and encoder / decoder elements of system 1000 are distributed across multiple Ics and / or discrete components. In various embodiments, the system 1000 is communicatively coupled to one or more other systems, or other electronic devices, via, for example, a communications bus or through dedicated input and / or output ports. In various embodiments, the system 1000 is configured to implement one or more of the aspects described in this document.

[0028] The system 1000 includes at least one processor 1010 configured to execute instructions loaded therein for implementing, for example, the various aspects described in this document. Processor 1010 can include embedded memory, input output interface, and various other circuitries as known in the art. The system 1000 includes at least one memory 1020 (e.g., a volatile memory device, and / or a non-volatile memory device). System 1000 includes a storage device 1040, which can include non-volatile memory and / or volatile memory, including, but not limited to, Electrically Erasable Programmable Read-Only Memory (EEPROM), Read- Only Memory (ROM), Programmable Read-Only Memory (PROM), Random Access Memory (RAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), flash-based memory, magnetic disk drive, solid-state drive (SSD), and / or optical disk drive. The storage device 1040 can include an internal storage device, an attached storage device (including detachable and non-detachable storage devices), and / or a network accessible storage device (a.k.a. cloud storage), as non-limiting examples.

[0029] System 1000 includes an encoder / decoder module 1030 configured, for example, to process data to provide an encoded video or decoded video, and the encoder / decoder module 1030 can include its own processor and memory. The encoder / decoder module 1030 represents module(s) that can be included in a device to perform the encoding and / or decoding functions described further below. As is known, a device can include one or both of the encoding and decoding modules. Additionally, encoder / decoder module 1030 can be implemented as a separate element of system 1000 or can be incorporated within processor 1010 as a combination of hardware and software as known to those skilled in the art.

[0030] Program code to be loaded onto processor 1010 or encoder / decoder 1030 to perform one or more of the aspects described in this document can be stored in storage device 1040 and subsequently loaded onto memory 1020 for execution by processor 1010. In accordance with various embodiments, one or more of processor 1010, memory 1020, storage device 1040, and encoder / decoder module 1030 can store one or more of various items during the performance of the processes described in this document. Such stored items can include, but are not limited to, the input video, the decoded video or portions of the decoded video, the bitstream, matrices, variables, and intermediate or final results from the processing of equations, formulas, operations, and operational logic.

[0031] In some embodiments, memory inside of the processor 1010 and / or the encoder / decoder module 1030 is used to store instructions and to provide working memory for processing that is needed during encoding or decoding. In other embodiments, however, a memory external to the processing device (for example, the processing device can be either the processor 1010 or the encoder / decoder module 1030) is used for one or more of these functions. The external memory can be the memory 1020 and / or the storage device 1040, for example, a dynamic volatile memory and / or anon-volatile flash memory. In several embodiments, an external nonvolatile flash memory is used to store the operating system of, for example, a television. In at least one embodiment, a fast external dynamic volatile memory such as a RAM is used as working memory for video coding and decoding operations, such as for MPEG-2 (MPEG refers to the Moving Picture Experts Group, MPEG-2 is also referred to as ISO / IEC 13818, and 13818-1 is also known as H.222, and 13818-2 is also known as H.262), HEVC (HEVC refers to High Efficiency Video Coding, also known as H.265), or VVC (Versatile Video Coding, also known as H.266).

[0032] The input to the elements of system 1000 can be provided through various input devices as indicated in block 1130. Such input devices include, but are not limited to, a radio frequency (RF) portion that receives an RF signal transmitted, for example, over the air by a broadcaster, a Component (COMP) input terminal (or a set of COMP input terminals), a Universal Serial Bus (USB) input terminal, and / or a High-Definition Multimedia Interface (HDMI) input terminal. Other examples include composite video.

[0033] In various embodiments, the input devices of block 1130 have associated respective input processing elements as known in the art. For example, the RF portion can be associated with elements suitable for selecting a desired frequency (also referred to as selecting a signal, or band-limiting a signal to a band of frequencies), down converting the selected signal, bandlimiting again to a narrower band of frequencies to select (for example) a signal frequency band which can be referred to as a channel in certain embodiments, demodulating the down converted and band-limited signal, performing error correction, and demultiplexing to select the desired stream of data packets. The RF portion of various embodiments includes one or more elements to perform these functions, for example, frequency selectors, signal selectors, band-limiters, channel selectors, filters, downconverters, demodulators, error correctors, and demultiplexers. The RF portion can include a tuner that performs various of these functions, including, for example, down converting the received signal to a lower frequency (for example, an intermediate frequency or a near-baseband frequency) or to baseband. In one set-top box embodiment, the RF portion and its associated input processing element receives an RF signal transmitted over a wired (for example, cable) medium, and performs frequency selection by filtering, down converting, and filtering again to a desired frequency band. Various embodiments rearrange the order of the above-described (and other) elements, remove some of these elements, and / or add other elements performing similar or different functions. Adding elements can include inserting elements in between existing elements, such as, for example, inserting amplifiers and an analog-to-digital converter. In various embodiments, the RF portion includes an antenna. The RF portion may comply with standard specifications such as those published by Digital Video Broadcasting (DVB), Advanced Television Systems Committee (ATSC), Association of Radio Industries and Businesses (ARIB) or others.

[0034] Additionally, the USB and / or HDMI terminals can include respective interface processors for connecting system 1000 to other electronic devices across USB and / or HDMI connections. It is to be understood that various aspects of input processing, for example, Reed- Solomon error correction, can be implemented, for example, within a separate input processing IC or within processor 1010 as necessary. Similarly, aspects of USB or HDMI interface processing can be implemented within separate interface Ics or within processor 1010 as necessary. The demodulated, error corrected, and demultiplexed stream is provided to various processing elements, including, for example, processor 1010, and encoder / decoder 1030 operating in combination with the memory and storage elements to process the data stream as necessary for presentation on an output device.

[0035] Various elements of system 1000 can be provided within an integrated housing, Within the integrated housing, the various elements can be interconnected and transmit data therebetween using suitable connection arrangement 1140, for example, an internal bus as known in the art, including the Inter-IC (I2C) bus, wiring, and printed circuit boards.

[0036] The system 1000 includes communication interface 1050 that enables communication with other devices via communication channel 1060. The communication interface 1050 can include, but is not limited to, a transceiver configured to transmit and to receive data over communication channel 1060. The communication interface 1050 can include, but is not limited to, a modem or network card and the communication channel 1060 can be implemented, for example, within a wired and / or a wireless medium.

[0037] Data is streamed, or otherwise provided, to the system 1000, in various embodiments, using a wireless network such as a Wi-Fi network, for example IEEE 802.11 (IEEE refers to the Institute of Electrical and Electronics Engineers). The Wi-Fi signal of these embodiments is received over the communications channel 1060 and the communications interface 1050 which are adapted for Wi-Fi communications. The communications channel 1060 of these embodiments is typically connected to an access point or router that provides access to external networks including the Internet for allowing streaming applications and other over-the-top communications. Other embodiments provide streamed data to the system 1000 using a set- top box that delivers the data over the HDMI connection of the input block 1130. Still other embodiments provide streamed data to the system 1000 using the RF connection of the input block 1130. As indicated above, various embodiments provide data in a non-streaming manner. Additionally, various embodiments use wireless networks other than Wi-Fi, for example a cellular network or a Bluetooth network.

[0038] The system 1000 can provide an output signal to various output devices, including a display 1100, speakers 1110, and other peripheral devices 1120. The display 1100 of various embodiments includes one or more of, for example, a touchscreen display, an organic lightemitting diode (OLED) display, a curved display, and / or a foldable display. The display 1100 can be for a television, a tablet, a laptop, a cell phone (mobile phone), or other device. The display 1100 can also be integrated with other components (for example, as in a smart phone), or separate (for example, an external monitor for a laptop). The other peripheral devices 1120 include, in various examples of embodiments, one or more of a stand-alone digital video disc (or digital versatile disc) (DVR, for both terms), a disk player, a stereo system, and / or a lighting system. Various embodiments use one or more peripheral devices 1120 that provide a function based on the output of the system 1000. For example, a disk player performs the function of playing the output of the system 1000.

[0039] In various embodiments, control signals are communicated between the system 1000 and the display 1100, speakers 1110, or other peripheral devices 1120 using signaling such as AV. Link, Consumer Electronics Control (CEC), or other communications protocols that enable device-to-device control with or without user intervention. The output devices can be communicatively coupled to system 1000 via dedicated connections through respective interfaces 1070, 1080, and 1090. Alternatively, the output devices can be connected to system 1000 using the communications channel 1060 via the communications interface 1050. The display 1100 and speakers 1110 can be integrated in a single unit with the other components of system 1000 in an electronic device such as, for example, a television. In various embodiments, the display interface 1070 includes a display driver, such as, for example, a timing controller chip.

[0040] The display 1100 and speaker 1110 can alternatively be separate from one or more of the other components, for example, if the RF portion of input 1130 is part of a separate set-top box. In various embodiments in which the display 1100 and speakers 1110 are external components, the output signal can be provided via dedicated output connections, including, for example, HDMI ports, USB ports, or COMP outputs.

[0041] The embodiments can be carried out by computer software implemented by the processor 1010 or by hardware, or by a combination of hardware and software. As a nonlimiting example, the embodiments can be implemented by one or more integrated circuits. The memory 1020 can be of any type appropriate to the technical environment and can be implemented using any appropriate data storage technology, such as optical memory devices, magnetic memory devices, semiconductor-based memory devices, fixed memory, and removable memory, as non-limiting examples. The processor 1010 can be of any type appropriate to the technical environment, and can encompass one or more of microprocessors, general purpose computers, special purpose computers, and processors based on a multi-core architecture, as non-limiting examples.

[0042] Figure 2 describes an example of a context in which following embodiments can be implemented. In this context 200, a system 210 transmits a video stream to a system 230 using a communication channel 220. Examples of system 210 comprise a camera, a storage device, a computer, a drone, a video surveillance camera, a server or any device capable of delivering a video stream. The video stream is either encoded and transmitted by the system 210 or received and / or stored by the system 210 and then transmitted. The communication channel 220 is a wired (for example Internet, Ethernet, Cable network) or a wireless (for example WiFi, 3G, 4G or 5G, satellite TV, terrestrial TV) network link. The system 230 receives and decodes the video stream to generate a sequence of decoded pictures. An example of system 230 is a set top box. The obtained sequence of decoded pictures is then transmitted to a display system 250 using a communication channel 240, that could be a wired or wireless network as introduced above. The display system 250 then displays said pictures. An example of display system 250 is a television or display monitor.

[0043] In an embodiment, the system 230 and the display system 250 are comprised in a single device, thus combining the reception, decoding and display of the video stream. Examples of such device are a television, a computer, a tablet, a smartphone, a head-mounted display, a vehicle entertainment system, a medical device.

[0044] Figure 3 illustrates a block diagram of an example of video encoder. Variations of this encoder 300 are contemplated, but the encoder 300 is described below for purposes of clarity without describing all expected variations. Before being encoded, the video sequence may go through pre-encoding processing 301, for example, applying a color transform to the input color picture (e.g., conversion from RGB 4:4:4 to YcbCr 4:2:0), or performing a remapping of the input picture components in order to get a signal distribution more resilient to compression (for instance using a histogram equalization of one of the color components). Metadata can be associated with the pre-processing and attached to the bitstream, for example in the form of supplemental enhancement information (SEI) messages, for the standards that include such mechanism.

[0045] In the encoder, a picture is encoded by the encoder elements as described below. The picture to be encoded is partitioned (302), for example as further described in figure 5, and processed in units such as coding units. Each unit is encoded using, for example, either an intra or inter mode. When a unit is encoded in an intra mode, it performs intra prediction (360). In an inter mode, motion estimation (375) and compensation (370) are performed. The encoder decides (305) which one of the intra mode or inter mode to use for encoding the unit, and indicates the intra / inter decision by, for example, a prediction mode flag. Prediction residuals are calculated, for example, by subtracting (320) the predicted block from the original image block. The prediction residuals are then transformed (325) and quantized (330). The quantized transform coefficients, as well as motion vectors and other syntax elements, are entropy coded (345) to output a bitstream. The encoder can skip the transform and apply quantization directly to the non-transformed residual signal. The encoder can bypass both transform and quantization, i.e., the residual is coded directly without the application of the transform or quantization processes.

[0046] The encoder decodes an encoded block to provide a reference for further predictions. The quantized transform coefficients are de-quantized (340) and inverse transformed (350) to decode prediction residuals. Combining (355) the decoded prediction residuals and the predicted block, an image block is reconstructed. In-loop filters (365) are applied to the reconstructed picture to perform, for example, deblocking / SAO (Sample Adaptive Offset), Adaptive Loop-Filter (ALF) filtering to reduce encoding artifacts. The filtered image is stored at a reference picture buffer (380) for further use.

[0047] The encoder also generally performs video decoding as part of encoding video data.

[0048] Figure 4 illustrates a block diagram of an example of video decoder. In the decoder 400, a bitstream is decoded by the decoder elements as described below. Video decoder 400 generally performs a decoding pass reciprocal to the encoding pass as described in previous figure. The input of the decoder includes a video bitstream, which can be generated by video encoder 300 of figure 3. The bitstream is first entropy decoded (430) to obtain transform coefficients, motion vectors, and other coded information. The picture partition information indicates how the picture is partitioned. The decoder may therefore divide (435) the picture according to the decoded picture partitioning information. The transform coefficients are de-quantized (440) and inverse transformed (450) to decode the prediction residuals. Combining (455) the decoded prediction residuals and the predicted block, an image block is reconstructed. The predicted block can be obtained (470) from intra prediction (460) or motion-compensated prediction (i.e., inter prediction) (475). In-loop filters (465) are applied to the reconstructed image. The filtered image is stored at a reference picture buffer (480).

[0049] The decoded picture can further go through post-decoding processing (485), for example, an inverse color transform (e.g., conversion from YCbCr 4:2:0 to RGB 4:4:4) or an inverse remapping performing the inverse of the remapping process performed in the preencoding processing (301 of figure 3). The post-decoding processing can use metadata derived in the pre-encoding processing and signaled in the bitstream.

[0050] Figure 5 illustrates an example of partitioning undergone by an image of an original video sequence. An original video sequence 500 comprises a plurality of pictures 510. A picture comprises a plurality of pixels, generally arranged in a grid comprising rows and columns. It is considered in this document that a pixel is composed of three components: a luminance component and two chrominance components. Other types of pixels are however possible comprising less or more components such as only a luminance component or an additional depth component or an additional transparency component.

[0051] A picture is divided into a plurality of coding entities. First, as represented by reference 530, a picture is divided in a grid of blocks called coding tree units (CTU). A CTU consists of a block of luminance samples together with two corresponding blocks of chrominance samples. The size of such block is generally N*N, and N is generally a power of two having a maximum value of “128” for example. Second, a picture is divided into one or more groups of CTU. For example, it can be divided into one or more tile rows and tile columns, a tile being a sequence of CTU covering a rectangular region of a picture. In some cases, a tile could be divided into one or more bricks, each of which consisting of at least one row of CTU within the tile. Above the concept of tiles and bricks, another encoding entity, called slice, exists, that can contain at least one tile of a picture or at least one brick of a tile. In the example represented by reference 520, the picture 21 is divided into three slices SI, S2 and S3 of the raster-scan slice mode, each comprising a plurality of tiles (not represented), each tile comprising only one brick.

[0052] As represented by reference 540, a CTU may be partitioned into the form of a hierarchical tree of one or more sub-blocks called coding units (CU). The CTU is the root (i.e., the parent node) of the hierarchical tree and can be partitioned in a plurality of CU (i.e., child nodes). Each CU becomes a leaf of the hierarchical tree if it is not further partitioned in smaller CU or becomes a parent node of smaller CU (i.e., child nodes) if it is further partitioned. During the coding of a picture, the partitioning is adaptive, each CTU being partitioned to Optimize a compression efficiency.

[0053] For example, the CTU 540 is first partitioned in four square CU using a quadtree type partitioning. The upper left CU 541 is a leaf of the hierarchical tree since it is not further partitioned, i.e., it is not a parent node of any other CU. The upper right CU is further partitioned in four smaller square CU 551, 552, 553, 554 using again a quadtree type partitioning. The bottom left CU is vertically partitioned in three rectangular CU 561, 562, 563 using a ternary tree type partitioning. The bottom right CU is vertically partitioned in two rectangular CU 571, 572 using a binary tree type partitioning.

[0054] In HEVC appeared the concept of prediction unit (PU) and transform unit (TU). Indeed, in HEVC, the coding entity that is used for prediction (i.e., a PU) and transform (i.e., a TU) can be a subdivision of a CU. For example, as represented in the figure, a CU of size 2N*2N, can be divided in PU 580 of size N*2N or of size 2N*N. In addition, said CU can be divided in four TU 590 of size N*N or in “16” TU of size (N / 2)x(N / 2). Other video coding standards also use these notions. In VVC, except in some particular cases, frontiers of the TU and PU are aligned on the frontiers of the CU. Consequently, a CU comprises generally one TU and one PU.

[0055] In the present application, the terms “reconstructed” and “decoded” may be used interchangeably, the terms “pixel” and “sample” may be used interchangeably, the terms “image,” “picture”, “sub-picture”, “slice” and “frame” may be used interchangeably. Usually, but not necessarily, the term “reconstructed” is used at the encoder side while “decoded” is used at the decoder side. In the present application, the term “block” or “picture block” can be used to refer to any one of a CTU, a CU, a PU and a TU. In addition, the term “block” or “picture block” can be used to refer to a macroblock, a partition and a sub-block as specified in H.264 / AVC or in other video coding standards, and more generally to refer to an array of samples of numerous sizes.

[0056] Video coding standards like AVC, HEVC and VVC enable embedding of metadata in video bitstreams through SEI (Supplemental Enhancement information) messages. Those messages are defined either in the core standard or companion standard like VSEI (Versatile Supplemental Enhancement Information), and more get added in successive versions of these standards.

[0057] A SEI message is a syntax structure that is defined in various MPEG standards to allow carriage of metadata. It is a specific type of NAL (Network Access Layer) unit, which is the elementary packet in MPEG bitstream formats. The SEI syntax may vary slightly across different standards, but it commonly contains at least a payload type, a payload length, and the payload itself. The SEI syntax defined for VVC is illustrated in Table 1 as an example.

[0058] Table 1 In addition, a specific syntax structure is typically defined for each payload type and instantiated by a sei_payload syntax structure according to each pay load type. For example, a specific SEI message related to Neural-Network Post-Filter Characteristics (NNPFC-SEI) specifies that a neural network may be used as a post-processing filter (hereafter abbreviated as NNPF) and provides some parameters of such neural network, therefore allowing an encoder to define a neural network for performing a post-processing operation after the decoding operation. The syntax of such NNPFC-SEI message, as disclosed in ISO / IEC DIS 23002-7, is illustrated in Table 2.

[0059]

[0060] Table 2

[0061] ANNPFC-SEI message indicates the intended purpose oftheNNPF, specifies the input and output of the neural network and describes its complexity. Up to now, 5 modes have been defined: enhancing visual quality, changing spatial resolution (e.g., up-sampling from high- definition decoded video to ultra-high definition), changing picture rate (e.g., up-sampling from 30 Hz to 60 Hz), up-sampling bit depth to increase the dynamic range of pixel values, colorization to convert monochrome video to full colors. The SEI syntax defined in ISO / IEC DIS 23002-7 allows to define the purpose of a NNPF by using a flag hereafter named nnpfc_purpose as illustrated in Table 3, where ( nnpfc_purpose & bitMask ) not equal to 0 indicates that the NNPF has the purpose associated with the bitMask value. When nnpfc purpose is greater than 0 and ( nnpfc_purpose & bitMask ) is equal to 0, the purpose associated with the bitMask value is not applicable to the NNPF. When nnpfc_purpose is equal to 0x00, the NNPF may be used as determined by the application and as specified by the nnpfc_application_purpose_tag_uri. For instance, if the nnpfc_purpose is equal to OxOC (ObOOOl lOO), it means that we want to activate a resolution resampling NNPF and a picture rate upsampling NNPF.

[0062] Table 3

[0063] The value of nnpfc_purpose shall be in the range of 0 to 63, inclusive, in bitstreams conforming to this edition of this document. Values of 64 to 65 535, inclusive, for nnpfc purpose are reserved for future use by ITU-T | ISO / IEC and shall not be present in bitstreams conforming to this edition of this document. Decoders conforming to this edition of this document shall ignore NNPFC SEI messages with nnpfc_purpose in the range of 64 to 65 535, inclusive.

[0064] This bitfield is used to derive corresponding variables for the purpose flags shown in table 3. The variables ChromaUpsamplingFlag, ResolutionResamplingFlag, PictureRateUpsamplingFlag, BitDepthUpsamplingFlag, and ColourizationFlag, specifying whether nnpfc_purpose indicates the purpose of the NNPF to include chroma upsampling, resolution resampling, picture rate upsampling, bit depth upsampling, and colourization mode respectively, are derived from the nnpfc_purpose bitfield as follows:

[0065] ChromaUpsamplingFlag = ( ( nnpfc_purpose & 0x02 ) > 0 ) ? 1 : 0

[0066] ResolutionResamplingFlag = ( ( nnpfc_purpose & 0x04 ) > 0 ) ? 1 : 0

[0067] PictureRateUpsamplingFlag = ( ( nnpfc_purpose & 0x08 ) > 0 ) ? 1 : 0 BitDepthUpsamplingFlag = ( ( nnpfc_purpose & 0x10 ) > 0 ) ? 1 : 0 ColourizationFlag = ( ( nnpfc_purpose & 0x20 ) > 0 ) ? 1 : 0

[0068] The use of a NNPFC-SEI message provides backward compatibility. Indeed, by implementing neural-network filters as a post-processing step and signaling them in a SEI message, their utilization can be introduced to neural network capable devices and services without negatively impacting older systems that lack the ability to execute neural networks.

[0069] Embodiments described hereafter have been designed with the foregoing in mind and extend the purpose of NNPFC-SEI messages to include energy-aware applications. Therefore, a system compliant with such messages will be able to create an energy-aware image with a certain amount of energy reduction and therefore to reduce the energy consumption of the decoded image when displayed on screen.

[0070] At least one embodiment proposes to signal the use of a neural network post-processing filter for energy-aware processing and provides parameters for the energy-aware processing.

[0071] Figure 6 illustrates a block diagram of an example of video coding system according to embodiments. In step 610, the input video (601) is encoded. A NNPFC SEI message (602) comprising a selected energy reduction rate is defined, for example according to the syntax described in the tables below. In step 620, the encoded video and the NNPFC SEI message are provided to the decoder and conventional video decoding is performed in step 630. Since the NNPFC SEI message comprise syntax elements related to energy-aware processing, in step 632, the decoded video is post-processed by the neural network post-processing filter to reduce the amount of energy consumed, for example using the techniques introduced above. In step 640, the resulting energy-aware video is displayed.

[0072] In at least one embodiment, the use of an energy-aware related neural network postprocessing filter is signaled as an additional purpose in aNNPCF-SEI message by using anew flag, hereafter called Energy AwareFlag, inserted in the last entry of the table as illustrated in Table 4. The value of 0x40 for the Energy AwareFlag is an example. Other bitmask values may be used to carry this flag.

[0073] Table 4

[0074] The other elements of Table 4 are identical to those described in Table 3. The variable Energy AwareFlag, defined for specifying the energy-aware mode is derived from the nnpfc purpose bitfield as follows:

[0075] Energy AwareFlag = ( ( nnpfc_purpose & 0x40 ) > 0 ) ? 1 : 0

[0076] After the addition of this new bitmask value, the value of nnpfc_purpose shall now be in the range of 0 to 127, inclusive and values of 128 to 65 535, inclusive are reserved for future use.

[0077] In addition, a new section is added to the NNPCF-SEI message to specify characteristics or parameters of the energy-aware post processing.

[0078] In at least one embodiment, a simple indication of the target energy reduction ratio is inserted in the NNPCF-SEI message, under the condition of the activation of the Energy AwareFlag. The table 5 illustrates an example of syntax for the NNPCF-SEI message. For the sake of readability, only an extract of the complete message is illustrated in this table. Please refer to the syntax of table 2 for the other elements.

[0079] Table 5 In at least one embodiment, the nnpfc_reduction_ratio syntax element relates to parameter representing a target energy reduction ratio. The value of this parameter represents a target energy reduction ratio selected among a list of predetermined reduction rates, for example coded over 2 bits, as illustrated in Table 6. In such embodiment, for example, when Energy AwareFlag equal to 1, nnpfc_reduction_ratio equals to 2 represents an energy reduction rate of 20%.

[0080] Table 6

[0081] In at least one embodiment, the value of the nnpfc_reduction_ratio syntax element represents a target energy reduction ratio value, for example coded over 4 bits, thus varying between 0 and 15. In such embodiment, for example, Energy AwareFlag equal to 1 and nnpfc_reduction_ratio equal to the value 4 represents an energy reduction rate of 27%. The value 27% is obtained by considering a linear mapping between the nnpfc_reduction_ratio and the maximum value coded over 4 bits (i.e. 15). The reduction ratio expressed in percentage of reduction in a range from 0 to 100% is simply given by where [%] gives the nearest integer (floor(x+0.5)).

[0082] For nnpfc_reduction_ratio = 2 the reduction ratio is 13.

[0083] For nnpfc_reduction_ratio = 4 the reduction ratio is 27.

[0084] For nnpfc_reduction_ratio = 8 the reduction ratio is 53.

[0085] In at least one embodiment, the value of the nnpfc_reduction_ratio syntax element directly represents a target energy reduction ratio value, for example coded over 8 bits, thus varying between 0 and 255. Similarly, to the previous embodiment, the reduction ratio is simply given The target energy reduction ratios expressed in the embodiments are representing a target level of reduction, as expected by the viewer, the manufacturer, or the service provider.

[0086] Depending on the type of the specified filter, the neural network post filter can process the YUV components or the RGB components. In this case, the flag nnpfc_separate_colour_description_present_flag (see table 2) is used to specify the color transformation.

[0087] In at least one embodiment, the input of the neural network post-processing filter is YUV and the output of the neural network post-processing filter is also YUV. In this case, several strategies can be defined. A first example of strategy is that the post filter only modifies the Y component, U and V components are not changed. A second example of strategy is that the post filter computes the new Y component from the incoming Y component. However, since images are generally expressed using RGB values, the RGB values of the input image are modified by multiplying the RGB components by the ratio of the luminance. In this context, two color transformations are made: YUV to RGB, and the modified RGB to YUV.

[0088] In at least one embodiment, the neural network post-processing filter is YUV and computes internally an attenuation map. Such attenuation map is composed of one or more components (e.g., one component for the three YUV components, two components, one for Y and two for chroma components, or 3 components). In this case, the operation for combining the attenuation map with the input YUV image (i.e. , the output of the decoder) is defined in an additional flag, called nnpfc_combination_mode as illustrated in Table 7. When nnpfc_combination_mode is set to ‘O’, the operation uses an addition. In other words, pixels values of the attenuation map generated internally by the neural network post-processing filter are added to pixel values of the image or video. When nnpfc_combination_mode is set to ‘1’, the operation uses a multiplication. In other words, pixel values of the image or video are scaled (multiplied) by pixels values of the attenuation map generated internally by the neural network post-processing filter.

[0089] Table 7 In addition, a flag, called nnpfc attenuation comp flag specifies on which color component(s) of the input decoded image should be applied using the process defined by nnpfc combination mode. It also specifies how many components the attenuation map computed by the post filter should contain. When equal to 0, the internally attenuation map contains only one component, and this component should be applied to the luma component of the input decoded image. When equal to 1, the internally attenuation map contains two components, and the first component should be applied to the luma component of the input decoded image, and the second component should be applied to both chroma components of the input decoded image. When equal to 2, the internally attenuation map contains only one component, and this component should be applied to the luma component and the chroma components of the input decoded image. When equal to 3, the internally attenuation map contains only one component, and this component should be applied to the RGB components (after YUV to RGB conversion) of the input decoded image. When equal to 4, the internally attenuation map contains three components and that these components should be applied respectively to the luma and chroma components of the input decoded image.

[0090] When equal to 5, the internally attenuation map contains three components and these components should be applied respectively to the RGB components (after YUV to RGB conversion) of the input decoded image.

[0091] When equal to 6, the mapping between the components of the input decoded image and the components of the internally attenuation map corresponds to some proprietary user-defined process. This is summarized in Table 8.

[0092]

[0093] Table 8

[0094] To carry such additional flags, the energy-aware related syntax elements of table 5 are modified as shown in table 9. Table 9

[0095] In at least one embodiment, some additional parameters are provided to the neural network post-processing filter through the NNPFC-SEI message. As illustrated in Table 10, these parameters are related to quality and display information.

[0096] Table 10

[0097] In at least one embodiment, nnpfc_video_quality indicates the minimal quality target value. This means that the neural network post filter post-processing filter has two constraints to consider: a target of energy reduction and a minimal quality target (which corresponds to the lowest quality after post processing) for the nnpfc_video_quality_metric. Therefore, the receiver or display device may balance the amount of energy reduction between the value of this metric and the energy reduction rate. The nnpfc video quality metric indicates the quality metric to be considered by the neural network for measuring the quality of an energy -reduced image. Its value is selected among the values illustrated in Table 11, to select among Peak Signal to Noise Ratio (PSNR), Structural SIMilarity Index (SSIM), Weighted Spherical Peak Signal to Noise Ratio (ws-PSNR), or Video Multimethod assessment fusion (VMAF). The scale and value depend on which metric is used. For PSNR or ws-PSNR, the metric is measured in dB, for SSIM the value is comprised between 0 and 1 (Maximal quality), and for VMAF the value is comprised between 0 and 100 (Maximal quality).

[0098] Table 11

[0099] In at least one embodiment, nnpfc display model indicates the target display for which the energy reduction is made. As illustrated in Table 12, this metadata is represented by a 4- bits bit field mask which indicates that the computation of the energy-aware images should be tailored for a particular type of display. For example, nnpfc_display_model =“0010” means the computation of the energy-aware image is tailored for Emissive display.

[0100] | Bit number | Display type |

[0101] Table 12

[0102] Figure 7 illustrates an example process for encoding a bitstream comprising an energy reduction NNPFC SEI message according to embodiments. The process 700 is for example implemented by a processor 1010 of a device 1000 of figure 1, a system 210 of figure 2, or an encoder 300 of figure 3. In step 710, the processor obtains video data. In step 720, the processor determines neural network post-processing filter characteristics related to energy reduction. In step 730, the processor determines an energy reduction NNPFC SEI message comprising information related to an energy reduction process, for example according to the syntax described above. This step may comprise specifying the mode nnpfc_mode_id, activating the nnpfc_purpose and defining an amount of reduction nnpfc_reduction_ratio. In step 740, the processor conventionally encodes the video. In step 750, the processor determines a bitstream that comprises the encoded video data and the energy reduction NNPFC SEI message. In step 760, the processor provides the bitstream.

[0103] In at least one embodiment, the NNPF is predetermined (i.e. standardized). In at least one embodiment, the NNPF is defined by a URL. In at least one embodiment, the weights of the NNPF model are transmitted in the bitstream (for example using ISO / IEC 15938-17 syntax introduced in table 2). These methods are activated using the nnpfc_mode_id flag and setting the appropriate parameters.

[0104] Figure 8 illustrates an example process for decoding a bitstream comprising an energy reduction NNPFC SEI message according to embodiments. The process 800 is for example implemented by a device 1000 of figure 1, a system 230 of figure 2, or a decoder 400 of figure 4. In step 810, the processor obtains the bitstream that comprises an encoded video data and metadata for an energy reduction network post-processing filter packaged into an energy reduction NNPFC SEI message, for example based on the syntax of tables 3 or 4. In step 820, the processor conventionally decodes the video from the encoded video data. In step 830, the processor determines neural network post-processing filter characteristics related to energy reduction from the energy reduction NNPFC SEI message. In step 840, based on the determined characteristics, the processor applies the neural network post-processing filter to the decoded video. In step 850, the processor provides the energy aware video. In at least one embodiment, the neural network post-processing filter is applied only under certain conditions such as a user choice, a device configuration parameter, a parameter of the device (such as low level of battery for mobile devices) or other conditions.

[0105] Although some parts of the description refer to video, the embodiments are not restricted to conventional (2D) videos and apply to any type of visual media content such as static images, stereoscopic (3D) images or videos, 360° immersive images or video, point clouds, based on the same principles as described above.

[0106] This application describes a variety of aspects, including tools, features, embodiments, models, approaches, etc. Many of these aspects are described with specificity and, at least to show the individual characteristics, are often described in a manner that may sound limiting. However, this is for purposes of clarity in description, and does not limit the application or scope of those aspects. Indeed, all of the different aspects can be combined and interchanged to provide further aspects. Moreover, the aspects can be combined and interchanged with aspects described in earlier filings as well.

[0107] The aspects described and contemplated in this application can be implemented in many different forms. Figures provide some embodiments, but other embodiments are contemplated and the discussion of these figures does not limit the breadth of the implementations. At least one of the aspects generally relates to video encoding and decoding, and at least one other aspect generally relates to transmitting a bitstream generated or encoded. These and other aspects can be implemented as a method, an apparatus, a computer readable storage medium having stored thereon instructions for encoding or decoding video data according to any of the methods described, and / or a computer readable storage medium having stored thereon a bitstream generated according to any of the methods described.

[0108] Various methods are described herein, and each of the methods comprises one or more steps or actions for achieving the described method. Unless a specific order of steps or actions is required for proper operation of the method, the order and / or use of specific steps and / or actions may be modified or combined.

[0109] Various numeric values are used in the present application, for example, 128 for the block size. The specific values are for example purposes and the aspects described are not limited to these specific values. Various implementations involve decoding. “Decoding”, as used in this application, can encompass all or part of the processes performed, for example, on a received encoded sequence in order to produce a final output suitable for display. In various embodiments, such processes include one or more of the processes typically performed by a decoder, for example, entropy decoding, inverse quantization, inverse transformation, and differential decoding. In various embodiments, such processes also, or alternatively, include processes performed by a decoder of various implementations described in this application, for example, adapting the illumination compensation process.

[0110] As further examples, in one embodiment “decoding” refers only to entropy decoding, in another embodiment “decoding” refers only to differential decoding, and in another embodiment “decoding” refers to a combination of entropy decoding and differential decoding. Whether the phrase “decoding process” is intended to refer specifically to a subset of operations or generally to the broader decoding process will be clear based on the context of the specific descriptions and is believed to be well understood by those skilled in the art.

[0111] Various implementations involve encoding. In an analogous way to the above discussion about “decoding”, “encoding” as used in this application can encompass all or part of the processes performed, for example, on an input video sequence in order to produce an encoded bitstream. In various embodiments, such processes include one or more of the processes typically performed by an encoder, for example, partitioning, differential encoding, transformation, quantization, and entropy encoding. In various embodiments, such processes also, or alternatively, include processes performed by an encoder of various implementations described in this application.

[0112] As further examples, in one embodiment “encoding” refers only to entropy encoding, in another embodiment “encoding” refers only to differential encoding, and in another embodiment “encoding” refers to a combination of differential encoding and entropy encoding. Whether the phrase “encoding process” is intended to refer specifically to a subset of operations or generally to the broader encoding process will be clear based on the context of the specific descriptions and is believed to be well understood by those skilled in the art.

[0113] Note that the syntax elements as used herein, are descriptive terms. As such, they do not preclude the use of other syntax element names.

[0114] When a figure is presented as a flow diagram, it should be understood that it also provides a block diagram of a corresponding apparatus. Similarly, when a figure is presented as a block diagram, it should be understood that it also provides a flow diagram of a corresponding method / process.

[0115] Various embodiments refer to rate distortion optimization. In particular, during the encoding process, the balance or trade-off between the rate and distortion is usually considered, often given the constraints of computational complexity. The rate distortion optimization is usually formulated as minimizing a rate distortion function, which is a weighted sum of the rate and of the distortion. There are different approaches to solve the rate distortion optimization problem. For example, the approaches may be based on an extensive testing of all encoding options, including all considered modes or coding parameters values, with a complete evaluation of their coding cost and related distortion of the reconstructed signal after coding and decoding. Faster approaches may also be used, to save encoding complexity, in particular with computation of an approximated distortion based on the prediction or the prediction residual signal, not the reconstructed one. Mix of these two approaches can also be used, such as by using an approximated distortion for only some of the possible encoding options, and a complete distortion for other encoding options. Other approaches only evaluate a subset of the possible encoding options. More generally, many approaches employ any of a variety of techniques to perform the optimization, but the optimization is not necessarily a complete evaluation of both the coding cost and related distortion.

[0116] This application describes a variety of aspects, including tools, features, embodiments, models, approaches, etc. Many of these aspects are described with specificity and, at least to show the individual characteristics, are often described in a manner that may sound limiting. However, this is for purposes of clarity in description, and does not limit the application or scope of those aspects. Indeed, all of the different aspects can be combined and interchanged to provide further aspects. Moreover, the aspects can be combined and interchanged with aspects described in earlier filings as well.

[0117] The implementations and aspects described herein can be implemented in, for example, a method or a process, an apparatus, a software program, a data stream, or a signal. Even if only discussed in the context of a single form of implementation (for example, discussed only as a method), the implementation of features discussed can also be implemented in other forms (for example, an apparatus or program). An apparatus can be implemented in, for example, appropriate hardware, software, and firmware. The methods can be implemented in, for example, a processor, which refers to processing devices in general, including, for example, a computer, a microprocessor, an integrated circuit, or a programmable logic device. Processors also include communication devices, such as, for example, computers, tablets, smartphones, cell phones, portable / personal digital assistants, and other devices that facilitate communication of information between end-users.

[0118] Reference to “one embodiment” or “an embodiment” or “one implementation” or “an implementation”, as well as other variations thereof, means that a particular feature, structure, characteristic, and so forth described in connection with the embodiment is included in at least one embodiment. Thus, the appearances of the phrase “in one embodiment” or “in an embodiment” or “in one implementation” or “in an implementation”, as well any other variations, appearing in various places throughout this application are not necessarily all referring to the same embodiment.

[0119] Additionally, this application may refer to “determining” various pieces of information. Determining the information can include one or more of, for example, estimating the information, calculating the information, predicting the information, or retrieving the information from memory.

[0120] Further, this application may refer to “accessing” various pieces of information. Accessing the information can include one or more of, for example, receiving the information, retrieving the information (for example, from memory), storing the information, moving the information, copying the information, calculating the information, determining the information, predicting the information, or estimating the information.

[0121] Additionally, this application may refer to “receiving” various pieces of information. Receiving is, as with “accessing”, intended to be a broad term. Receiving the information can include one or more of, for example, accessing the information, or retrieving the information (for example, from memory). Further, “receiving” is typically involved, in one way or another, during operations such as, for example, storing the information, processing the information, transmitting the information, moving the information, copying the information, erasing the information, calculating the information, determining the information, predicting the information, or estimating the information.

[0122] In the present application, the terms “reconstructed” and “decoded” may be used interchangeably, the terms “pixel” and “sample” may be used interchangeably, the terms “image,” “picture”, “frame”, “slice” and “tiles” may be used interchangeably. Usually, but not necessarily, the term “reconstructed” is used at the encoder side while “decoded” is used at the decoder side. It is to be appreciated that the use of any of the following “ / ”, “and / or”, and “at least one of’, for example, in the cases of “A / B”, “A and / or B” and “at least one of A and B”, is intended to encompass the selection of the first listed option (A) only, or the selection of the second listed option (B) only, or the selection of both options (A and B). As a further example, in the cases of “A, B, and / or C” and “at least one of A, B, and C”, such phrasing is intended to encompass the selection of the first listed option (A) only, or the selection of the second listed option (B) only, or the selection of the third listed option (C) only, or the selection of the first and the second listed options (A and B) only, or the selection of the first and third listed options (A and C) only, or the selection of the second and third listed options (B and C) only, or the selection of all three options (A and B and C). This may be extended, as is clear to one of ordinary skill in this and related arts, for as many items as are listed.

[0123] Also, as used herein, the word “signal” refers to, among other things, indicating something to a corresponding decoder. For example, in certain embodiments the encoder signals a particular one of an illumination compensation parameter. In this way, in an embodiment the same parameter is used at both the encoder side and the decoder side. Thus, for example, an encoder can transmit (explicit signaling) a particular parameter to the decoder so that the decoder can use the same particular parameter. Conversely, if the decoder already has the particular parameter as well as others, then signaling can be used without transmitting (implicit signaling) to simply allow the decoder to know and select the particular parameter. By avoiding transmission of any actual functions, a bit savings is realized in various embodiments. It is to be appreciated that signaling can be accomplished in a variety of ways. For example, one or more syntax elements, flags, and so forth are used to signal information to a corresponding decoder in various embodiments. While the preceding relates to the verb form of the word “signal”, the word “signal” can also be used herein as a noun.

[0124] As will be evident to one of ordinary skill in the art, implementations can produce a variety of signals formatted to carry information that can be, for example, stored or transmitted. The information can include, for example, instructions for performing a method, or data produced by one of the described implementations. For example, a signal can be formatted to carry the bitstream of a described embodiment. Such a signal can be formatted, for example, as an electromagnetic wave (for example, using a radio frequency portion of spectrum) or as a baseband signal. The formatting can include, for example, encoding a data stream and modulating a carrier with the encoded data stream. The information that the signal carries can be, for example, analog or digital information. The signal can be transmitted over a variety of different wired or wireless links, as is known. The signal can be stored on a processor-readable medium.

[0125] We describe a number of embodiments. Features of these embodiments can be provided alone or in any combination, across various claim categories and types.

Claims

CLAIMS1. A method comprising: obtaining video data; determining energy reduction network post-processing filter characteristics; determining a supplemental enhancement information message comprising a target energy reduction ratio for an energy reduction network post-processing filter; encode video data; generate bitstream comprising encoded video and supplemental enhancement information message; and providing the bitstream.

2. A method comprising: obtaining a bitstream comprising encoded video data and a supplemental enhancement information message comprising a target energy reduction ratio for an energy reduction network post-processing filter; decoding video; applying to the decoded video the energy reduction neural network post-processing filter with the target energy reduction ratio; and providing energy-reduced video.

3. The method of any of claims 1 or 2, wherein the energy reduction ratio is selected in a set of pre-determined values of energy reduction.

4. The method of any of claims 1 or 2, wherein the energy reduction ratio is expressed as a percentage of reduction.

5. The method of any of claims 1 to 4, wherein the supplemental enhancement information message further comprises an information representative of a combination mode between the video and an output of an energy reduction network post-processing filter, the combination being selected among an addition or a multiplication.

6. The method of any of claims 1 to 5, wherein the supplemental enhancement information message further comprises an information representative of a minimal video quality target.

7. The method of claim 6, wherein the supplemental enhancement information message further comprises an identification of the quality metric to be selected among a set of quality metrics comprising PSNR, SSIM, wPSNR, WS-PSNR, and V-MAF.

8. The method of any of claims 1 to 7, wherein the supplemental enhancement information message further comprises an information representative of a display type.

9. An apparatus comprising one or more processor configured to: obtain video data; determining energy reduction network post-processing filter characteristics; determining a supplemental enhancement information message comprising a target energy reduction ratio for an energy reduction network post-processing filter; encode video data; generate bitstream comprising encoded video and supplemental enhancement information message; and providing the bitstream.

10. An apparatus comprising one or more processor configured to: obtain a bitstream comprising encoded video data and a supplemental enhancement information message comprising a target energy reduction ratio for an energy reduction network post-processing filter; decoding video; apply to the decoded video the energy reduction neural network post-processing filter with the target energy reduction ratio; and provide energy-reduced video.

11. The apparatus of any of claims 9 or 10, wherein the energy reduction ratio is selected in a set of pre-determined values of energy reduction.

12. The apparatus of any of claims 9 or 10, wherein the energy reduction ratio is expressed as a percentage of reduction.

13. The apparatus of any of claims 9 to 12, wherein the supplemental enhancement information message further comprises an information representative of a combination mode between thevideo and an output of an energy reduction network post-processing filter, the combination being selected among an addition or a multiplication.

14. The apparatus of any of claims 9 to 13, wherein the supplemental enhancement information message further comprises an information representative of a minimal video quality target.

15. The method of claim 14, wherein the supplemental enhancement information message further comprises an identification of the quality metric to be selected among a set of quality metrics comprising PSNR, SSIM, wPSNR, WS-PSNR, and V-MAF.

16. The apparatus of any of claims 9 to 15, wherein the supplemental enhancement information message further comprises an information representative of a display type.

17. A non-transitory computer readable medium containing data content generated according to the method of any one of claims 1 to 8.

18. A computer program product comprising instructions for performing the method of any one of claims 1 to 8 when executed by one of more processor.

Images