Encoding / decoding methods, encoding / decoding devices, encoders, decoders, and computer-readable recording media.

Abstract

The invention relates to methods and devices for encoding and decoding, and relates to the field of artificial intelligence technology, to improve the rate distortion performance of data encoding and decoding methods. The method comprises the following steps: first, obtain the data to be encoded, and then input the data to be encoded into a first encoding network to obtain the target parameter; then construct a second encoding network based on the target parameter; next, input the data to be encoded into the second encoding network to obtain the first feature; and finally, encode the first feature to obtain the encoded bit stream.

Description

Coding and decoding method and device

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on August 5, 2021, with application number 202110898667.8 and invention name “Encoding and Decoding Method and Device”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of artificial intelligence technology, and in particular to encoding and decoding methods and devices. Background Art

[0003] With the advancement of technology, the number and resolution of images are constantly increasing. This large number of images requires not only larger storage media, but also wider transmission bandwidths and longer transmission times. This has become a fundamental problem in image processing. To improve the storage and transmission efficiency of images, it is necessary to encode and compress large images.

[0004] Compressing images based on neural networks can improve the efficiency of image compression. Existing neural network-based image compression methods are mainly divided into neural network image compression methods that require online training (referred to as method one) and neural network image compression methods that do not require online training (referred to as method two). Method one has better rate-distortion performance, but the image compression speed is slow due to the need for online training. Method two has poor rate-distortion performance but fast image compression speed.

[0005] Summary of the Invention

[0006] This application provides a coding and decoding method and apparatus that can improve the rate-distortion performance of data coding and decoding methods without the need for online training. To achieve the above objectives, this application adopts the following technical solutions:

[0007] In a first aspect, the present application provides an encoding method, which includes: first obtaining data to be encoded, then inputting the data to be encoded into a first encoding network to obtain target parameters; then constructing a second encoding network according to the target parameters; then inputting the data to be encoded into the second encoding network to obtain a first feature; and finally encoding the first feature to obtain an encoded code stream.

[0008] In the existing encoding method, the encoding network (i.e., the second encoding network) uses fixed parameter weights to extract the content features of the data to be encoded (i.e., the first features), and then encodes the content features into a code stream (i.e., the encoded code stream) and sends it to the decoding end. The decoding end decodes and reconstructs the code stream to obtain decoded data. It can be seen that the parameter weights of the encoding network in the prior art are not related to the data to be encoded. In the encoding method provided by the present application, the data to be encoded is first input into the first encoding network, and then the first encoding network generates the parameter weights of the second encoding network according to the data to be encoded, and then the parameter weights of the second encoding network are dynamically adjusted according to the obtained weights, so that the parameter weights of the second encoding network are related to the data to be encoded, thereby increasing the expression ability of the second encoding network, so that the decoded data reconstructed by decoding the code stream obtained by the decoding end through the first feature encoding is closer to the data to be encoded, thereby improving the rate-distortion performance of the encoding and decoding network.

[0009] Optionally, the target parameter is a parameter weight of all convolutions or partial convolutions and nonlinear activations of the second encoding network.

[0010] In one possible implementation, encoding the first feature to obtain a coded bitstream includes: rounding the first feature to obtain a rounded value of the first feature; performing probability estimation on the rounded value of the first feature to obtain an estimated probability distribution of the rounded value of the first feature; and performing entropy encoding on the rounded value of the first feature according to the estimated probability distribution of the rounded value of the first feature to obtain the coded bitstream.

[0011] The rounded value of the first feature is entropy encoded through the estimated probability distribution of the rounded value of the first feature to form a code stream, which can reduce the coding redundancy of the output first feature and further reduce the data transmission volume during the data encoding and decoding (compression) process.

[0012] In one possible implementation, the performing probability estimation on the rounded value of the first feature to obtain an estimated probability distribution of the rounded value of the first feature includes: performing probability estimation on the rounded value of the first feature based on first information to obtain an estimated probability distribution of the rounded value of the first feature, wherein the first information includes at least one of context information and side information.

[0013] Estimating the probability distribution through context information and side information can improve the accuracy of the estimated probability distribution, thereby reducing the bit rate in the entropy coding process and reducing the entropy coding overhead.

[0014] In a second aspect, the present application provides a decoding method, comprising: first obtaining a code stream to be decoded; then decoding the code stream to be decoded to obtain a rounded value of a first feature and a rounded value of a second feature; then inputting the rounded value of the second feature into a first decoding network to obtain the target parameter; then constructing a second decoding network based on the target parameter; and finally inputting the rounded value of the first feature into the second decoding network to obtain decoded data. The rounded value of the first feature is used to obtain the decoded data, and the rounded value of the second feature is used to obtain the target parameter.

[0015] In the existing decoding method, the decoding network (i.e., the second decoding network) uses fixed parameter weights to decode and reconstruct the content value features of the coded data (i.e., the rounded value of the first feature) to obtain decoded data. It can be seen that the parameter weights of the decoding network in the prior art are not related to the data to be decoded. In the present application, the content features and model features of the data to be decoded (i.e., the first feature and the second feature) are encoded into a code stream to be decoded, and then the decoding end obtains the rounded value of the second feature by decoding the code stream to be decoded. The rounded value of the second feature is input into the first decoding network to obtain the parameter weight of the second decoding network, and then the parameter weight of the second decoding network is dynamically adjusted according to the parameter weight, so that the parameter weight of the second decoding network is related to the data to be decoded, thereby improving the expression ability of the second decoding network, and making the decoded data obtained by decoding and reconstructing the second decoding network closer to the data to be encoded, thereby improving the rate-distortion performance of the encoding and decoding network.

[0016] Optionally, the target parameter is a parameter weight of all or part of the convolution and nonlinear activation of the second decoding network.

[0017] Optionally, the code stream to be decoded may include a first code stream to be decoded and a second code stream to be decoded.

[0018] In a possible implementation, decoding the to-be-decoded code stream to obtain a rounded value of the first feature and a rounded value of the second feature includes: decoding the first to-be-decoded code stream to obtain a rounded value of the first feature; and decoding the second to-be-decoded code stream to obtain a rounded value of the second feature.

[0019] In one possible implementation, decoding the first to-be-decoded code stream to obtain the rounded value of the first feature includes: performing probability estimation on the rounded value of the first feature in the first to-be-decoded code stream to obtain an estimated probability distribution of the rounded value of the first feature; and performing entropy decoding on the first to-be-decoded code stream according to the estimated probability distribution of the rounded value of the first feature to obtain the rounded value of the first feature.

[0020] In one possible implementation, performing probability estimation on the rounded values ​​of the first feature in the first to-be-decoded bitstream to obtain an estimated probability distribution of the rounded values ​​of the first feature includes: performing probability estimation on the rounded values ​​of the first feature in the first to-be-decoded bitstream based on first information to obtain an estimated probability distribution of the rounded values ​​of the first feature, where the first information includes at least one of context information and side information.

[0021] In one possible implementation, decoding the second to-be-decoded code stream to obtain the rounded value of the second feature includes: performing probability estimation on the rounded value of the second feature in the second to-be-decoded code stream to obtain an estimated probability distribution of the rounded value of the second feature; and performing entropy decoding on the second to-be-decoded code stream according to the estimated probability distribution of the rounded value of the second feature to obtain the rounded value of the second feature.

[0022] In one possible implementation, the performing probability estimation on the rounded value of the second feature in the second to-be-decoded bitstream to obtain an estimated probability distribution of the rounded value of the second feature includes: performing probability estimation on the rounded value of the second feature in the second to-be-decoded bitstream based on first information to obtain an estimated probability distribution of the rounded value of the second feature, where the first information includes at least one of context information and side information.

[0023] In a third aspect, the present application provides a decoding method, comprising: first obtaining a code stream to be decoded; then decoding the code stream to be decoded to obtain a rounded value of a first feature; then inputting the rounded value of the first feature into a third decoding network to obtain a target parameter; then constructing a second decoding network based on the target parameter; and finally inputting the rounded value of the first feature into the second decoding network to obtain decoded data. The first feature is used to obtain the decoded data and the target parameter.

[0024] In the existing decoding method, the decoding network (i.e., the second decoding network) uses fixed parameter weights to decode and reconstruct the content value characteristics of the coded data (i.e., the rounded value of the first feature) to obtain decoded data. It can be seen that the parameter weights of the decoding network in the prior art are not related to the data to be decoded. In the present application, the rounded value of the first feature is obtained by decoding the feature of the data to be decoded (i.e., the first feature) encoded into the code stream to be decoded, and the rounded value of the first feature is input into the first decoding network to obtain the parameter weight of the second decoding network. Then, the parameter weight of the second decoding network is dynamically adjusted according to the parameter weight, so that the parameter weight of the second decoding network is related to the data to be decoded, thereby improving the expression ability of the second decoding network, and making the decoded data obtained by decoding and reconstructing the second decoding network closer to the data to be encoded, thereby improving the rate-distortion performance of the encoding and decoding network.

[0025] Optionally, the target parameter is a parameter weight of all or part of the convolution and nonlinear activation of the second decoding network.

[0026] In one possible implementation, decoding the to-be-decoded bitstream to obtain the rounded value of the first feature includes: performing probability estimation on the rounded value of the first feature in the to-be-decoded bitstream to obtain an estimated probability distribution of the rounded value of the first feature; and performing entropy decoding on the to-be-decoded bitstream according to the estimated probability distribution of the rounded value of the first feature to obtain the rounded value of the first feature.

[0027] In one possible implementation, the performing probability estimation on the rounded value of the first feature in the to-be-decoded bitstream to obtain an estimated probability distribution of the rounded value of the first feature includes: performing probability estimation on the rounded value of the first feature in the to-be-decoded bitstream based on first information to obtain an estimated probability distribution of the rounded value of the first feature, where the first information includes at least one of context information and side information.

[0028] In a fourth aspect, the present application provides an encoding device, which includes a processing circuit, wherein the processing circuit is used to: obtain data to be encoded; input the data to be encoded into a first encoding network to obtain target parameters; construct a second encoding network according to the target parameters; input the data to be encoded into the second encoding network to obtain a first feature; and encode the first feature to obtain an encoded code stream.

[0029] Optionally, the target parameter is a parameter weight of all convolutions or partial convolutions and nonlinear activations of the second encoding network.

[0030] In one possible implementation, the processing circuit is specifically used to: round the first feature to obtain a rounded value of the first feature; perform probability estimation on the rounded value of the first feature to obtain an estimated probability distribution of the rounded value of the first feature; and perform entropy encoding on the rounded value of the first feature according to the estimated probability distribution of the rounded value of the first feature to obtain the encoded code stream.

[0031] In one possible implementation, the processing circuit is specifically used to: perform probability estimation on the rounded value of the first feature based on first information to obtain an estimated probability distribution of the rounded value of the first feature, where the first information includes at least one of context information and side information.

[0032] In a fifth aspect, the present application provides a decoding device, which includes a processing circuit, wherein the processing circuit is used to: obtain a code stream to be decoded; decode the code stream to be decoded to obtain a rounded value of a first feature and a rounded value of a second feature, the rounded value of the first feature is used to obtain decoded data, and the rounded value of the second feature is used to obtain a target parameter; input the rounded value of the second feature into a first decoding network to obtain the target parameter; construct a second decoding network according to the target parameter; input the rounded value of the first feature into the second decoding network to obtain decoded data.

[0033] Optionally, the target parameter is a parameter weight of all or part of the convolution and nonlinear activation of the second decoding network.

[0034] Optionally, the code stream to be decoded includes a first code stream to be decoded and a second code stream to be decoded.

[0035] In a possible implementation, the processing circuit is specifically configured to: decode the first to-be-decoded code stream to obtain a rounded value of the first feature; and decode the second to-be-decoded code stream to obtain a rounded value of the second feature.

[0036] In one possible implementation, the processing circuit is specifically configured to: perform probability estimation on a rounded value of a first feature in the first to-be-decoded bitstream to obtain an estimated probability distribution of the rounded value of the first feature; and perform entropy decoding on the first to-be-decoded bitstream according to the estimated probability distribution of the rounded value of the first feature to obtain the rounded value of the first feature.

[0037] In one possible implementation, the processing circuit is specifically used to: perform probability estimation on the rounded value of the first feature in the first to-be-decoded code stream based on first information to obtain an estimated probability distribution of the rounded value of the first feature, where the first information includes at least one of context information and side information.

[0038] In one possible implementation, the processing circuit is specifically configured to: perform probability estimation on a rounded value of a second feature in the second to-be-decoded bitstream to obtain an estimated probability distribution of the rounded value of the second feature; and perform entropy decoding on the second to-be-decoded bitstream according to the estimated probability distribution of the rounded value of the second feature to obtain the rounded value of the second feature.

[0039] In one possible implementation, the processing circuit is specifically used to: perform probability estimation on the rounded value of the second feature in the second to-be-decoded code stream based on first information to obtain an estimated probability distribution of the rounded value of the second feature, where the first information includes at least one of context information and side information.

[0040] In a sixth aspect, the present application provides a decoding device, which includes a processing circuit, wherein the processing circuit is used to: obtain a code stream to be decoded; decode the code stream to be decoded to obtain a rounded value of a first feature, and the rounded value of the first feature is used to obtain decoded data and a target parameter; input the rounded value of the first feature into a first decoding network to obtain a target parameter; construct a second decoding network according to the target parameter; and input the rounded value of the first feature into the second decoding network to obtain decoded data.

[0041] Optionally, the target parameter is a parameter weight of all or part of the convolution and nonlinear activation of the second decoding network.

[0042] In one possible implementation, the processing circuit is specifically configured to: perform probability estimation on a rounded value of a first feature in the to-be-decoded bitstream to obtain an estimated probability distribution of the rounded value of the first feature; and perform entropy decoding on the to-be-decoded bitstream according to the estimated probability distribution of the rounded value of the first feature to obtain the rounded value of the first feature.

[0043] In one possible implementation, the processing circuit is specifically used to: perform probability estimation on the rounded value of the first feature in the to-be-decoded code stream based on first information to obtain an estimated probability distribution of the rounded value of the first feature, wherein the first information includes at least one of context information and side information.

[0044] In a seventh aspect, an embodiment of the present application further provides an encoder comprising: at least one processor, which, when the at least one processor executes program code or instructions, implements the method described in the above-mentioned first aspect or any possible implementation thereof.

[0045] Optionally, the encoder may further include at least one memory for storing the program code or instruction.

[0046] In an eighth aspect, an embodiment of the present application further provides a decoder comprising: at least one processor, which, when the at least one processor executes program code or instructions, implements the method described in the above second aspect or any possible implementation thereof.

[0047] Optionally, the decoder may further include at least one memory, and the at least one memory is used to store the program code or instruction.

[0048] In a ninth aspect, embodiments of the present application further provide a chip comprising: an input interface, an output interface, and at least one processor. Optionally, the chip further comprises a memory. The at least one processor is configured to execute code in the memory. When the at least one processor executes the code, the chip implements the method described in the first aspect or any possible implementation thereof.

[0049] Optionally, the chip may also be an integrated circuit.

[0050] In a tenth aspect, an embodiment of the present application further provides a terminal comprising the above-mentioned encoding device, decoding device, encoder, decoder or the above-mentioned chip.

[0051] In an eleventh aspect, the present application further provides a computer-readable storage medium for storing a computer program, wherein the computer program includes methods for implementing the method described in the first aspect or any possible implementation thereof.

[0052] In a twelfth aspect, an embodiment of the present application further provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to implement the method described in the first aspect or any possible implementation thereof.

[0053] The encoding device, decoding device, encoder, decoder, computer storage medium, computer program product and chip provided in this embodiment are all used to execute the method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the method provided above and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0055] FIG1a is an exemplary block diagram of a decoding system provided in an embodiment of the present application;

[0056] FIG1b is an exemplary block diagram of a video decoding system provided in an embodiment of the present application;

[0057] FIG2 is an exemplary block diagram of a video encoder provided in an embodiment of the present application;

[0058] FIG3 is an exemplary block diagram of a video decoder provided in an embodiment of the present application;

[0059] FIG4 is an exemplary schematic diagram of candidate image blocks provided in an embodiment of the present application;

[0060] FIG5 is an exemplary block diagram of a video decoding device provided in an embodiment of the present application;

[0061] FIG6 is an exemplary block diagram of a device provided in an embodiment of the present application;

[0062] FIG7a is a schematic diagram of an application scenario provided by an embodiment of the present application;

[0063] FIG7 b is a schematic diagram of an application scenario provided by an embodiment of the present application;

[0064] FIG8 is a schematic diagram of a flow chart of a coding and decoding method provided in an embodiment of the present application;

[0065] FIG9 is a schematic structural diagram of a coding and decoding system provided in an embodiment of the present application;

[0066] FIG10 is a schematic diagram of a flow chart of another encoding and decoding method provided in an embodiment of the present application;

[0067] FIG11 is a schematic diagram of the structure of another encoding and decoding system provided in an embodiment of the present application;

[0068] FIG12 is a schematic structural diagram of another encoding and decoding system provided in an embodiment of the present application;

[0069] FIG13 is a schematic diagram of a flow chart of another encoding and decoding method provided in an embodiment of the present application;

[0070] FIG14 is a schematic structural diagram of another encoding and decoding system provided in an embodiment of the present application;

[0071] FIG15 is a schematic diagram illustrating the performance of the encoding and decoding method provided in an embodiment of the present application;

[0072] FIG16 is a schematic diagram of an application scenario provided by an embodiment of the present application;

[0073] FIG17 is a schematic diagram of another application scenario provided by an embodiment of the present application;

[0074] FIG18 is a schematic structural diagram of a coding and decoding device provided in an embodiment of the present application;

[0075] FIG19 is a schematic structural diagram of another encoding and decoding device provided in an embodiment of the present application;

[0076] FIG20 is a schematic diagram of the structure of a chip provided in an embodiment of the present application. DETAILED DESCRIPTION

[0077] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0078] The term "and / or" in this article is merely a description of the association relationship between associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0079] The terms "first" and "second" and the like in the specification and drawings of this application are used to distinguish different objects, or to distinguish different processing of the same object, rather than to describe a specific order of objects.

[0080] Furthermore, the terms "including," "having," and any variations thereof mentioned in the description of this application are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units not listed, or may optionally include other steps or units inherent to the process, method, product, or apparatus.

[0081] It should be noted that in the description of the embodiments of this application, words such as "exemplarily" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplarily" or "for example" in the embodiments of this application should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplarily" or "for example" is intended to present the relevant concepts in a concrete manner.

[0082] In the description of the present application, unless otherwise specified, “plurality” means two or more.

[0083] The embodiments of the present application provide an AI-based data compression / decompression technology, in particular, a neural network-based data compression / decompression technology, and specifically provide a coding / decoding technology to improve the traditional hybrid data coding / decoding system.

[0084] Data encoding and decoding includes two parts: data encoding and data decoding. Data encoding is performed on the source side (or commonly referred to as the encoder side), and generally includes processing (e.g., compressing) the original data to reduce the amount of data required to represent the original data (thereby more efficiently storing and / or transmitting). Data decoding is performed on the destination side (or commonly referred to as the decoder side), and generally includes inverse processing relative to the encoder side to reconstruct the original data. The "encoding and decoding" of the data involved in the embodiments of the present application should be understood as the "encoding" or "decoding" of the data. The encoding part and the decoding part are also collectively referred to as encoding and decoding (encoding and decoding, CODEC).

[0085] In the case of lossless data encoding, the original data can be reconstructed, that is, the reconstructed original data has the same quality as the original data (assuming there is no transmission loss or other data loss during storage or transmission). In the case of lossy data encoding, further compression is performed through quantization or the like to reduce the amount of data required to represent the original data, but the decoder side cannot fully reconstruct the original data, that is, the quality of the reconstructed original data is lower or worse than the quality of the original data.

[0086] The embodiments of the present application can be applied to video data, image data, audio data, integer data, and other data with compression / decompression requirements. The following uses the encoding of video data (referred to as video encoding) as an example to illustrate the embodiments of the present application. For other types of data (such as image data, audio data, integer data, and other data with compression / decompression requirements), reference can be made to the following description, which will not be repeated in the embodiments of the present application. It should be noted that, compared to video encoding, the encoding process of data such as audio data and integer data does not require the data to be divided into blocks, but the data can be directly encoded.

[0087] Video coding generally refers to processing a sequence of images to form a video or video sequence. In the field of video coding, the terms "picture", "frame" or "image" can be used as synonyms.

[0088] Several video coding standards fall under the category of "lossy hybrid video codecs" (i.e., combining spatial and temporal prediction in the pixel domain with 2D transform coding in the transform domain for applying quantization). Each image in a video sequence is typically divided into a set of non-overlapping blocks, which are typically coded at the block level. In other words, the encoder typically processes, i.e., encodes, the video at the block (video block) level, for example, by generating a prediction block through spatial (intra-frame) and temporal (inter-frame) prediction; subtracting the prediction block from the current block (currently processed / to-be-processed block) to obtain a residual block; transforming and quantizing the residual block in the transform domain to reduce the amount of data to be transmitted (compressed), while the decoder applies the inverse of the encoder's processing to the coded or compressed block to reconstruct the current block for representation. Furthermore, the encoder needs to repeat the decoder's processing steps so that the encoder and decoder generate the same predictions (e.g., intra-frame predictions and inter-frame predictions) and / or reconstructed pixels for processing, i.e., encoding, the subsequent block.

[0089] In the following embodiment of the decoding system 10 , the encoder 20 and the decoder 30 are described with reference to FIG. 1 a to FIG. 3 .

[0090] FIG1a is an exemplary block diagram of a decoding system 10 provided in an embodiment of the present application, such as a video decoding system 10 (or simply, decoding system 10) that can utilize the techniques of the present application. The video encoder 20 (or simply, encoder 20) and the video decoder 30 (or simply, decoder 30) in the video decoding system 10 represent devices that can be used to perform various techniques according to various examples described in this application.

[0091] As shown in FIG. 1 a , a decoding system 10 includes a source device 12 for providing encoded image data 21 such as an encoded image to a destination device 14 for decoding the encoded image data 21 .

[0092] The source device 12 includes an encoder 20 , and optionally, may include an image source 16 , a preprocessor (or preprocessing unit) 18 such as an image preprocessor, and a communication interface (or communication unit) 22 .

[0093] The image source 16 may include or may be any type of image capture device for capturing real-world images, etc., and / or any type of image generation device, such as a computer graphics processor for generating computer-animated images, or any type of device for acquiring and / or providing real-world images, computer-generated images (e.g., screen content, virtual reality (VR) images, and / or any combination thereof (e.g., augmented reality (AR) images). The image source may be any type of memory or storage that stores any of the above images.

[0094] In order to distinguish the processing performed by the pre-processor (or pre-processing unit) 18 , the image (or image data) 17 may also be referred to as a raw image (or raw image data) 17 .

[0095] The preprocessor 18 is configured to receive raw image data 17 and preprocess the raw image data 17 to obtain a preprocessed image (or preprocessed image data) 19. For example, the preprocessing performed by the preprocessor 18 may include cropping, color format conversion (e.g., from RGB to YCbCr), color grading, or denoising. It will be appreciated that the preprocessor 18 may be an optional component.

[0096] The video encoder (or encoder) 20 is used to receive the pre-processed image data 19 and provide encoded image data 21 (which will be further described below with reference to FIG. 2 and the like).

[0097] The communication interface 22 in the source device 12 can be used to receive the encoded image data 21 and send the encoded image data 21 (or any other processed version) to another device such as the destination device 14 or any other device through the communication channel 13 for storage or direct reconstruction.

[0098] The destination device 14 includes a decoder 30 and, in addition or alternatively, may include a communication interface (or communication unit) 28 , a post-processor (or post-processing unit) 32 , and a display device 34 .

[0099] The communication interface 28 in the destination device 14 is used to receive the encoded image data 21 (or any other processed version) directly from the source device 12 or from any other source device such as a storage device, for example, the storage device is a encoded image data storage device, and provide the encoded image data 21 to the decoder 30.

[0100] The communication interface 22 and the communication interface 28 can be used to send or receive encoded image data (or encoded data) 21 through a direct communication link between the source device 12 and the destination device 14, such as a direct wired or wireless connection, or through any type of network, such as a wired network, a wireless network or any combination thereof, any type of private network and public network or any combination thereof.

[0101] For example, the communication interface 22 may be used to encapsulate the encoded image data 21 into a suitable format such as a message, and / or process the encoded image data using any type of transmission coding or processing for transmission over a communication link or network.

[0102] The communication interface 28 corresponds to the communication interface 22 , and can be used, for example, to receive transmission data and process the transmission data using any type of corresponding transmission decoding or processing and / or decapsulation to obtain the encoded image data 21 .

[0103] Both the communication interface 22 and the communication interface 28 can be configured as a unidirectional communication interface as indicated by the arrow pointing from the source device 12 to the corresponding communication channel 13 of the destination device 14 in Figure 1a, or a bidirectional communication interface, and can be used to send and receive messages, etc. to establish a connection, confirm and exchange any other information related to the communication link and / or data transmission such as encoded image data transmission, etc.

[0104] The video decoder (or decoder) 30 is used to receive the encoded image data 21 and provide decoded image data (or decoded image data) 31 (which will be further described below with reference to FIG. 3 and the like).

[0105] The post-processor 32 is configured to post-process the decoded image data 31 (also referred to as reconstructed image data), such as the decoded image, to obtain post-processed image data 33, such as the post-processed image. The post-processing performed by the post-processing unit 32 may include, for example, color format conversion (e.g., from YCbCr to RGB), color grading, cropping, or resampling, or any other processing for generating the decoded image data 31 for display on a display device 34, etc.

[0106] The display device 34 is configured to receive the post-processed image data 33 and display the image to a user or viewer. The display device 34 may be or include any type of display for displaying the reconstructed image, such as an integrated or external display screen or monitor. For example, the display screen may include a liquid crystal display (LCD), an organic light emitting diode (OLED) display, a plasma display, a projector, a micro-LED display, a liquid crystal on silicon (LCoS) display, a digital light processor (DLP), or any other type of display screen.

[0107] The decoding system 10 also includes a training engine 25, which is used to train the encoder 20 (especially the entropy coding unit 270 in the encoder 20) or the decoder 30 (especially the entropy decoding unit 304 in the decoder 30) to perform entropy coding on the image block to be encoded according to the estimated probability distribution. For a detailed description of the training engine 25, please refer to the following method test embodiment.

[0108] Although FIG1a shows source device 12 and destination device 14 as separate devices, device embodiments may also include both source device 12 and destination device 14 or the functions of both source device 12 and destination device 14, that is, both source device 12 or the corresponding functions and destination device 14 or the corresponding functions. In these embodiments, source device 12 or the corresponding functions and destination device 14 or the corresponding functions may be implemented using the same hardware and / or software or through separate hardware and / or software or any combination thereof.

[0109] According to the description, the existence and (accurate) division of different units or functions in the source device 12 and / or the destination device 14 shown in FIG. 1 a may vary depending on actual devices and applications, which is obvious to those skilled in the art.

[0110] Please refer to Figure 1b, which is an exemplary block diagram of a video decoding system 40 provided in an embodiment of the present application. The encoder 20 (e.g., video encoder 20) or the decoder 30 (e.g., video decoder 30), or both, can be implemented by processing circuitry in the video decoding system 40 shown in Figure 1b, such as one or more microprocessors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), discrete logic, hardware, video encoding-specific processors, or any combination thereof. Please refer to Figures 2 and 3, Figure 2 is an exemplary block diagram of a video encoder provided in an embodiment of the present application, and Figure 3 is an exemplary block diagram of a video decoder provided in an embodiment of the present application. The encoder 20 can be implemented by processing circuitry 46 to include the various modules discussed with reference to the encoder 20 in Figure 2 and / or any other encoder systems or subsystems described herein. The decoder 30 can be implemented by processing circuitry 46 to include the various modules discussed with reference to the decoder 30 in Figure 3 and / or any other decoder systems or subsystems described herein. The processing circuitry 46 can be used to perform the various operations discussed below. As shown in FIG5 , if part of the technology is implemented in software, the device may store the software instructions in a suitable non-transitory computer-readable storage medium and use one or more processors to execute the instructions in hardware to perform the technology of the present application. One of the video encoder 20 and the video decoder 30 may be integrated into a single device as part of a combined codec (encoder / decoder, CODEC), as shown in FIG1 b.

[0111] The source device 12 and the destination device 14 may include any of a variety of devices, including any type of handheld or fixed device, such as a notebook computer or laptop, a mobile phone, a smart phone, a tablet or a tablet computer, a camera, a desktop computer, a set-top box, a television, a display device, a digital media player, a video game console, a video streaming device (e.g., a content service server or a content distribution server), a broadcast receiving device, a broadcast transmitting device, and a monitoring device, etc., and may not use or use any type of operating system. The source device 12 and the destination device 14 may also be devices in a cloud computing scenario, such as a virtual machine in a cloud computing scenario. In some cases, the source device 12 and the destination device 14 may be equipped with components for wireless communication. Therefore, the source device 12 and the destination device 14 may be wireless communication devices.

[0112] The source device 12 and the destination device 14 may be installed with virtual scene applications (APPs) such as virtual reality (VR), augmented reality (AR), or mixed reality (MR), and may run the VR, AR, or MR applications based on user operations (e.g., click, touch, slide, shake, voice control, etc.). The source device 12 and the destination device 14 may capture images / videos of any objects in the environment through cameras and / or sensors, and then display virtual objects on a display device based on the captured images / videos. The virtual objects may be virtual objects in the VR, AR, or MR scenes (i.e., objects in the virtual environment).

[0113] It should be noted that in the embodiment of the present application, the virtual scene application in the source device 12 and the destination device 14 can be an application built into the source device 12 and the destination device 14 themselves, or it can be an application provided by a third-party service provider and installed by the user. There is no specific limitation on this.

[0114] In addition, the source device 12 and the destination device 14 may be installed with a real-time video transmission application, such as a live broadcast application. The source device 12 and the destination device 14 may capture images / videos through cameras and then display the captured images / videos on a display device.

[0115] In some cases, the video decoding system 10 shown in FIG1a is merely exemplary, and the techniques provided herein may be applicable to video encoding settings (e.g., video encoding or video decoding) that do not necessarily include any data communication between an encoding device and a decoding device. In other examples, data is retrieved from a local memory, sent over a network, and so on. A video encoding device may encode data and store the data in a memory, and / or a video decoding device may retrieve data from a memory and decode the data. In some examples, encoding and decoding are performed by devices that do not communicate with each other but simply encode data to a memory and / or retrieve and decode data from a memory.

[0116] Please refer to Figure 1b, which is an exemplary block diagram of a video decoding system 40 provided in an embodiment of the present application. As shown in Figure 1b, the video decoding system 40 may include an imaging device 41, a video encoder 20, a video decoder 30 (and / or a video encoder / decoder implemented by a processing circuit 46), an antenna 42, one or more processors 43, one or more memory storage devices 44 and / or a display device 45.

[0117] 1b, imaging device 41, antenna 42, processing circuit 46, video encoder 20, video decoder 30, processor 43, memory 44, and / or display device 45 are capable of communicating with one another. In different embodiments, video decoding system 40 may include only video encoder 20 or only video decoder 30.

[0118] In some instances, antenna 42 can be used to transmit or receive an encoded bitstream of video data. Additionally, in some instances, display device 45 can be used to present the video data. Processing circuitry 46 can include application-specific integrated circuit (ASIC) logic, a graphics processor, a general-purpose processor, and the like. Video decoding system 40 can also include an optional processor 43, which can similarly include application-specific integrated circuit (ASIC) logic, a graphics processor, a general-purpose processor, and the like. Furthermore, memory storage 44 can be any type of memory, such as volatile memory (e.g., static random access memory (SRAM), dynamic random access memory (DRAM), etc.) or non-volatile memory (e.g., flash memory). In a non-limiting example, memory storage 44 can be implemented as cache memory. In other instances, processing circuitry 46 can include memory (e.g., cache memory, etc.) for implementing an image buffer, etc.

[0119] In some examples, video encoder 20 implemented by logic circuitry may include an image buffer (e.g., implemented by processing circuitry 46 or memory storage 44) and a graphics processing unit (e.g., implemented by processing circuitry 46). The graphics processing unit may be communicatively coupled to the image buffer. The graphics processing unit may include video encoder 20 implemented by processing circuitry 46 to implement the various modules discussed with reference to FIG. 2 and / or any other encoder systems or subsystems described herein. Logic circuitry may be used to perform the various operations discussed herein.

[0120] In some examples, the video decoder 30 may be implemented by processing circuitry 46 in a similar manner to implement the various modules discussed with reference to the video decoder 30 of FIG. 3 and / or any other decoder systems or subsystems described herein. In some examples, the logic circuitry-implemented video decoder 30 may include an image buffer (implemented by processing circuitry 46 or memory storage 44) and a graphics processing unit (e.g., implemented by processing circuitry 46). The graphics processing unit may be communicatively coupled to the image buffer. The graphics processing unit may include the video decoder 30 implemented by processing circuitry 46 to implement the various modules discussed with reference to FIG. 3 and / or any other decoder systems or subsystems described herein.

[0121] In some examples, antenna 42 may be used to receive an encoded bitstream of video data. As discussed, the encoded bitstream may include data related to the encoded video frames, indicators, index values, mode selection data, etc., as discussed herein, such as data related to encoding partitions (e.g., transform coefficients or quantized transform coefficients, optional indicators (as discussed), and / or data defining encoding partitions). Video decoding system 40 may also include video decoder 30 coupled to antenna 42 and configured to decode the encoded bitstream. Display device 45 is configured to present the video frames.

[0122] It should be understood that for the examples described herein with reference to video encoder 20, video decoder 30 can be configured to perform the reverse process. With respect to signaling syntax elements, video decoder 30 can be configured to receive and parse such syntax elements and decode the associated video data accordingly. In some examples, video encoder 20 can entropy encode the syntax elements into an encoded video bitstream. In such examples, video decoder 30 can parse such syntax elements and decode the associated video data accordingly.

[0123] For ease of description, the embodiments of the present application are described with reference to the universal video coding (VVC) reference software or the high-efficiency video coding (HEVC) developed by the joint collaboration team on video coding (JCT-VC) of the ITU-T video coding experts group (VCEG) and the ISO / IEC motion picture experts group (MPEG). Those skilled in the art will understand that the embodiments of the present application are not limited to HEVC or VVC.

[0124] Encoders and encoding methods

[0125] As shown in FIG2 , the video encoder 20 includes an input terminal (or input interface) 201, a residual calculation unit 204, a transform processing unit 206, a quantization unit 208, an inverse quantization unit 210, an inverse transform processing unit 212, a reconstruction unit 214, a loop filter 220, a decoded picture buffer (DPB) 230, a mode selection unit 260, an entropy coding unit 270, and an output terminal (or output interface) 272. The mode selection unit 260 may include an inter-frame prediction unit 244, an intra-frame prediction unit 254, and a segmentation unit 262. The inter-frame prediction unit 244 may include a motion estimation unit and a motion compensation unit (not shown). The video encoder 20 shown in FIG2 may also be referred to as a hybrid video encoder or a video encoder based on a hybrid video codec.

[0126] 2 , the inter-frame prediction unit is a trained target model (also known as a neural network) that processes an input image, image region, or image block to generate a prediction value for the input image block. For example, the neural network for inter-frame prediction receives an input image, image region, or image block and generates a prediction value for the input image, image region, or image block.

[0127] The residual calculation unit 204, the transform processing unit 206, the quantization unit 208, and the mode selection unit 260 constitute the forward signal path of the encoder 20, while the inverse quantization unit 210, the inverse transform processing unit 212, the reconstruction unit 214, the buffer 216, the loop filter 220, the decoded picture buffer (DPB) 230, the inter-frame prediction unit 244, and the intra-frame prediction unit 254 constitute the backward signal path of the encoder, where the backward signal path of the encoder 20 corresponds to the signal path of the decoder (see decoder 30 in Figure 3). The inverse quantization unit 210, the inverse transform processing unit 212, the reconstruction unit 214, the loop filter 220, the decoded picture buffer 230, the inter-frame prediction unit 244, and the intra-frame prediction unit 254 also constitute the "internal decoder" of the video encoder 20.

[0128] Images and image segmentation (images and blocks)

[0129] Encoder 20 is operable to receive, via input 201 or the like, an image (or image data) 17, for example, an image from a sequence of images forming a video or video sequence. The received image or image data may also be a pre-processed image (or pre-processed image data) 19. For simplicity, the following description uses image 17. Image 17 may also be referred to as a current image or image to be encoded (particularly when distinguishing the current image from other images in video encoding, such as previously encoded and / or decoded images in the same video sequence, i.e., a video sequence that also includes the current image).

[0130] A (digital) image is, or can be considered to be, a two-dimensional array or matrix of pixels with intensity values. The pixels in the array are also referred to as pixels (or pels, short for picture elements). The number of pixels in the array or image in the horizontal and vertical directions (or axes) determines the image size and / or resolution. To represent color, three color components are typically used, meaning that an image can be represented as or include three pixel arrays. In the RBG format or color space, an image includes corresponding arrays of red, green, and blue pixels. However, in video coding, each pixel is typically represented in a luma / chroma format or color space, such as YCbCr, which includes a luma component indicated by Y (sometimes also indicated by L) and two chroma components, indicated by Cb and Cr. The luma component Y represents the brightness or grayscale level intensity (for example, in grayscale images, both are the same), while the two chroma components (abbreviated as chroma) Cb and Cr represent the chroma or color information components. Accordingly, an image in YCbCr format includes a luma pixel array of luma pixel values ​​(Y) and two chroma pixel arrays of chroma values ​​(Cb and Cr). An image in RGB format can be converted or transformed into YCbCr format, and vice versa, a process also known as color conversion or transformation. If the image is black and white, the image may include only a luma pixel array. Accordingly, the image may be, for example, a luma pixel array in monochrome format or a luma pixel array and two corresponding chroma pixel arrays in 4:2:0, 4:2:2, and 4:4:4 color formats.

[0131] In one embodiment, an embodiment of the video encoder 20 may include an image segmentation unit (not shown in FIG. 2 ) for segmenting the image 17 into a plurality of (typically non-overlapping) image blocks 203. These blocks may also be referred to as root blocks, macroblocks (H.264 / AVC) or coding tree blocks (CTBs), or coding tree units (CTUs) in the H.265 / HEVC and VVC standards. The segmentation unit may be used to use the same block size for all images in a video sequence and a corresponding grid of defined block sizes, or to vary the block size between images or subsets or groups of images, and to segment each image into corresponding blocks.

[0132] In other embodiments, the video encoder may be configured to directly receive a block 203 of the image 17, for example, one, several or all blocks constituting the image 17. The image block 203 may also be referred to as a current image block or an image block to be encoded.

[0133] Like image 17, image block 203 is also or can be considered to be a two-dimensional array or matrix of pixels having intensity values ​​(pixel values), but image block 203 is smaller than image 17. In other words, block 203 may include one pixel array (e.g., a luminance array in the case of monochrome image 17, or a luminance array or chrominance array in the case of a color image), or three pixel arrays (e.g., one luminance array and two chrominance arrays in the case of a color image 17), or any other number and / or type of arrays depending on the color format used. The number of pixels in the horizontal and vertical directions (or axes) of block 203 defines the size of block 203. Accordingly, a block may be an M×N (M columns×N rows) pixel array, or an M×N transform coefficient array, etc.

[0134] In one embodiment, the video encoder 20 shown in FIG. 2 is configured to encode the image 17 block by block, for example, performing encoding and prediction on each block 203 .

[0135] In one embodiment, the video encoder 20 shown in FIG2 may also be configured to partition and / or encode an image using slices (also referred to as video slices), where an image may be partitioned or encoded using one or more slices (typically non-overlapping). Each slice may include one or more blocks (e.g., coding tree units (CTUs)) or one or more groups of blocks (e.g., tiles in the H.265 / HEVC / VVC standard and bricks in the VVC standard).

[0136] In one embodiment, the video encoder 20 shown in Figure 2 can also be used to segment and / or encode an image using slices / coding block groups (also called video coding block groups) and / or coding blocks (also called video coding blocks), where the image can be segmented or encoded using one or more slices / coding block groups (usually non-overlapping), each slice / coding block group may include one or more blocks (e.g., CTUs) or one or more coding blocks, etc., where each coding block can be in a shape such as a rectangle and may include one or more complete or partial blocks (e.g., CTUs).

[0137] Residual calculation

[0138] The residual calculation unit 204 is used to calculate the residual block 205 (the prediction block 265 is described in detail later) based on the image block (or original block) 203 and the prediction block 265 in the following manner: for example, the pixel value of the prediction block 265 is subtracted from the pixel value of the image block 203 pixel by pixel (pixel by pixel) to obtain the residual block 205 in the pixel domain.

[0139] Transform

[0140] The transform processing unit 206 is configured to perform a discrete cosine transform (DCT) or a discrete sine transform (DST) on the pixel values ​​of the residual block 205 to obtain transform coefficients 207 in the transform domain. The transform coefficients 207 may also be referred to as transform residual coefficients, representing the residual block 205 in the transform domain.

[0141] The transform processing unit 206 may be used to apply an integerized approximation of the DCT / DST, such as the transform specified for H.265 / HEVC. This integerized approximation is typically scaled by a factor compared to the orthogonal DCT transform. In order to maintain the norm of the residual block after the forward and inverse transforms, other scaling factors are used as part of the transform process. The scaling factor is typically selected based on certain constraints, such as whether the scaling factor is a power of 2 for the shift operation, the bit depth of the transform coefficients, a trade-off between accuracy and implementation cost, etc. For example, a specific scaling factor is specified for the inverse transform on the encoder 20 side by the inverse transform processing unit 212 (and for the corresponding inverse transform on the decoder 30 side by, for example, the inverse transform processing unit 312), and correspondingly, a corresponding scaling factor may be specified for the forward transform on the encoder 20 side by the transform processing unit 206.

[0142] In one embodiment, the video encoder 20 (correspondingly, the transform processing unit 206) may be configured to output transform parameters such as one or more transform types, for example, directly output or output after being encoded or compressed by the entropy coding unit 270, such that the video decoder 30 may receive and use the transform parameters for decoding.

[0143] Quantification

[0144] The quantization unit 208 is configured to quantize the transform coefficients 207 by, for example, scalar quantization or vector quantization to obtain quantized transform coefficients 209 . The quantized transform coefficients 209 may also be referred to as quantized residual coefficients 209 .

[0145] The quantization process may reduce the bit depth associated with some or all of the transform coefficients 207. For example, during quantization, an n-bit transform coefficient may be rounded down to an m-bit transform coefficient, where n is greater than m. The degree of quantization may be modified by adjusting a quantization parameter (QP). For example, for scalar quantization, varying degrees of scaling may be applied to achieve finer or coarser quantization. A smaller quantization step size corresponds to finer quantization, while a larger quantization step size corresponds to coarser quantization. The appropriate quantization step size may be indicated by a quantization parameter (QP). For example, the quantization parameter may be an index into a predefined set of appropriate quantization step sizes. For example, a smaller quantization parameter may correspond to fine quantization (a smaller quantization step size), while a larger quantization parameter may correspond to coarse quantization (a larger quantization step size), or vice versa. Quantization may include dividing by the quantization step size, while the corresponding or inverse dequantization performed by the inverse quantization unit 210, etc., may include multiplying by the quantization step size. Embodiments according to some standards, such as HEVC, may be used to determine the quantization step size using the quantization parameter. Generally, the quantization step size may be calculated based on the quantization parameter using a fixed-point approximation of an equation involving division. Other scaling factors can be introduced for quantization and dequantization to restore the norm of the residual block that may have been modified by the scaling used in the fixed-point approximation of the equations for the quantization step size and the quantization parameter. In one exemplary implementation, the scaling of the inverse transform and dequantization can be combined. Alternatively, a custom quantization table can be used and indicated from the encoder to the decoder in the bitstream, etc. Quantization is a lossy operation, where larger quantization step sizes result in greater losses.

[0146] In one embodiment, the video encoder 20 (correspondingly, the quantization unit 208) may be configured to output a quantization parameter (QP), for example, directly or after being encoded or compressed by the entropy coding unit 270, such that the video decoder 30 may receive and use the quantization parameter for decoding.

[0147] Dequantization

[0148] The inverse quantization unit 210 is configured to perform inverse quantization performed by the quantization unit 208 on the quantized coefficients to obtain dequantized coefficients 211. For example, the inverse quantization scheme performed by the quantization unit 208 may be performed according to or using the same quantization step size as the quantization unit 208. The dequantized coefficients 211 may also be referred to as dequantized residual coefficients 211, and correspond to the transform coefficients 207. However, due to the loss caused by quantization, the dequantized coefficients 211 are generally not identical to the transform coefficients.

[0149] Inverse transform

[0150] The inverse transform processing unit 212 is configured to perform the inverse transform of the transform performed by the transform processing unit 206, such as an inverse discrete cosine transform (DCT) or an inverse discrete sine transform (DST), to obtain a reconstructed residual block 213 (or corresponding dequantized coefficients 213) in the pixel domain. The reconstructed residual block 213 may also be referred to as a transform block 213.

[0151] reconstruction

[0152] The reconstruction unit 214 (e.g., the summer 214) is used to add the transform block 213 (i.e., the reconstructed residual block 213) to the prediction block 265 to obtain the reconstructed block 215 in the pixel domain, for example, by adding the pixel point values ​​of the reconstructed residual block 213 and the pixel point values ​​of the prediction block 265.

[0153] Filtering

[0154] The loop filter unit 220 (or simply "loop filter" 220) is used to filter the reconstructed block 215 to obtain a filter block 221, or generally to filter the reconstructed pixels to obtain filtered pixel values. For example, the loop filter unit is used to smoothly perform pixel conversion or improve video quality. The loop filter unit 220 may include one or more loop filters, such as a deblocking filter, a sample-adaptive offset (SAO) filter, or one or more other filters, such as an adaptive loop filter (ALF), a noise suppression filter (NSF), or any combination thereof. For example, the loop filter unit 220 may include a deblocking filter, an SAO filter, and an ALF filter. The order of the filtering process can be a deblocking filter, an SAO filter, and an ALF filter. For another example, a process called luma mapping with chroma scaling (LMCS) (i.e., an adaptive in-loop reshaper) is added. This process is performed before deblocking. For another example, the deblocking filtering process can also be applied to internal sub-block edges, such as affine sub-block edges, ATMVP sub-block edges, sub-block transform (SBT) edges, and intra sub-partition (ISP) edges. Although the loop filter unit 220 is shown as a loop filter in FIG2 , in other configurations, the loop filter unit 220 can be implemented as a post-loop filter. The filter block 221 can also be referred to as a filter reconstruction block 221.

[0155] In one embodiment, the video encoder 20 (correspondingly, the loop filter unit 220) may be configured to output loop filter parameters (e.g., SAO filter parameters, ALF filter parameters, or LMCS parameters), for example, directly or after being entropy-encoded by the entropy coding unit 270, such that the decoder 30 may receive and use the same or different loop filter parameters for decoding.

[0156] Decoded Image Buffer

[0157] The decoded picture buffer (DPB) 230 may be a reference picture memory that stores reference picture data for use by the video encoder 20 when encoding video data. The DPB 230 may be formed from any of a variety of memory devices, such as dynamic random access memory (DRAM), including synchronous DRAM (SDRAM), magnetoresistive RAM (MRAM), resistive RAM (RRAM), or other types of memory devices. The decoded picture buffer 230 may be used to store one or more filter blocks 221. The decoded picture buffer 230 may also be used to store other previously filtered blocks, such as previously reconstructed and filtered blocks 221, for the same current picture or a different picture, such as a previously reconstructed picture, and may provide a complete previously reconstructed, or decoded, picture (and corresponding reference blocks and pixels) and / or a partially reconstructed current picture (and corresponding reference blocks and pixels), for example, for inter-frame prediction. The decoded image buffer 230 may also be used to store one or more unfiltered reconstructed blocks 215, or generally to store unfiltered reconstructed pixels, for example, reconstructed blocks 215 that have not been filtered by the loop filtering unit 220, or reconstructed blocks or reconstructed pixels that have not undergone any other processing.

[0158] Mode selection (segmentation and prediction)

[0159] The mode selection unit 260 includes a segmentation unit 262, an inter-frame prediction unit 244, and an intra-frame prediction unit 254, which are configured to receive or obtain original image data, such as an original block 203 (current block 203 of the current image 17) and reconstructed image data, such as filtered and / or unfiltered reconstructed pixels or reconstructed blocks of the same (current) image and / or one or more previously decoded images, from the decoded image buffer 230 or other buffer (e.g., a column buffer, not shown in FIG. 2). The reconstructed image data is used as reference image data for prediction, such as inter-frame prediction or intra-frame prediction, to obtain a prediction block 265 or a prediction value 265.

[0160] The mode selection unit 260 may be used to determine or select a partitioning for the current block (including no partitioning) and prediction mode (eg, intra-frame or inter-frame prediction mode), generate a corresponding prediction block 265 , and calculate the residual block 205 and reconstruct the reconstruction block 215 .

[0161] In one embodiment, the mode selection unit 260 may be configured to select a segmentation and prediction mode (e.g., from prediction modes supported or available by the mode selection unit 260) that provides the best match or minimum residual (minimum residual means better compression during transmission or storage), or provides minimum signaling overhead (minimum signaling overhead means better compression during transmission or storage), or simultaneously considers or balances both. The mode selection unit 260 may be configured to determine the segmentation and prediction mode based on rate distortion optimization (RDO), i.e., select the prediction mode that provides minimum rate distortion optimization. Terms such as "best," "lowest," and "optimal" herein do not necessarily refer to "best," "lowest," or "optimal" overall, but may also refer to situations where termination or selection criteria are met, e.g., values ​​exceeding or falling below a threshold or other limit may result in a "suboptimal selection" but reduce complexity and processing time.

[0162] In other words, the partitioning unit 262 may be configured to partition an image in a video sequence into a sequence of coding tree units (CTUs), the CTU 203 being further partitioned into smaller block portions or sub-blocks (again forming blocks), e.g., by iteratively using quad-tree partitioning (QT), binary-tree partitioning (BT), or triple-tree partitioning (TT), or any combination thereof, and for, e.g., performing prediction on each of the block portions or sub-blocks, wherein the mode selection comprises selecting a tree structure for partitioning the block 203 and selecting a prediction mode to be applied to each of the block portions or sub-blocks.

[0163] The segmentation (eg, performed by segmentation unit 262) and prediction processes (eg, performed by inter-prediction unit 244 and intra-prediction unit 254) performed by video encoder 20 are described in detail below.

[0164] segmentation

[0165] The partitioning unit 262 can partition (or divide) an image block (or CTU) 203 into smaller parts, such as square or rectangular blocks. For an image with three pixel arrays, a CTU consists of N×N luminance pixel blocks and two corresponding chrominance pixel blocks. The maximum allowed size of a luminance block in a CTU is specified as 128×128 in the developing Universal Video Coding (VVC) standard, but may be specified to a value other than 128×128, such as 256×256, in the future. The CTUs of an image can be grouped / collected into slices / coding block groups, coding blocks, or bricks. A coding block covers a rectangular area of ​​an image and can be divided into one or more bricks. A brick consists of multiple CTU rows within a coding block. A coding block that is not partitioned into multiple bricks can be called a brick. However, a brick is a true subset of a coding block and is therefore not called a coding block. VVC supports two coding block group modes: raster scan slice / coding block group mode and rectangular slice mode. In raster scan CBG mode, a slice / CBG contains a sequence of CBs from a raster scan of the CBs of an image. In rectangular slice mode, a slice contains multiple bricks of an image that together form a rectangular region of the image. The bricks within a rectangular slice are arranged in the slice's brick raster scan order. These smaller blocks (also called sub-blocks) can be further split into smaller parts. This is also known as tree partitioning or hierarchical tree partitioning, where a root block at, for example, root tree level 0 (hierarchy level 0, depth 0) can be recursively split into two or more blocks at the next lower tree level, such as nodes at tree level 1 (hierarchy level 1, depth 1). These blocks can in turn be split into two or more blocks at the next lower level, such as tree level 2 (hierarchy level 2, depth 2), and so on, until the partitioning is complete (because an end criterion is met, such as reaching a maximum tree depth or minimum block size). Blocks that are not further split are also called leaf blocks or leaf nodes of the tree. A tree divided into two parts is called a binary tree (BT), a tree divided into three parts is called a ternary tree (TT), and a tree divided into four parts is called a quadtree (QT).

[0166] For example, a coding tree unit (CTU) may be or include a CTB for luma pixels, two corresponding CTBs for chroma pixels of an image with a three-pixel array, or a CTB for pixels of a monochrome image, or a CTB for pixels of an image encoded using three independent color planes and syntax structures for encoding pixels. Accordingly, a coding tree block (CTB) may be an N×N block of pixels, where N may be set to a value such that a component is divided into CTBs, which is known as partitioning. A coding unit (CU) may be or include a coding block of luma pixels, two corresponding coding blocks for chroma pixels of an image with a three-pixel array, or a coding block of pixels of a monochrome image, or a coding block of pixels of an image encoded using three independent color planes and syntax structures for encoding pixels. Accordingly, a coding block (CB) may be an M×N block of pixels, where M and N may be set to a value such that a CTB is divided into coding blocks, which is known as partitioning.

[0167] For example, in an embodiment, according to HEVC, a coding tree unit (CTU) can be divided into multiple CUs using a quadtree structure represented as a coding tree. A decision is made at the leaf-CU level whether to use inter-frame (temporal) prediction or intra-frame (spatial) prediction to encode an image area. Each leaf-CU can be further divided into one, two, or four PUs according to the PU partition type. The same prediction process is used within a PU, and relevant information is transmitted to the decoder in units of PUs. After applying the prediction process according to the PU partition type to obtain a residual block, the leaf-CU can be divided into transform units (TUs) according to other quadtree structures similar to the coding tree for the CU.

[0168] For example, in an embodiment, according to the latest video coding standard currently under development (called Versatile Video Coding (VVC), a combined quadtree of nested multi-type trees (such as binary trees and ternary trees) is used to divide the segment structure for partitioning the coding tree unit. In the coding tree structure within the coding tree unit, the CU can be square or rectangular. For example, the coding tree unit (CTU) is first partitioned by the quadtree structure. The quadtree leaf nodes are further partitioned by the multi-type tree structure. The multi-type tree structure has four partition types: vertical binary tree partition (SPLIT_BT_VER), horizontal binary tree partition (SPLIT_BT_HOR), vertical ternary tree partition The multi-type tree leaf nodes are called coding units (CUs), unless the CU is too large for the maximum transform length, such segmentation is used for prediction and transform processing without any other splitting. In most cases, this means that the block sizes of CUs, PUs, and TUs in the coding block structure of the quadtree nested multi-type tree are the same. This exception occurs when the maximum supported transform length is less than the width or height of the color components of the CU. VVC has developed a unique signaling mechanism for the split partitioning information in the coding structure with quadtree nested multi-type trees. In the signaling mechanism, the coding The tree unit (CTU) as the root of the quadtree is first split by the quadtree structure. Then each quadtree leaf node (when large enough) is further split into a multi-type tree structure. In the multi-type tree structure, the first flag (mtt_split_cu_flag) is used to indicate whether the node is further split. When the node is further split, the second flag (mtt_split_cu_vertical_flag) is used to indicate the division direction, and the third flag (mtt_split_cu_binary_flag) is used to indicate whether the division is a binary tree division or a ternary tree division. According to mtt_split_c The values ​​of u_vertical_flag and mtt_split_cu_binary_flag allow the decoder to derive the multi-type tree splitting mode (MttSplitMode) of the CU based on predefined rules or tables. It should be noted that for certain designs, such as the 64×64 luminance block and 32×32 chroma pipeline design in the VVC hardware decoder, TT splitting is not allowed when the width or height of the luminance coding block is greater than 64. TT splitting is also not allowed when the width or height of the chroma coding block is greater than 32. The pipeline design divides the image into multiple virtual pipeline data units (VPDUs), and each VPDU is defined as a non-overlapping unit in the image. In the hardware decoder, consecutive VPDUs are processed simultaneously in multiple pipeline stages.In most pipeline stages, the VPDU size is roughly proportional to the buffer size, so it is desirable to keep the VPDU small. In most hardware decoders, the VPDU size can be set to the maximum transform block (TB) size. However, in VVC, the ternary tree (TT) and binary tree (BT) partitioning may increase the VPDU size.

[0169] In addition, it should be noted that when a part of the tree node block exceeds the bottom or the right boundary of the image, the tree node block is forcibly divided until all pixels of each coding CU are located within the image boundary.

[0170] For example, the intra sub-partitions (ISP) tool may divide the luma intra prediction block into two or four sub-partitions vertically or horizontally according to the block size.

[0171] In one example, mode select unit 260 of video encoder 20 may be used to perform any combination of the segmentation techniques described above.

[0172] As described above, the video encoder 20 is configured to determine or select the best or optimal prediction mode from a (predetermined) set of prediction modes. The set of prediction modes may include, for example, intra-frame prediction modes and / or inter-frame prediction modes.

[0173] Intra-frame prediction

[0174] The intra prediction mode set may include 35 different intra prediction modes, for example, non-directional modes like DC (or mean) mode and planar mode, or directional modes as defined in HEVC, or may include 67 different intra prediction modes, for example, non-directional modes like DC (or mean) mode and planar mode, or directional modes as defined in VVC. For example, several traditional angle intra prediction modes are adaptively replaced by wide-angle intra prediction modes for non-square blocks defined in VVC. For another example, in order to avoid the division operation of DC prediction, only the longer side is used to calculate the average value of the non-square block. In addition, the intra prediction result of the planar mode can also be modified using the position dependent intra prediction combination (PDPC) method.

[0175] The intra prediction unit 254 is configured to generate an intra prediction block 265 using reconstructed pixels of adjacent blocks of the same current image according to an intra prediction mode in the intra prediction mode set.

[0176] The intra-frame prediction unit 254 (or generally the mode selection unit 260) is also used to output intra-frame prediction parameters (or generally information indicating the selected intra-frame prediction mode for the block) in the form of syntax elements 266 to the entropy coding unit 270 for inclusion in the encoded image data 21, so that the video decoder 30 can perform operations, such as receiving and using the prediction parameters for decoding.

[0177] The intra prediction modes in HEVC include DC prediction mode, plane prediction mode and 33 angular prediction modes, with a total of 35 candidate prediction modes. The current block can use the pixels of the reconstructed image blocks on the left and above as references for intra prediction. The image blocks in the surrounding area of ​​the current block used for intra prediction of the current block are called reference blocks, and the pixels in the reference blocks are called reference pixels. Among the 35 candidate prediction modes, the DC prediction mode is applicable to areas with flat textures in the current block. All pixels in this area use the average value of the reference pixels in the reference block as prediction; the plane prediction mode is applicable to image blocks with smoothly changing textures. The current block that meets this condition uses the reference pixels in the reference block for bilinear interpolation as the prediction of all pixels in the current block; the angular prediction mode uses the characteristic that the texture of the current block is highly correlated with the texture of the adjacent reconstructed image blocks, and copies the values ​​of the reference pixels in the corresponding reference block along a certain angle as the prediction of all pixels in the current block.

[0178] The HEVC encoder selects an optimal intra-frame prediction mode for the current block from 35 candidate prediction modes and writes this optimal intra-frame prediction mode into the video bitstream. To improve the coding efficiency of intra-frame prediction, the encoder / decoder derives three most probable modes from the optimal intra-frame prediction modes of the reconstructed image blocks in the surrounding area using intra-frame prediction. If the optimal intra-frame prediction mode selected for the current block is one of these three most probable modes, a first index is encoded to indicate that the selected optimal intra-frame prediction mode is one of these three most probable modes; if the selected optimal intra-frame prediction mode is not one of these three most probable modes, a second index is encoded to indicate that the selected optimal intra-frame prediction mode is one of the other 32 modes (other than the aforementioned three most probable modes among the 35 candidate prediction modes). The HEVC standard uses a 5-bit fixed-length code as the aforementioned second index.

[0179] The HEVC encoder derives the three most probable modes by selecting the optimal intra-frame prediction modes of the left and upper neighboring image blocks of the current block and adding them to a set. If these two optimal intra-frame prediction modes are the same, only one is retained in the set. If these two optimal intra-frame prediction modes are the same and both are angular prediction modes, two angular prediction modes adjacent to the angular direction are selected and added to the set. Otherwise, the planar prediction mode, the DC mode, and the vertical prediction mode are selected and added to the set in sequence until the number of modes in the set reaches three.

[0180] After the HEVC decoder performs entropy decoding on the bitstream, it obtains the mode information of the current block, which includes an indicator indicating whether the optimal intra-frame prediction mode of the current block is among the three most probable modes, and the index of the optimal intra-frame prediction mode of the current block among the three most probable modes or the index of the optimal intra-frame prediction mode of the current block among the other 32 modes.

[0181] Inter-frame prediction

[0182] In a possible implementation, the set of inter-frame prediction modes depends on the available reference image (i.e., at least part of the previously decoded image stored in DBP230 as mentioned above) and other inter-frame prediction parameters, for example, on whether the entire reference image is used or only a part of the reference image is used, such as a search window area around the area of ​​the current block, to search for the best matching reference block, and / or on whether pixel interpolation such as half-pixel, quarter-pixel and / or 1 / 16 interpolation is performed, for example.

[0183] In addition to the above prediction modes, skip mode and / or direct mode may also be employed.

[0184] For example, in extended merge prediction, the merge candidate list of this mode consists of the following five candidate types in order: spatial MVP from spatially neighboring CUs, temporal MVP from collocated CUs, history-based MVP from the FIFO table, pairwise average MVP, and zero MV. Decoder-side motion vector refinement (DMVR) based on bilateral matching can be used to increase the accuracy of the MV in merge mode. Merge mode with MVD (MMVD) is derived from merge mode with motion vector difference. The MMVD flag is sent immediately after the skip flag and merge flag to specify whether the CU uses MMVD mode. A CU-level adaptive motion vector resolution (AMVR) scheme can be used. AMVR supports encoding the CU's MVD with different precisions. The MVD of the current CU is adaptively selected based on the prediction mode of the current CU. When the CU is encoded in merge mode, the combined inter / intra prediction (CIIP) mode can be applied to the current CU. The CIIP prediction is obtained by weighted averaging the inter and intra prediction signals. For affine motion compensation prediction, the affine motion field of the block is described by the motion information of 2 control points (4 parameters) or 3 control points (6 parameters) motion vectors. Subblock-based temporal motion vector prediction (SbTMVP) is similar to the temporal motion vector prediction (TMVP) in HEVC, but it predicts the motion vector of the sub-CU within the current CU. Bidirectional optical flow (BDOF), formerly known as BIO, is a simplified version that reduces calculations, especially in terms of the number of multiplications and the size of the multipliers. In the triangle partitioning mode, the CU is evenly divided into two triangular parts using diagonal partitioning and anti-diagonal partitioning. In addition, the bidirectional prediction mode is extended based on the simple average to support the weighted average of the two prediction signals.

[0185] The inter-frame prediction unit 244 may include a motion estimation (ME) unit and a motion compensation (MC) unit (both not shown in FIG. 2 ). The motion estimation unit may be configured to receive or obtain an image block 203 (the current image block 203 of the current image 17 ) and a decoded image 231 , or at least one or more previously reconstructed blocks, e.g., reconstructed blocks of one or more other / different previously decoded images 231 , to perform motion estimation. For example, a video sequence may include the current image and the previously decoded image 231 , or in other words, the current image and the previously decoded image 231 may be part of or form a sequence of images forming the video sequence.

[0186] For example, the encoder 20 may be configured to select a reference block from a plurality of reference blocks of the same or different images in a plurality of other images, and provide the reference image (or reference image index) and / or the offset (spatial offset) between the position (x, y coordinates) of the reference block and the position of the current block as an inter-frame prediction parameter to the motion estimation unit. This offset is also referred to as a motion vector (MV).

[0187] The motion compensation unit is configured to obtain, for example, receive, inter-frame prediction parameters and perform inter-frame prediction based on or using the inter-frame prediction parameters to obtain an inter-frame prediction block 246. The motion compensation performed by the motion compensation unit may include extracting or generating a prediction block based on a motion / block vector determined by motion estimation, and may also include performing interpolation with sub-pixel accuracy. Interpolation filtering can generate pixel points of other pixels from pixel points of known pixels, thereby potentially increasing the number of candidate prediction blocks that can be used to encode the image block. Upon receiving a motion vector corresponding to a PU of the current image block, the motion compensation unit may locate the prediction block pointed to by the motion vector in one of the reference picture lists.

[0188] The motion compensation unit may also generate syntax elements associated with blocks and video slices for use by video decoder 30 when decoding image blocks of a video slice. In addition to, or in lieu of, slices and corresponding syntax elements, coding block groups and / or coding blocks and corresponding syntax elements may be generated or used.

[0189] In the process of obtaining a candidate motion vector list in an advanced motion vector prediction (AMVP) mode, motion vectors (MVs) that can be added to the candidate motion vector list as alternatives include MVs of spatially and temporally adjacent image blocks of a current block, wherein the MVs of spatially adjacent image blocks can further include the MVs of a left candidate image block located to the left of the current block and the MVs of an upper candidate image block located above the current block. For example, please refer to FIG. 4 , which is an exemplary schematic diagram of candidate image blocks provided in an embodiment of the present application. As shown in FIG. 4 , the set of left candidate image blocks includes {A0, A1}, the set of upper candidate image blocks includes {B0, B1, B2}, and the set of temporally adjacent candidate image blocks includes {C, T}. All three sets can be added to the candidate motion vector list as alternatives. However, according to existing coding standards, the maximum length of the candidate motion vector list for AMVP is 2. Therefore, it is necessary to determine the MVs of up to two image blocks to be added to the candidate motion vector list from the three sets according to a prescribed order. The order may be to give priority to the set of candidate image blocks {A0, A1} to the left of the current block (consider A0 first, and then consider A1 if A0 is not available), then consider the set of candidate image blocks {B0, B1, B2} above the current block (consider B0 first, and then consider B1 if B0 is not available, and then consider B2 if B1 is not available), and finally consider the set of candidate image blocks {C, T} that are adjacent to the current block in the time domain (consider T first, and then consider C if T is not available).

[0190] After obtaining the candidate motion vector list, the optimal MV is determined from the candidate motion vector list using the rate distortion cost (RD cost), and the candidate motion vector with the smallest RD cost is used as the motion vector predictor (MVP) of the current block. The rate distortion cost is calculated using the following formula:

[0191] J=SAD+λR

[0192] Wherein, J represents RD cost, SAD is the sum of absolute differences (SAD) between the pixel values ​​of the predicted block obtained after motion estimation using the candidate motion vector and the pixel values ​​of the current block, R represents the bit rate, and λ represents the Lagrange multiplier.

[0193] The encoder passes the index of the determined MVP in the candidate motion vector list to the decoder. Furthermore, a motion search can be performed within a neighborhood centered on the MVP to obtain the actual motion vector of the current block. The encoder calculates the motion vector difference (MVD) between the MVP and the actual motion vector and also passes the MVD to the decoder. The decoder parses the index, finds the corresponding MVP in the candidate motion vector list based on the index, parses the MVD, and adds the MVD to the MVP to obtain the actual motion vector of the current block.

[0194] When obtaining the candidate motion information list in Merge mode, the motion information that can be added to the candidate motion information list includes the motion information of spatially or temporally adjacent image blocks to the current block. For spatially and temporally adjacent image blocks, refer to Figure 4. The spatially adjacent candidate motion information in the candidate motion information list comes from five spatially adjacent blocks (A0, A1, B0, B1, and B2). If the spatially adjacent blocks are unavailable or are intra-predicted, their motion information is not added to the candidate motion information list. The temporal candidate motion information for the current block is obtained by scaling the MV of the corresponding block in the reference frame based on the picture order count (POC) of the reference frame and the current frame. The block at position T in the reference frame is first determined to be available. If not, the block at position C is selected. After obtaining the candidate motion information list, the optimal motion information from the candidate motion information list is determined using the RD cost as the motion information for the current block. The encoder transmits the index of the optimal motion information in the candidate motion information list (denoted as the merge index) to the decoder.

[0195] Entropy Coding

[0196] The entropy coding unit 270 is configured to apply an entropy coding algorithm or scheme (e.g., a variable length coding (VLC) scheme, a context adaptive VLC (CALVC) scheme, an arithmetic coding scheme, a binarization algorithm, context adaptive binary arithmetic coding (CABAC), syntax-based context-adaptive binary arithmetic coding (SBAC), probability interval partitioning entropy (PIPE) coding, or other entropy coding methods or techniques) to the quantized residual coefficients 209, inter-frame prediction parameters, intra-frame prediction parameters, loop filter parameters, and / or other syntax elements, resulting in coded image data 21 that can be output via an output terminal 272 in the form of a coded bitstream 21, etc., so that the video decoder 30, etc. can receive and use the parameters for decoding. The coded bitstream 21 can be transmitted to the video decoder 30 or stored in a memory for later transmission or retrieval by the video decoder 30.

[0197] Other structural variations of the video encoder 20 may be used to encode the video stream. For example, a non-transform based encoder 20 may directly quantize the residual signal without a transform processing unit 206 for certain blocks or frames. In another implementation, the encoder 20 may have the quantization unit 208 and the inverse quantization unit 210 combined into a single unit.

[0198] Decoder and decoding method

[0199] As shown in FIG3 , a video decoder 30 is configured to receive coded image data 21 (e.g., a coded bitstream 21) coded by, for example, an encoder 20, and obtain a decoded image 331. The coded image data or bitstream includes information for decoding the coded image data, such as data representing image blocks of a coded video slice (and / or coding block group or coding block) and related syntax elements.

[0200] 3 , decoder 30 includes an entropy decoding unit 304, an inverse quantization unit 310, an inverse transform processing unit 312, a reconstruction unit 314 (e.g., summer 314), a loop filter 320, a decoded picture buffer (DBP) 330, a mode application unit 360, an inter-prediction unit 344, and an intra-prediction unit 354. Inter-prediction unit 344 may be or include a motion compensation unit. In some examples, video decoder 30 may perform a decoding process that is generally the reverse of the encoding process described with reference to video encoder 100 of FIG. 2 .

[0201] As described with respect to encoder 20, inverse quantization unit 210, inverse transform processing unit 212, reconstruction unit 214, loop filter 220, decoded picture buffer DPB 230, inter-prediction unit 344, and intra-prediction unit 354 also constitute the "built-in decoder" of video encoder 20. Accordingly, inverse quantization unit 310 may be functionally identical to inverse quantization unit 110, inverse transform processing unit 312 may be functionally identical to inverse transform processing unit 122, reconstruction unit 314 may be functionally identical to reconstruction unit 214, loop filter 320 may be functionally identical to loop filter 220, and decoded picture buffer 330 may be functionally identical to decoded picture buffer 230. Therefore, the explanations of the corresponding units and functions of video encoder 20 apply accordingly to the corresponding units and functions of video decoder 30.

[0202] Entropy decoding

[0203] Entropy decoding unit 304 is configured to parse bitstream 21 (or generally, coded image data 21) and perform entropy decoding on the coded image data 21 to obtain quantization coefficients 309 and / or decoded coding parameters (not shown in FIG. 3 ), such as any or all of inter-frame prediction parameters (e.g., reference image indexes and motion vectors), intra-frame prediction parameters (e.g., intra-frame prediction modes or indices), transform parameters, quantization parameters, loop filter parameters, and / or other syntax elements. Entropy decoding unit 304 may be configured to apply a decoding algorithm or scheme corresponding to the coding scheme of entropy coding unit 270 of encoder 20. Entropy decoding unit 304 may also be configured to provide inter-frame prediction parameters, intra-frame prediction parameters, and / or other syntax elements to mode application unit 360, as well as to provide other parameters to other units of decoder 30. Video decoder 30 may receive syntax elements at the video slice and / or video block level. In addition to, or in lieu of, slices and corresponding syntax elements, coding block groups and / or coding blocks and corresponding syntax elements may also be received or used.

[0204] Dequantization

[0205] The inverse quantization unit 310 may be configured to receive a quantization parameter (QP) (or generally information related to inverse quantization) and quantization coefficients from the encoded image data 21 (e.g., parsed and / or decoded by the entropy decoding unit 304), and inverse quantize the decoded quantization coefficients 309 based on the quantization parameter to obtain inverse quantization coefficients 311, which may also be referred to as transform coefficients 311. The inverse quantization process may include using the quantization parameter calculated by the video encoder 20 for each video block in the video slice to determine a degree of quantization, and thus a degree of inverse quantization to be performed.

[0206] Inverse transform

[0207] The inverse transform processing unit 312 may be configured to receive the dequantized coefficients 311, also referred to as transform coefficients 311, and apply a transform to the dequantized coefficients 311 to obtain a reconstructed residual block 213 in the pixel domain. The reconstructed residual block 213 may also be referred to as a transform block 313. The transform may be an inverse transform, such as an inverse DCT, an inverse DST, an inverse integer transform, or a conceptually similar inverse transform process. The inverse transform processing unit 312 may also be configured to receive transform parameters or corresponding information from the encoded image data 21 (e.g., parsed and / or decoded by the entropy decoding unit 304) to determine the transform to be applied to the dequantized coefficients 311.

[0208] reconstruction

[0209] The reconstruction unit 314 (eg, summer 314 ) is configured to add the reconstructed residual block 313 to the prediction block 365 to obtain the reconstructed block 315 in the pixel domain, eg, by adding the pixel values ​​of the reconstructed residual block 313 and the pixel values ​​of the prediction block 365 .

[0210] Filtering

[0211] The loop filter unit 320 (in or after the encoding loop) is used to filter the reconstructed block 315 to obtain a filter block 321, thereby smoothly performing pixel conversion or improving video quality. The loop filter unit 320 may include one or more loop filters, such as a deblocking filter, a sample-adaptive offset (SAO) filter, or one or more other filters, such as an adaptive loop filter (ALF), a noise suppression filter (NSF), or any combination. For example, the loop filter unit 220 may include a deblocking filter, an SAO filter, and an ALF filter. The order of the filtering process can be a deblocking filter, an SAO filter, and an ALF filter. For another example, a process called luma mapping with chroma scaling (LMCS) (i.e., an adaptive in-loop reshaper) is added. This process is performed before deblocking. For another example, the deblocking filtering process can also be applied to internal sub-block edges, such as affine sub-block edges, ATMVP sub-block edges, sub-block transform (SBT) edges, and intra sub-partition (ISP) edges. Although the loop filter unit 320 is shown as a loop filter in Figure 3, in other configurations, the loop filter unit 320 can be implemented as a post-loop filter.

[0212] Decoded Image Buffer

[0213] The decoded video blocks 321 of one picture are then stored in a decoded picture buffer 330, which stores the decoded picture 331 as a reference picture for subsequent motion compensation of other pictures and / or for respective output displays.

[0214] The decoder 30 is used to output the decoded image 311 through the output terminal 312, etc., for display to the user or for the user to view.

[0215] predict

[0216] The inter-frame prediction unit 344 may be functionally identical to the inter-frame prediction unit 244 (particularly the motion compensation unit), and the intra-frame prediction unit 354 may be functionally identical to the inter-frame prediction unit 254 and may determine the partitioning or segmentation and perform prediction based on the segmentation and / or prediction parameters or corresponding information received from the coded image data 21 (e.g., parsed and / or decoded by the entropy decoding unit 304). The mode application unit 360 may be configured to perform prediction (intra-frame or inter-frame prediction) for each block based on the reconstructed image, block, or corresponding pixel point (filtered or unfiltered), resulting in a prediction block 365.

[0217] When the video slice is encoded as an intra-coded (I) slice, the intra-prediction unit 354 in the mode application unit 360 is configured to generate a prediction block 365 for the image block of the current video slice based on the indicated intra-prediction mode and data from previously decoded blocks of the current image. When the video image is encoded as an inter-coded (i.e., B or P) slice, the inter-prediction unit 344 (e.g., a motion compensation unit) in the mode application unit 360 is configured to generate a prediction block 365 for the video block of the current video slice based on the motion vector and other syntax elements received from the entropy decoding unit 304. For inter-prediction, these prediction blocks can be generated from one of the reference pictures in one of the reference picture lists. Video decoder 30 can construct reference frame list 0 and list 1 using a default construction technique based on the reference pictures stored in DPB 330. The same or similar processes may be applied to embodiments of coding block groups (e.g., video coding block groups) and / or coding blocks (e.g., video coding blocks) in addition to or instead of slices (e.g., video slices), e.g., video may be encoded using I, P, or B coding block groups and / or coding blocks.

[0218] Mode application unit 360 is configured to determine prediction information for video blocks of a current video slice by parsing motion vectors and other syntax elements, and to use the prediction information to generate a prediction block for the current video block being decoded. For example, mode application unit 360 uses received syntax elements to determine the prediction mode (e.g., intra prediction or inter prediction) used to encode the video blocks of the video slice, the inter prediction slice type (e.g., B slice, P slice, or GPB slice), construction information for one or more reference picture lists for the slice, motion vectors for each inter-coded video block in the slice, inter prediction status for each inter-coded video block in the slice, and other information to decode the video blocks within the current video slice. In addition to or in lieu of slices (e.g., video slices), the same or similar processes may be applied to embodiments involving coding block groups (e.g., video coding block groups) and / or coding blocks (e.g., video coding blocks), for example, where video may be encoded using I, P, or B coding block groups and / or coding blocks.

[0219] In one embodiment, the video encoder 30 of FIG3 may also be configured to partition and / or decode an image using slices (also referred to as video slices), where an image may be partitioned or decoded using one or more (typically non-overlapping) slices. Each slice may include one or more blocks (e.g., CTUs) or one or more groups of blocks (e.g., coding blocks in the H.265 / HEVC / VVC standard and bricks in the VVC standard).

[0220] In one embodiment, the video decoder 30 shown in Figure 3 can also be used to segment and / or decode an image using slices / coding block groups (also called video coding block groups) and / or coding blocks (also called video coding blocks), where the image can be segmented or decoded using one or more slices / coding block groups (usually non-overlapping), each slice / coding block group may include one or more blocks (e.g., CTUs) or one or more coding blocks, etc., where each coding block can be in a shape such as a rectangle and may include one or more complete or partial blocks (e.g., CTUs).

[0221] Other variations of the video decoder 30 may be used to decode the encoded image data 21. For example, the decoder 30 may generate an output video stream without the loop filter unit 320. For example, a non-transform-based decoder 30 may directly inverse quantize the residual signal without the inverse transform processing unit 312 for certain blocks or frames. In another implementation, the video decoder 30 may have the inverse quantization unit 310 and the inverse transform processing unit 312 combined into a single unit.

[0222] It should be understood that the processing result of the current step can be further processed in the encoder 20 and the decoder 30 and then output to the next step. For example, after interpolation filtering, motion vector derivation, or loop filtering, the processing result of interpolation filtering, motion vector derivation, or loop filtering can be further operated on, such as clipping or shifting operations.

[0223] It should be noted that further operations can be performed on the derived motion vector of the current block (including but not limited to the control point motion vector of the affine mode, the sub-block motion vector of the affine, planar, ATMVP mode, the temporal motion vector, etc.). For example, the value of the motion vector is limited to a predefined range based on the representation bit of the motion vector. If the representation bit of the motion vector is bitDepth, the range is -2^(bitDepth-1) to 2^(bitDepth-1)-1, where "^" represents a power. For example, if bitDepth is set to 16, the range is -32768 to 32767; if bitDepth is set to 18, the range is -131072 to 131071. For example, the value of the derived motion vector (e.g., the MV of four 4×4 sub-blocks in an 8×8 block) is limited so that the maximum difference between the integer parts of the four 4×4 sub-block MVs does not exceed N pixels, for example, not more than 1 pixel. Two methods of limiting the motion vector based on bitDepth are provided here.

[0224] Although the above embodiments primarily describe video coding, it should be noted that embodiments of the decoding system 10, encoder 20, and decoder 30, as well as other embodiments described herein, may also be used for still image processing or coding, i.e., processing or coding a single image in a video codec that is independent of any previous or subsequent images. In general, if image processing is limited to a single image 17, the inter-frame prediction unit 244 (encoder) and the inter-frame prediction unit 344 (decoder) may not be available. All other functionalities (also referred to as tools or techniques) of the video encoder 20 and video decoder 30 are also applicable to still image processing, such as residual calculation 204 / 304, transform 206, quantization 208, inverse quantization 210 / 310, (inverse) transform 212 / 312, segmentation 262 / 362, intra-frame prediction 254 / 354, and / or loop filtering 220 / 320, entropy coding 270, and entropy decoding 304.

[0225] Please refer to Figure 5, which is an exemplary block diagram of a video decoding device 500 provided in an embodiment of the present application. Video decoding device 500 is suitable for implementing the disclosed embodiments described herein. In one embodiment, video decoding device 500 can be a decoder, such as the video decoder 30 in Figure 1a, or an encoder, such as the video encoder 20 in Figure 1a.

[0226] Video decoding device 500 includes: an input port 510 (or input port 510) and a receiver unit (Rx) 520 for receiving data; a processor, logic unit, or central processing unit (CPU) 530 for processing data; for example, processor 530 may be a neural network processor 530; a transmitter unit (Tx) 540 and an output port 550 (or output port 550) for transmitting data; and a memory 560 for storing data. Video decoding device 500 may also include optical-to-electrical (OE) components and electrical-to-optical (EO) components coupled to input port 510, receiver unit 520, transmitter unit 540, and output port 550 for outputting or transmitting optical or electrical signals.

[0227] The processor 530 is implemented in hardware and software. The processor 530 can be implemented as one or more processor chips, cores (e.g., multi-core processors), FPGAs, ASICs, and DSPs. The processor 530 communicates with the input port 510, the receiving unit 520, the transmitting unit 540, the output port 550, and the memory 560. The processor 530 includes a decoding module 570 (e.g., a neural network-based decoding module 570). The decoding module 570 implements the embodiments disclosed above. For example, the decoding module 570 performs, processes, prepares, or provides various encoding operations. Therefore, the decoding module 570 provides substantial improvements to the functionality of the video decoding device 500 and affects the switching of the video decoding device 500 to different states. Alternatively, the decoding module 570 is implemented by instructions stored in the memory 560 and executed by the processor 530.

[0228] Memory 560 includes one or more disks, tape drives, and solid-state drives and can be used as overflow data storage for storing programs when such programs are selected for execution, and for storing instructions and data read during program execution. Memory 560 can be volatile and / or non-volatile and can be read-only memory (ROM), random access memory (RAM), ternary content-addressable memory (TCAM), and / or static random-access memory (SRAM).

[0229] Please refer to FIG. 6 , which is an exemplary block diagram of an apparatus 600 provided in an embodiment of the present application. The apparatus 600 may be used as either or both of the source device 12 and the destination device 14 in FIG. 1 a .

[0230] The processor 602 in the apparatus 600 may be a central processing unit. Alternatively, the processor 602 may be any other type of device or devices, now available or developed in the future, capable of manipulating or processing information. While the disclosed implementations may be implemented using a single processor, such as the processor 602 shown, using more than one processor may provide greater speed and efficiency.

[0231] In one implementation, the memory 604 in the apparatus 600 may be a read-only memory (ROM) device or a random access memory (RAM) device. Any other suitable type of storage device may be used as the memory 604. The memory 604 may include code and data 606 that are accessed by the processor 602 via a bus 612. The memory 604 may also include an operating system 608 and application programs 610, which include at least one program that allows the processor 602 to perform the methods described herein. For example, the application programs 610 may include applications 1 through N, as well as a video decoding application that performs the methods described herein.

[0232] The apparatus 600 may also include one or more output devices, such as a display 618. In one example, the display 618 may be a touch-sensitive display that combines a display with touch-sensitive elements that can be used to sense touch input. The display 618 may be coupled to the processor 602 via the bus 612.

[0233] Although bus 612 in device 600 is described herein as a single bus, bus 612 may include multiple buses. Furthermore, secondary storage may be directly coupled to other components of device 600 or accessed via a network, and may include a single integrated unit such as a memory card or multiple units such as multiple memory cards. Thus, device 600 may have a variety of configurations.

[0234] Since the embodiments of the present application involve the application of neural networks, in order to facilitate understanding, some nouns or terms used in the embodiments of the present application are explained below, and these nouns or terms are also considered part of the content of the invention.

[0235] (1) Neural Network

[0236] A neural network (NN) is a machine learning model. A neural network can be composed of neural units. A neural unit can refer to an operation unit with xs and intercept 1 as input. The output of the operation unit can be:

[0237]

[0238] Where s = 1, 2, ... n, n is a natural number greater than 1, Ws is the weight of xs, and b is the bias of the neural unit. f is the activation function of the neural unit, which is used to introduce nonlinear characteristics into the neural network to convert the input signal in the neural unit into the output signal. The output signal of the activation function can be used as the input of the next convolutional layer. The activation function can be a sigmoid function. A neural network is a network formed by connecting many of the above-mentioned single neural units together, that is, the output of one neural unit can be the input of another neural unit. The input of each neural unit can be connected to the local receptive field of the previous layer to extract the features of the local receptive field. The local receptive field can be an area composed of several neural units.

[0239] (2) Deep Neural Networks

[0240] A deep neural network (DNN), also known as a multi-layer neural network, can be understood as a neural network with many hidden layers. The "many" here does not have a specific metric. Based on the position of different layers in a DNN, the neural network inside the DNN can be divided into three categories: input layer, hidden layer, and output layer. Generally speaking, the first layer is the input layer, the last layer is the output layer, and the layers in between are all hidden layers. The layers are fully connected, that is, any neuron in the i-th layer must be connected to any neuron in the i+1-th layer. Although DNN looks complicated, the work of each layer is actually not complicated. Simply put, it is the following linear relationship expression: in, is the input vector, is the output vector, is the offset vector, W is the weight matrix (also called coefficient), and α() is the activation function. Each layer is just an input vector After such a simple operation, the output vector Since there are many DNN layers, the coefficient W and the offset vector The definition of these parameters in DNN is as follows: Take the coefficient W as an example: Assume that in a three-layer DNN, the linear coefficient from the 4th neuron in the second layer to the 2nd neuron in the third layer is defined as The superscript 3 represents the layer number of the coefficient W, while the subscript corresponds to the output of the third layer index 2 and the input of the second layer index 4. In summary, the coefficient from the kth neuron in the L-1th layer to the jth neuron in the Lth layer is defined as It's important to note that the input layer has no W parameter. In deep neural networks, more hidden layers allow the network to better capture complex real-world situations. Theoretically, a model with more parameters has higher complexity and greater "capacity," meaning it can handle more complex learning tasks. Training a deep neural network is essentially the process of learning the weight matrix, with the ultimate goal of obtaining the weight matrices for all layers of a trained deep neural network (a weight matrix formed by the vectors W across many layers).

[0241] (3) Convolutional Neural Network

[0242] A convolutional neural network (CNN) is a deep neural network with a convolutional structure and a deep learning architecture. A deep learning architecture involves multiple levels of learning at different levels of abstraction using machine learning algorithms. As a deep learning architecture, a CNN is a feed-forward artificial neural network in which individual neurons respond to input images. A CNN consists of a feature extractor consisting of convolutional and pooling layers. The feature extractor can be thought of as a filter, and the convolution process can be thought of as convolving an input image or feature map with a trainable filter.

[0243] A convolutional layer is a layer of neurons in a convolutional neural network that performs convolution on the input signal. A convolutional layer can include multiple convolution operators, also known as kernels. In image processing, a convolution operator acts as a filter that extracts specific information from the input image matrix. A convolution operator is essentially a weight matrix, which is usually predefined. During the convolution operation, the weight matrix is ​​typically applied horizontally to the input image, pixel by pixel (or two pixels by two pixels, depending on the stride), to extract specific features from the image. The size of the weight matrix should be proportional to the image size. It is important to note that the depth dimension of the weight matrix is ​​the same as the depth dimension of the input image; during the convolution operation, the weight matrix extends across the entire depth of the input image. Therefore, convolution with a single weight matrix produces a convolved output with a single depth dimension. However, in most cases, multiple weight matrices of the same size (row × column) are applied instead. This is known as multiple homogeneous matrices. The outputs of each weight matrix are stacked to form the depth dimension of the convolutional image. The dimension here can be understood as being determined by the "multiple" mentioned above. Different weight matrices can be used to extract different features from the image. For example, one weight matrix is ​​used to extract image edge information, another weight matrix is ​​used to extract specific colors in the image, and yet another weight matrix is ​​used to blur unwanted noise in the image. The multiple weight matrices have the same size (rows × columns), and the feature maps extracted by these multiple weight matrices of the same size are also the same size. The extracted feature maps of the same size are then merged to form the output of the convolution operation. In practical applications, the weight values ​​in these weight matrices require extensive training. The weight matrices formed by the trained weight values ​​can be used to extract information from the input image, allowing the convolutional neural network to make accurate predictions. When a convolutional neural network has multiple convolutional layers, the initial convolutional layers often extract more general features, which can also be called low-level features. As the depth of the convolutional neural network increases, the features extracted by subsequent convolutional layers become increasingly complex, such as high-level semantic features. Features with higher semantics are more applicable to the problem being solved.

[0244] Because it's often necessary to reduce the number of trainable parameters, pooling layers are often periodically introduced after convolutional layers. This can be done in a single convolutional layer followed by a pooling layer, or in a multi-layered system followed by one or more pooling layers. In image processing, the sole purpose of a pooling layer is to reduce the spatial size of an image. Pooling layers can include average pooling and / or max pooling operators, which are used to downsample the input image to produce a smaller image. The average pooling operator calculates the average value of pixel values ​​within a specific range, producing the average pooling result. The max pooling operator takes the pixel with the largest value within a specific range as the max pooling result. Furthermore, just as the size of the weight matrix used in a convolutional layer should be related to the image size, the operators in a pooling layer should also be related to the image size. The output image size after processing by a pooling layer can be smaller than the size of the image input to the pooling layer. Each pixel in the output image represents the average or maximum value of the corresponding subregion of the image input to the pooling layer.

[0245] After being processed by the convolution layer / pooling layer, the convolutional neural network is still not sufficient to output the required output information. Because as mentioned above, the convolution layer / pooling layer only extracts features and reduces the parameters brought by the input image. However, in order to generate the final output information (the required class information or other related information), the convolutional neural network needs to use the neural network layer to generate one or a group of outputs of the required number of classes. Therefore, the neural network layer may include multiple hidden layers, and the parameters contained in the multiple hidden layers can be pre-trained based on relevant training data of a specific task type. For example, the task type may include image recognition, image classification, image super-resolution reconstruction, etc.

[0246] Optionally, after the multiple hidden layers in the neural network layer, an output layer of the entire convolutional neural network is also included. The output layer has a loss function similar to the classification cross entropy, which is specifically used to calculate the prediction error. Once the forward propagation of the entire convolutional neural network is completed, the backpropagation will begin to update the weight values ​​and biases of the aforementioned layers to reduce the loss of the convolutional neural network and the error between the result output by the convolutional neural network through the output layer and the ideal result.

[0247] (4) Recurrent Neural Network

[0248] Recurrent neural networks (RNNs) are designed to process sequential data. In traditional neural network models, each layer is fully connected, from the input layer to the hidden layer to the output layer, while nodes within each layer are disconnected. While these conventional neural networks have solved many difficult problems, they are still inadequate for many others. For example, to predict the next word in a sentence, you generally need to use the previous words, as the previous and next words in a sentence are not independent. RNNs are called recurrent neural networks because the current output of a sequence is dependent on the previous output. Specifically, the network memorizes previous information and applies it to the calculation of the current output. This means that nodes within the hidden layer are no longer disconnected but connected, and the input to a hidden layer includes not only the output of the input layer but also the output of the previous hidden layer. In theory, RNNs can process sequence data of any length. Training an RNN is similar to training a traditional CNN or DNN. This approach also uses the backpropagation algorithm, but with one key difference: if the RNN is expanded, its parameters, such as W, are shared; this is not the case with traditional neural networks, as in the example above. Furthermore, when using gradient descent, the output of each step depends not only on the state of the network at the current step but also on the state of the network at several previous steps. This learning algorithm is called backpropagation through time (BPTT).

[0249] Since we already have convolutional neural networks, why do we still need recurrent neural networks? The reason is simple. Convolutional neural networks assume that elements are independent of each other, and that inputs and outputs are also independent, such as cats and dogs. However, in the real world, many elements are interconnected, such as the changes in stock prices over time. Or, for example, someone says, "I love traveling, and my favorite place is Yunnan. I must visit it someday." Humans should know to fill in the blank with "Yunnan." This is because humans make inferences based on context, but how can machines do the same? That's where RNNs come in. RNNs aim to give machines the ability to remember, like humans do. Therefore, the output of an RNN depends on both the current input and historical memory.

[0250] (5) Loss function

[0251] During the training of a deep neural network, because we want the output of the deep neural network to be as close as possible to the desired predicted value, we can compare the current network's predicted value with the desired target value and then update the weight vector of each layer of the neural network based on the difference between the two. (Of course, before the first update, there is usually an initialization process, which pre-configures the parameters for each layer in the deep neural network.) For example, if the network's predicted value is too high, the weight vector is adjusted to make it predict a lower value. This adjustment is continued until the deep neural network can predict the desired target value or a value very close to the desired target value. Therefore, it is necessary to predefine "how to compare the difference between the predicted value and the target value." This is the loss function (or objective function), which is an important equation used to measure the difference between the predicted value and the target value. For example, the loss function output value (loss) indicates a greater difference, so training a deep neural network becomes a process of minimizing this loss.

[0252] (6) Backpropagation algorithm

[0253] Convolutional neural networks can use the back propagation (BP) algorithm to correct the size of the parameters in the initial super-resolution model during training, reducing the reconstruction error loss of the super-resolution model. Specifically, the forward propagation of the input signal to the output generates an error loss. This error loss information is then backpropagated to update the parameters of the initial super-resolution model, thereby converging the error loss. The BP algorithm is a backward propagation movement dominated by the error loss, aiming to obtain the optimal super-resolution model parameters, such as the weight matrix.

[0254] (7) Generative Adversarial Networks

[0255] Generative adversarial networks (GANs) are a type of deep learning model. They consist of at least two modules: a generative model and a discriminative model. These two modules learn from each other through interaction to produce better outputs. Both the generative and discriminative models can be neural networks, specifically deep neural networks or convolutional neural networks. The basic principle of a GAN is as follows: For example, consider a GAN that generates images. Suppose there are two networks, G (Generator) and D (Discriminator). G is the image generator network, which receives random noise z and generates an image from it, denoted as G(z). D is the discriminator network, which determines whether an image is "real." Its input parameter is x, representing an image. Its output, D(x), represents the probability that x is real. A value of 1 indicates a 100% probability of authenticity, while a value of 0 indicates a high probability of non-authenticity. During the training of this generative adversarial network, the goal of the generative network G is to generate realistic images as much as possible to deceive the discriminative network D, while the goal of the discriminative network D is to distinguish the images generated by G from real images as much as possible. This creates a dynamic "game" between G and D, which is the "game" in "generative adversarial network." Ultimately, under ideal conditions, G can generate images G(z) that are sufficiently realistic, while D has difficulty determining whether the images generated by G are real, i.e., D(G(z)) = 0.5. This results in an excellent generative model G that can be used to generate images.

[0256] FIG7a is a schematic diagram of an application scenario provided by an embodiment of the present application. As shown in FIG7a, the application scenario is that a device acquires data, compresses the acquired data, and then stores the compressed data. The device can integrate the functions of the aforementioned source device and destination device.

[0257] 1. The device obtains data.

[0258] 2. The device compresses the data to obtain compressed data.

[0259] 3. The device stores compressed data.

[0260] It should be understood that the device compresses the data in order to save storage space. Optionally, the device can store the compressed data in an album or a cloud album.

[0261] 4. The device decompresses the compressed data to obtain the data.

[0262] Figure 7b is a schematic diagram of an application scenario provided by an embodiment of the present application. As shown in Figure 7b, the application scenario is that the source device obtains data, compresses the obtained data to obtain compressed data, and then sends the compressed data to the destination device.

[0263] In an embodiment of the present application, the source device may compress the acquired data and transmit it to the destination device, thereby reducing the transmission bandwidth.

[0264] 1. The source device obtains data.

[0265] 2. The source device compresses the data to obtain compressed data.

[0266] 3. The source device sends compressed data to the destination device.

[0267] The source device compresses the data before transmitting it, which can reduce the transmission bandwidth and improve the transmission efficiency.

[0268] 4. The destination device decompresses the compressed data to obtain the data.

[0269] Please refer to Figure 8, which is a flow chart of a coding method 800 provided in an embodiment of the present application. The coding method 800 can be performed by an encoder and a decoder. The coding method 800 is described as a series of steps or operations. It should be understood that the coding method 800 can be performed in various orders and / or occur simultaneously, and is not limited to the execution order shown in Figure 8. As shown in Figure 8, the coding method 800 may include:

[0270] Step 801: The encoder obtains data to be encoded.

[0271] Exemplarily, the encoder obtains data x to be encoded.

[0272] Step 802: The encoder inputs the data to be encoded into the first encoding network to obtain target parameters.

[0273] The target parameter may be the parameter weight of all or part of the convolution and nonlinear activation of the second encoding network.

[0274] Optionally, the first encoding network may include a convolution kernel generator (convolution or fully connected group), which is used to generate target parameters according to the data to be encoded.

[0275] Exemplarily, the encoder inputs the to-be-encoded data x into the first encoding network to obtain the target parameter θ g .

[0276] Step 803: The encoder constructs a second encoding network according to the target parameters.

[0277] For example, the encoder is based on the target parameter θg Construct the second encoding network g a (x;θ g ).

[0278] Step 804: The encoder inputs the data to be encoded into the second encoding network to obtain the first feature.

[0279] The first feature is used to reconstruct the data to be encoded, and the first feature may also be called a content feature. For example, the first feature may be a three-dimensional feature map of the data to be encoded x.

[0280] Exemplarily, the encoder inputs the to-be-encoded data x into the second encoding network g a (x;θ g ) to obtain the first feature y. Where y satisfies y=g a (x;θ g ).

[0281] Step 805: The encoder encodes the first feature to obtain an encoded bitstream (ie, a bitstream to be decoded).

[0282] In one possible implementation, encoding a first feature to obtain an encoded bitstream may include: first, the encoder rounding the first feature to obtain a rounded value of the first feature; then, the encoder performing probability estimation on the rounded value of the first feature to obtain an estimated probability distribution of the rounded value of the first feature; and then, the encoder performing entropy encoding on the rounded value of the first feature based on the estimated probability distribution of the rounded value of the first feature to obtain the encoded bitstream. The rounded value of the first feature may be referred to as a first value feature or a content rounded feature.

[0283] For example, the encoder first rounds the first feature y to obtain the rounded value of the first feature The encoder then rounds the first feature to Perform probability estimation to obtain the estimated probability distribution of the rounded value of the first feature The encoder then estimates the probability distribution of the rounded value of the first feature Rounded value of the first feature Perform entropy coding to obtain a coded bit stream.

[0284] in, satisfy round means rounding.

[0285] satisfy is the entropy estimation network.

[0286] Optionally, the encoder performing a probability estimation on the rounded value of the first feature to obtain an estimated probability distribution of the rounded value of the first feature may include: the encoder performing a probability estimation on the rounded value of the first feature based on first information to obtain the estimated probability distribution of the rounded value of the first feature, wherein the first information includes at least one of context information and side information.

[0287] It is worth mentioning that estimating the probability distribution through context information and side information can improve the accuracy of the estimated probability distribution, thereby reducing the bit rate in the entropy coding process and reducing the entropy coding overhead.

[0288] Step 806: The encoder sends the encoded bitstream to the decoder.

[0289] Step 807: The decoder decodes the encoded bitstream to obtain a rounded value of the first feature.

[0290] In one possible implementation, the decoder decodes the encoded bitstream to obtain the rounded value of the first feature, which may include: the decoder first performs a probability estimation on the rounded value of the first feature in the encoded bitstream to obtain an estimated probability distribution of the rounded value of the first feature; and then the decoder performs entropy decoding on the encoded bitstream according to the estimated probability distribution of the rounded value of the first feature to obtain the rounded value of the first feature.

[0291] Step 808: The decoder inputs the rounded value of the first feature into the decoding network to obtain decoded data.

[0292] Exemplarily, the decoder converts the rounded value of the first feature Input decoding network Get decoded data Among them, the decoded data satisfy The parameter weights for all or part of the convolution and nonlinear activation of the decoding network.

[0293] In the existing encoding method, the encoding network (i.e., the second encoding network) uses fixed parameter weights to extract the content features (i.e., the first features) of the data to be encoded, and then encodes the content features into a code stream (i.e., the encoded code stream) and sends it to the decoding end, and the decoding end decodes and reconstructs the code stream to obtain decoded data. It can be seen that the parameter weights of the encoding network in the prior art are not related to the data to be encoded. In the encoding method provided in the embodiment of the present application, the data to be encoded is first input into the first encoding network, and then the first encoding network generates the parameter weights of the second encoding network according to the data to be encoded, and then the parameter weights of the second encoding network are dynamically adjusted according to the obtained weights, so that the parameter weights of the second encoding network are related to the data to be encoded, thereby increasing the expression ability of the second encoding network, so that the decoded data reconstructed by decoding the code stream obtained by the decoding end through the first feature encoding is closer to the data to be encoded, thereby improving the rate-distortion performance of the encoding and decoding network.

[0294] The encoding and decoding method 800 provided in the embodiment of the present application can be applied to the encoding and decoding system shown in Figure 9. As shown in Figure 9, the encoding and decoding system includes a first encoding network 901, a second encoding network 902, a rounding module 903, an entropy estimation network 904, an entropy encoding module 905, an entropy decoding module 906, and a decoding network 907.

[0295] As shown in Figure 9, the data to be encoded is first input into the first encoding network 901 to obtain target parameters, and then the parameters of the second encoding network 902 are adjusted by the target parameters (that is, the parameter weights of all convolutions or partial convolutions and nonlinear activations of the second encoding network 902 are adjusted by the target parameters).

[0296] The data to be encoded is input into the second encoding network 902 to obtain the first feature.

[0297] The rounding module 903 rounds the first feature to obtain a rounded value of the first feature.

[0298] The entropy estimation network 904 performs probability estimation on the rounded value of the first feature to obtain an estimated probability distribution of the rounded value of the first feature.

[0299] The entropy coding module 905 performs entropy coding on the rounded value of the first feature according to the estimated probability distribution of the rounded value of the first feature to obtain a coded bitstream.

[0300] The entropy decoding module 906 performs entropy decoding on the encoded bitstream according to the estimated probability distribution of the rounded value of the first feature to obtain the rounded value of the first feature.

[0301] The rounded value of the first feature is input into the decoding network 907 to obtain decoded data.

[0302] Please refer to Figure 10, which is a flow chart of a coding and decoding method 1000 provided in an embodiment of the present application. The coding and decoding method 1000 can be performed by an encoder and a decoder. The coding and decoding method 1000 is described as a series of steps or operations. It should be understood that the coding and decoding method 1000 can be performed in various orders and / or occur simultaneously, and is not limited to the execution order shown in Figure 10. As shown in Figure 10, the coding and decoding method 1000 may include:

[0303] Step 1001: The encoder obtains data to be encoded.

[0304] Step 1002: The encoder inputs the data to be encoded into the second encoding network to obtain a first feature.

[0305] The first feature is used to reconstruct the data to be encoded.

[0306] Step 1003: The encoder inputs the data to be encoded into the first encoding network to obtain a second feature.

[0307] Among them, the second feature is used to reconstruct the target parameter. The second feature can also be called a model feature. The target parameter is the parameter weight of all convolutions or partial convolutions and nonlinear activations of the second decoding network.

[0308] In one possible implementation, the encoder can also first split the first feature into two parts (first sub-feature and second sub-feature) based on the channel dimension, one part is used to reconstruct the data to be encoded (first sub-feature), and the other part is used to reconstruct the target parameter (second sub-feature). The encoder then inputs the second sub-feature into the first encoding network to obtain the second feature.

[0309] Optionally, to enable the second feature to be compressed with a smaller bitrate, the second sub-feature can be transformed using a convolutional and fully connected network before being input into the third encoding network. The second sub-feature before transformation can be referred to as an initial model feature, and the second sub-feature after transformation can be referred to as a model feature.

[0310] Step 1004: The encoder encodes the first feature to obtain a first code stream to be decoded.

[0311] Step 1005: The encoder encodes the second feature to obtain a second code stream to be decoded.

[0312] In a possible implementation, the encoder may encode the first feature and the second feature to obtain a code stream to be decoded.

[0313] Step 1006: The encoder sends the first to-be-decoded code stream and the second to-be-decoded code stream to the decoder.

[0314] Step 1007: The decoder decodes the first to-be-decoded bitstream to obtain a rounded value of the first feature.

[0315] In a possible implementation, the decoder decoding the first to-be-decoded code stream to obtain the rounded value of the first feature may include: the decoder performing probability estimation on the rounded value of the first feature in the first to-be-decoded code stream to obtain an estimated probability distribution of the rounded value of the first feature; and performing entropy decoding on the to-be-decoded code stream according to the estimated probability distribution of the rounded value of the first feature to obtain the rounded value of the first feature.

[0316] In one possible implementation, the performing probability estimation on the rounded values ​​of the first feature in the first to-be-decoded bitstream to obtain an estimated probability distribution of the rounded values ​​of the first feature includes: performing probability estimation on the rounded values ​​of the first feature in the first to-be-decoded bitstream based on first information to obtain an estimated probability distribution of the rounded values ​​of the first feature, where the first information includes at least one of context information and side information.

[0317] Step 1008: The decoder decodes the second to-be-decoded bitstream to obtain a rounded value of the second feature.

[0318] The rounded value of the second feature may also be referred to as a model rounded feature.

[0319] In one possible implementation, the decoder decodes a second to-be-decoded bitstream to obtain a rounded value of a second feature, including: the decoder performs probability estimation on the rounded value of the second feature in the second to-be-decoded bitstream to obtain an estimated probability distribution of the rounded value of the second feature; and performs entropy decoding on the second to-be-decoded bitstream according to the estimated probability distribution of the rounded value of the second feature to obtain the rounded value of the second feature.

[0320] In one possible implementation, the performing probability estimation on the rounded values ​​of the second feature in the second to-be-decoded bitstream to obtain an estimated probability distribution of the rounded values ​​of the second feature includes: performing probability estimation on the rounded values ​​of the second feature in the second to-be-decoded bitstream based on first information to obtain an estimated probability distribution of the rounded values ​​of the second feature, where the first information includes at least one of context information and side information.

[0321] Step 1009: The decoder inputs the rounded value of the second feature into the first decoding network to obtain the target parameter.

[0322] Step 1010: The decoder constructs a second decoding network according to the target parameters.

[0323] Step 1011: The decoder inputs the rounded value of the first feature into the second decoding network to obtain decoded data.

[0324] In the existing decoding method, the decoding network (i.e., the second decoding network) uses fixed parameter weights to decode and reconstruct the content value features of the coded data (i.e., the rounded value of the first feature) to obtain decoded data. It can be seen that the parameter weights of the decoding network in the prior art are not related to the data to be decoded. In the embodiment of the present application, the content features and model features of the data to be decoded (i.e., the first feature and the second feature) are encoded into a code stream to be decoded, and then the decoding end obtains the rounded value of the second feature by decoding the code stream to be decoded. The rounded value of the second feature is input into the first decoding network to obtain the parameter weight of the second decoding network, and then the parameter weight of the second decoding network is dynamically adjusted according to the parameter weight, so that the parameter weight of the second decoding network is related to the data to be decoded, thereby improving the expression ability of the second decoding network, and making the decoded data obtained by decoding and reconstructing the second decoding network closer to the data to be encoded, thereby improving the rate-distortion performance of the encoding and decoding network.

[0325] The encoding and decoding method 1000 provided in the embodiment of the present application can be applied to the encoding and decoding system shown in Figure 11. As shown in Figure 11, the encoding and decoding system includes a first encoding network 1101, a second encoding network 1102, a first rounding module 1103, a second rounding module 1104, an entropy estimation network 1105, a first entropy encoding module 1106, a second entropy encoding module 1107, a first entropy decoding module 1108, a second entropy decoding module 1109, a first decoding network 1110, and a second decoding network 1111.

[0326] As shown in FIG11 , the data to be encoded is first input into the second encoding network 1102 to obtain the first feature, and then the data to be encoded is input into the first encoding network 1101 to obtain the second feature.

[0327] The first rounding module 1103 rounds the first feature to obtain a rounded value of the first feature.

[0328] The second rounding module 1104 rounds the second feature to obtain a rounded value of the second feature.

[0329] The entropy estimation network 1105 first performs probability estimation on the rounded value of the first feature to obtain an estimated probability distribution of the rounded value of the first feature, and then performs probability estimation on the rounded value of the second feature to obtain an estimated probability distribution of the rounded value of the second feature.

[0330] The first entropy coding module 1106 performs entropy coding on the rounded value of the first feature according to the estimated probability distribution of the rounded value of the first feature to obtain a first code stream to be decoded.

[0331] The second entropy coding module 1107 performs entropy coding on the rounded value of the second feature according to the estimated probability distribution of the rounded value of the second feature to obtain a second code stream to be decoded.

[0332] The first entropy decoding module 1108 performs entropy decoding on the first to-be-decoded bitstream according to the estimated probability distribution of the rounded value of the first feature to obtain the rounded value of the first feature.

[0333] The second entropy decoding module 1109 performs entropy decoding on the second to-be-decoded bitstream according to the estimated probability distribution of the rounded value of the second feature to obtain the rounded value of the second feature.

[0334] The rounded value of the second feature is first input into the first decoding network 1110 to obtain the target parameters, and then the parameters of the second decoding network 1111 are adjusted according to the target parameters (i.e., the parameter weights of all or part of the convolution and nonlinear activation of the second decoding network 1111 are adjusted by the target parameters).

[0335] The rounded value of the first feature is input into the second decoding network 1111 to obtain decoded data.

[0336] The encoding and decoding method 1000 provided in the embodiment of the present application may also be applied to the encoding and decoding system shown in Figure 12. As shown in Figure 12, the encoding and decoding system includes a first encoding network 1201, a second encoding network 1202, a channel division module 1203, a first rounding module 1204, a second rounding module 1205, an entropy estimation network 1206, a first entropy encoding module 1207, a second entropy encoding module 1208, a first entropy decoding module 1209, a second entropy decoding module 1210, a first decoding network 1211, and a second decoding network 1212.

[0337] As shown in FIG12 , the data to be encoded is first input into the second encoding network 1102 to obtain the first feature.

[0338] The first feature is input into the channel division module 1203 and is divided into a first sub-feature and a second sub-feature in the channel dimension.

[0339] The second sub-feature is input into the first encoding network 1201 to obtain a second feature.

[0340] The first rounding module 1204 rounds the first sub-feature to obtain a rounded value of the first feature.

[0341] The second rounding module 1205 rounds the second feature to obtain a rounded value of the second feature.

[0342] The entropy estimation network 1206 first performs probability estimation on the rounded value of the first feature to obtain an estimated probability distribution of the rounded value of the first feature, and then performs probability estimation on the rounded value of the second feature to obtain an estimated probability distribution of the rounded value of the second feature.

[0343] The first entropy coding module 1207 performs entropy coding on the rounded value of the first feature according to the estimated probability distribution of the rounded value of the first feature to obtain a first code stream to be decoded.

[0344] The second entropy coding module 1208 performs entropy coding on the rounded value of the second feature according to the estimated probability distribution of the rounded value of the second feature to obtain a second code stream to be decoded.

[0345] The first entropy decoding module 1209 performs entropy decoding on the first to-be-decoded bitstream according to the estimated probability distribution of the rounded value of the first feature to obtain the rounded value of the first feature.

[0346] The second entropy decoding module 1210 performs entropy decoding on the second to-be-decoded bitstream according to the estimated probability distribution of the rounded value of the second feature to obtain the rounded value of the second feature.

[0347] The rounded value of the second feature is first input into the first decoding network 1211 to obtain the target parameters, and then the parameters of the second decoding network 1212 are adjusted according to the target parameters (that is, the parameter weights of all or part of the convolution and nonlinear activation of the second decoding network 1212 are adjusted by the target parameters).

[0348] The rounded value of the first feature is input into the second decoding network 1212 to obtain decoded data.

[0349] Please refer to Figure 13, which is a flow chart of a coding and decoding method 1300 provided in an embodiment of the present application. The coding and decoding method 1300 can be performed by an encoder and a decoder. The coding and decoding method 1300 is described as a series of steps or operations. It should be understood that the coding and decoding method 1300 can be performed in various orders and / or occur simultaneously, and is not limited to the execution order shown in Figure 13. As shown in Figure 13, the coding and decoding method 1300 may include:

[0350] Step 1301: The encoder obtains data to be encoded.

[0351] Step 1302: The encoder inputs the data to be encoded into the encoding network to obtain a first feature.

[0352] Step 1303: The encoder encodes the first feature to obtain a code stream to be decoded.

[0353] Step 1304: The encoder sends the code stream to be decoded to the decoder.

[0354] Step 1305: The decoder decodes the code stream to be decoded to obtain a rounded value of the first feature.

[0355] In a possible implementation, the decoder decoding the to-be-decoded bitstream to obtain the rounded value of the first feature may include: the decoder performing probability estimation on the rounded value of the first feature in the to-be-decoded bitstream to obtain an estimated probability distribution of the rounded value of the first feature; and performing entropy decoding on the to-be-decoded bitstream according to the estimated probability distribution of the rounded value of the first feature to obtain the rounded value of the first feature.

[0356] In one possible implementation, performing probability estimation on the rounded values ​​of the first feature in the to-be-decoded bitstream to obtain an estimated probability distribution of the rounded values ​​of the first feature includes: performing probability estimation on the rounded values ​​of the first feature in the to-be-decoded bitstream based on first information to obtain an estimated probability distribution of the rounded values ​​of the first feature, where the first information includes at least one of context information and side information.

[0357] Step 1306: The decoder inputs the rounded value of the first feature into the first decoding network to obtain the target parameter.

[0358] Optionally, the first decoding network may include a convolution kernel generator (convolution or fully connected group), which is used to generate target parameters according to the rounded value of the first feature of the data to be encoded.

[0359] Step 1307: The decoder constructs a second decoding network according to the target parameters.

[0360] Step 1308: The decoder inputs the rounded value of the first feature into the second decoding network to obtain decoded data.

[0361] In the existing decoding method, the decoding network (i.e., the second decoding network) uses fixed parameter weights to decode and reconstruct the content value characteristics of the coded data (i.e., the rounded value of the first feature) to obtain decoded data. It can be seen that the parameter weights of the decoding network in the prior art are not related to the data to be decoded. In the embodiment of the present application, the rounded value of the first feature is obtained by decoding the feature of the data to be decoded (i.e., the first feature) encoded into the code stream to be decoded, and the rounded value of the first feature is input into the first decoding network to obtain the parameter weight of the second decoding network. Then, the parameter weight of the second decoding network is dynamically adjusted according to the parameter weight, so that the parameter weight of the second decoding network is related to the data to be decoded, thereby improving the expression ability of the second decoding network, and making the decoded data obtained by decoding and reconstructing the second decoding network closer to the data to be encoded, thereby improving the rate-distortion performance of the encoding and decoding network.

[0362] The encoding and decoding method 1300 provided in this embodiment of the present application can be applied to the encoding and decoding system shown in Figure 14. As shown in Figure 14, the encoding and decoding system includes an encoding network 1401, a rounding module 1402, an entropy estimation network 1403, an entropy encoding module 1404, an entropy decoding module 1405, a first decoding network 1406, and a second decoding network 1407.

[0363] As shown in FIG14 , the data to be encoded is first input into the encoding network 1401 to obtain the first feature.

[0364] The rounding module 1402 rounds the first feature to obtain a rounded value of the first feature.

[0365] The entropy estimation network 1403 performs probability estimation on the rounded value of the first feature to obtain an estimated probability distribution of the rounded value of the first feature.

[0366] The entropy coding module 1404 performs entropy coding on the rounded value of the first feature according to the estimated probability distribution of the rounded value of the first feature to obtain a code stream to be decoded.

[0367] The entropy decoding module 1405 performs entropy decoding on the to-be-decoded bitstream according to the estimated probability distribution of the rounded value of the first feature to obtain the rounded value of the first feature.

[0368] The rounded value of the first feature is input into the first decoding network 1406 to obtain the target parameter, and then the parameters of the second decoding network 1406 are adjusted according to the target parameter (i.e., the parameter weights of all or part of the convolution and nonlinear activation of the second decoding network 1407 are adjusted by the target parameter).

[0369] The rounded value of the first feature is input into the second decoding network 1407 to obtain decoded data.

[0370] Please refer to Figure 15, which is a schematic diagram of the performance of the encoding and decoding method provided by an embodiment of the present application. The coordinate system in Figure 15 shows the performance of encoding and decoding the test set using the embodiment of the present application and related technologies under the Peak Signal to Noise Ratio (PSNR) indicator. The test set is a Kodak test set, which includes 24 images in Portable Network Graphics (PNG) format. The resolution of the 24 images can be 768×512 or 512×768. In the coordinate system of Figure 15, the horizontal axis is the bit rate (bits per pixel, BPP) and the vertical axis is PSNR. BPP is the number of bits used to store each pixel. The smaller the BPP, the lower the compression bit rate. PSNR is an objective standard for evaluating images. The higher the PSNR, the better the image quality.

[0371] In the coordinate system shown in FIG15 , line segment A represents the embodiment of the present application, and line segment B represents the related art. As can be seen from FIG15 , when the BPP index is the same, the PSNR index of the embodiment of the present application is higher than that of the related art. When the image compression quality (i.e., the PSNR index) is the same, the BPP index of the embodiment of the present application is lower than that of the related art. Therefore, it can be seen that the rate-distortion performance of the embodiment of the present application is higher than that of the related art, and the embodiment of the present application can improve the rate-distortion performance of the data encoding and decoding method.

[0372] The encoding and decoding methods provided in the embodiments of this application can be applied in scenarios including, but not limited to, all services involving the collection, storage, and transmission of image, video, and voice data in electronic devices, cloud services, and video surveillance (e.g., electronic device photography, video, and voice recording, photo albums, cloud photo albums, video surveillance, video conferencing, model compression, etc.).

[0373] FIG16 is a schematic diagram of an application scenario provided by an embodiment of the present application. As shown in FIG16 , in this application scenario, after an electronic device captures image data (data to be compressed), the captured image data (e.g., image data in RAW, YUV, or RGB format) is input into an AI encoding unit of the electronic device. The AI ​​encoding unit of the electronic device calls a first encoding network, a second encoding network, and an entropy estimation network to transform the image data into output features with lower redundancy and generate an estimated probability distribution of the output features. The arithmetic encoding unit of the electronic device calls an entropy encoding module to encode the output features into a data file based on the estimated probability distribution of the output features. The file saving unit saves the data file generated by the entropy encoding module to a corresponding storage location of the electronic device. When the electronic device needs to use the data file, it loads the data file from the corresponding storage location of the electronic device through the file loading unit and inputs it into the arithmetic decoding unit. The arithmetic decoding unit calls the entropy decoding module to decode the data file to obtain output features, and inputs the output features into the AI ​​decoding unit. The AI ​​decoding unit calls the first decoding network, the second decoding network, and the third decoding network to perform an inverse transformation on the output features and parse the output features into image data (e.g., RGB image data), i.e., compressed data. Among them, the AI ​​encoding unit and AI decoding unit can be deployed in the neural network processing unit (NPU) or graphics processing unit (GPU) of the electronic device. The arithmetic coding unit, file saving unit, file loading unit, and arithmetic decoding unit can be deployed in the CPU of the electronic device.

[0374] Figure 17 is a schematic diagram of another application scenario provided by an embodiment of the present application. As shown in Figure 17, in this application scenario, the electronic device directly uploads the stored image data (data to be compressed) or encodes (such as JPEG encoding) and then uploads it to the cloud side (such as a server). The cloud side directly inputs the received image data or decodes (such as JPEG decoding) and then inputs it into the AI ​​coding unit on the cloud side. The AI ​​coding unit on the cloud side calls the first coding network, the second coding network and the entropy estimation network to transform the image data into output features with lower redundancy and generate an estimated probability distribution of the output features. The arithmetic coding unit on the cloud side calls the entropy coding module to encode the output features into a data file according to the estimated probability distribution of the output features. The file saving unit saves the data file generated by the entropy coding module to the corresponding storage location on the cloud side. When the electronic device needs to use the data file, it sends a download request to the cloud side. After receiving the download request, the cloud side loads the data file from the corresponding storage location on the cloud side through the file loading unit and inputs it into the arithmetic decoding unit. The arithmetic decoding unit calls the entropy decoding module to decode the data file to obtain output features, and inputs the output features into the AI ​​decoding unit. The AI ​​decoding unit calls the first decoding network, the second decoding network, and the third decoding network to perform an inverse transformation on the output features and parse the output features into image data. The cloud sends the image data (compressed data) directly or encodes it to the electronic device.

[0375] The following will introduce a coding and decoding device for executing the above coding and decoding method with reference to FIG18 and FIG19.

[0376] It is understandable that, in order to implement the above functions, the encoding and decoding device includes hardware and / or software modules corresponding to the execution of each function. In combination with the algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application in combination with the embodiments, but such implementation should not be considered to be beyond the scope of this application.

[0377] In the embodiment of the present application, the functional modules of the codec device can be divided according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated modules can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is schematic and is only a logical functional division. In actual implementation, other division methods may be used.

[0378] In the case of dividing the functional modules into corresponding modules, Figure 18 shows a possible composition diagram of the encoding and decoding device involved in the above embodiments. As shown in Figure 18, the device 1800 may include: a transceiver unit 1801 and a processing unit 1802. The processing unit 1802 can implement the method performed by the encoding device, decoding device, encoder or decoder in the above method embodiment, and / or other processes used for the technology described in this article.

[0379] It should be noted that all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module and will not be repeated here.

[0380] When integrated, device 1800 may include a processing unit, a storage unit, and a communication unit. The processing unit may be used to control and manage the operations of device 1800, for example, supporting device 1800 in executing the steps performed by the aforementioned units. The storage unit may be used to support device 1800 in executing and storing program code and / or data. The communication unit may be used to support communication between device 1800 and other devices.

[0381] The processing unit may be a processor or a controller. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a digital signal processing (DSP) and a microprocessor, and so on. The storage unit may be a memory. The communication unit may specifically be a device that interacts with other electronic devices, such as a radio frequency circuit, a Bluetooth chip, or a Wi-Fi chip.

[0382] In one possible implementation, the encoding and decoding apparatus involved in the embodiments of the present application may be an apparatus 1900 having the structure shown in FIG19 , wherein the apparatus 1900 includes a processor 1901 and a transceiver 1902. The functions implemented by the transceiver unit 1801 and the processing unit 1802 in FIG18 may be implemented by the processor 1901.

[0383] Optionally, the device 1900 may further include a memory 1903 , and the processor 1901 and the memory 1903 may communicate with each other via an internal connection path. The relevant functions implemented by the storage unit in FIG18 may be implemented by the memory 1903 .

[0384] An embodiment of the present application further provides a computer storage medium, which stores computer instructions. When the computer instructions are executed on an electronic device, the electronic device executes the above-mentioned related method steps to implement the encoding and decoding method in the above-mentioned embodiment.

[0385] The embodiment of the present application further provides a computer program product. When the computer program product is run on a computer, the computer is caused to execute the above-mentioned related steps to implement the encoding and decoding method in the above-mentioned embodiment.

[0386] The present application also provides a coding and decoding device, which can be a chip, integrated circuit, component, or module. Specifically, the device may include a connected processor and a memory for storing instructions, or the device may include at least one processor for retrieving instructions from an external memory. When the device is running, the processor may execute the instructions to cause the chip to perform the coding and decoding methods described in the above method embodiments.

[0387] 20 shows a schematic structural diagram of a chip 2000. The chip 2000 includes one or more processors 2001 and an interface circuit 2002. Optionally, the chip 2000 may further include a bus 2003.

[0388] The processor 2001 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above encoding method can be completed by the hardware integrated logic circuit in the processor 2001 or the software instruction.

[0389] Optionally, the processor 2001 may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The methods and steps disclosed in the embodiments of the present application may be implemented or executed. The general-purpose processor may be a microprocessor or any conventional processor.

[0390] The interface circuit 2002 can be used to send or receive data, instructions or information. The processor 2001 can use the data, instructions or other information received by the interface circuit 2002 to process it, and can send the processing completion information through the interface circuit 2002.

[0391] Optionally, the chip also includes a memory, which may include a read-only memory and a random access memory, and provides operating instructions and data to the processor. Part of the memory may also include a non-volatile random access memory (NVRAM).

[0392] Optionally, the memory stores an executable software module or a data structure, and the processor can perform corresponding operations by calling an operation instruction stored in the memory (the operation instruction may be stored in an operating system).

[0393] Optionally, the chip can be used in an electronic device or DOP involved in the embodiments of the present application. Optionally, the interface circuit 2002 can be used to output the execution result of the processor 2001. For the encoding method provided in one or more embodiments of the present application, reference can be made to the aforementioned embodiments and will not be repeated here.

[0394] It should be noted that the corresponding functions of the processor 2001 and the interface circuit 2002 can be implemented through hardware design, software design, or a combination of hardware and software, and there is no limitation here.

[0395] Among them, the electronic device, computer storage medium, computer program product or chip provided in this embodiment is used to execute the corresponding method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, and will not be repeated here.

[0396] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0397] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0398] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0399] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0400] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0401] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0402] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the above methods of each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0403] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A coding method, It is characterized in that The method comprises: Get the data to be encoded; Inputting the data to be encoded into a first encoding network to obtain target parameters; constructing a second encoding network according to the target parameters; Inputting the to-be-encoded data into the second encoding network to obtain a first feature; The first feature is encoded to obtain an encoded code stream.

2. The method according to claim 1, It is characterized in that The target parameters are parameter weights of all or part of the convolutions and nonlinear activations of the second encoding network.

3. The method according to claim 1 or 2, It is characterized in that The step of encoding the first feature to obtain a coded bitstream includes: rounding the first feature to obtain a rounded value of the first feature; Performing probability estimation on the rounded value of the first feature to obtain an estimated probability distribution of the rounded value of the first feature; The rounded value of the first feature is entropy encoded according to the estimated probability distribution of the rounded value of the first feature to obtain the encoded bit stream.

4. The method according to claim 3, It is characterized in that The performing probability estimation on the rounded value of the first feature to obtain an estimated probability distribution of the rounded value of the first feature includes: A probability estimation is performed on the rounded value of the first feature according to first information to obtain an estimated probability distribution of the rounded value of the first feature, where the first information includes at least one of context information and side information.

5. A decoding method, It is characterized in that The method comprises: Get the code stream to be decoded; Decoding the to-be-decoded bitstream to obtain a rounded value of a first feature and a rounded value of a second feature, wherein the rounded value of the first feature is used to obtain decoded data, and the rounded value of the second feature is used to obtain a target parameter; Inputting the rounded value of the second feature into a first decoding network to obtain the target parameter; Constructing a second decoding network according to the target parameters; The rounded value of the first feature is input into the second decoding network to obtain decoded data.

6. The method according to claim 5, It is characterized in that The target parameters are parameter weights of all or part of the convolutions and nonlinear activations of the second decoding network.

7. The method according to claim 5 or 6, It is characterized in that The code stream to be decoded includes a first code stream to be decoded and a second code stream to be decoded, and decoding the code stream to be decoded to obtain a rounded value of the first feature and a rounded value of the second feature includes: Decoding the first to-be-decoded bitstream to obtain a rounded value of the first feature; The second to-be-decoded code stream is decoded to obtain a rounded value of the second feature.

8. The method according to claim 7, It is characterized in that The decoding of the first to-be-decoded code stream to obtain a rounded value of the first feature includes: Performing probability estimation on the rounded value of the first feature in the first to-be-decoded bitstream to obtain an estimated probability distribution of the rounded value of the first feature; The first to-be-decoded bitstream is entropy decoded according to the estimated probability distribution of the rounded value of the first feature to obtain the rounded value of the first feature.

9. The method according to claim 8, It is characterized in that The performing probability estimation on the rounded value of the first feature in the first to-be-decoded bitstream to obtain an estimated probability distribution of the rounded value of the first feature includes: Probability estimation is performed on the rounded value of the first feature in the first to-be-decoded bitstream according to first information to obtain an estimated probability distribution of the rounded value of the first feature, where the first information includes at least one of context information and side information.

10. The method according to any one of claims 7 to 9, It is characterized in that The decoding of the second to-be-decoded code stream to obtain a rounded value of the second feature includes: Performing probability estimation on the rounded value of the second feature in the second to-be-decoded bitstream to obtain an estimated probability distribution of the rounded value of the second feature; The second to-be-decoded code stream is entropy decoded according to the estimated probability distribution of the rounded value of the second feature to obtain the rounded value of the second feature.

11. The method according to claim 10, It is characterized in that The performing probability estimation on the rounded value of the second feature in the second to-be-decoded bitstream to obtain an estimated probability distribution of the rounded value of the second feature includes: Probability estimation is performed on the rounded value of the second feature in the second to-be-decoded bitstream according to first information to obtain an estimated probability distribution of the rounded value of the second feature, wherein the first information includes at least one of context information and side information.

12. A decoding method, It is characterized in that The method comprises: Get the code stream to be decoded; Decoding the to-be-decoded bitstream to obtain a rounded value of a first feature, wherein the rounded value of the first feature is used to obtain decoded data and a target parameter; Inputting the rounded value of the first feature into a first decoding network to obtain a target parameter; Constructing a second decoding network according to the target parameters; The rounded value of the first feature is input into the second decoding network to obtain decoded data.

13. The method according to claim 12, It is characterized in that The target parameters are parameter weights of all or part of the convolutions and nonlinear activations of the second decoding network.

14. The method according to claim 12 or 13, It is characterized in that The decoding of the to-be-decoded bitstream to obtain a rounded value of the first feature includes: Performing probability estimation on the rounded value of the first feature in the to-be-decoded bitstream to obtain an estimated probability distribution of the rounded value of the first feature; The code stream to be decoded is entropy decoded according to the estimated probability distribution of the rounded value of the first feature to obtain the rounded value of the first feature.

15. The method according to claim 14, It is characterized in that The performing probability estimation on the rounded value of the first feature in the to-be-decoded bitstream to obtain an estimated probability distribution of the rounded value of the first feature includes: Probability estimation is performed on the rounded value of the first feature in the to-be-decoded bitstream according to first information to obtain an estimated probability distribution of the rounded value of the first feature, where the first information includes at least one of context information and side information.

16. An encoding device, It is characterized in that comprising a processing circuit for: Get the data to be encoded; Inputting the data to be encoded into a first encoding network to obtain target parameters; constructing a second encoding network according to the target parameters; Inputting the to-be-encoded data into the second encoding network to obtain a first feature; The first feature is encoded to obtain an encoded code stream.

17. The device according to claim 16, It is characterized in that The target parameters are parameter weights of all or part of the convolutions and nonlinear activations of the second encoding network.

18. The device according to claim 16 or 17, It is characterized in that The processing circuit is specifically used for: rounding the first feature to obtain a rounded value of the first feature; Performing probability estimation on the rounded value of the first feature to obtain an estimated probability distribution of the rounded value of the first feature; The rounded value of the first feature is entropy encoded according to the estimated probability distribution of the rounded value of the first feature to obtain the encoded bit stream.

19. The device according to claim 18, It is characterized in that The processing circuit is specifically used for: A probability estimation is performed on the rounded value of the first feature according to first information to obtain an estimated probability distribution of the rounded value of the first feature, where the first information includes at least one of context information and side information.

20. A decoding device, It is characterized in that comprising a processing circuit for: Get the code stream to be decoded; Decoding the to-be-decoded bitstream to obtain a rounded value of a first feature and a rounded value of a second feature, wherein the rounded value of the first feature is used to obtain decoded data, and the rounded value of the second feature is used to obtain a target parameter; Inputting the rounded value of the second feature into a first decoding network to obtain the target parameter; Constructing a second decoding network according to the target parameters; The rounded value of the first feature is input into the second decoding network to obtain decoded data.

21. The device according to claim 20, It is characterized in that The target parameters are parameter weights of all or part of the convolutions and nonlinear activations of the second decoding network.

22. The device according to claim 20 or 21, It is characterized in that The code stream to be decoded includes a first code stream to be decoded and a second code stream to be decoded, and the processing circuit is specifically used for: Decoding the first to-be-decoded bitstream to obtain a rounded value of the first feature; The second to-be-decoded code stream is decoded to obtain a rounded value of the second feature.

23. The device according to claim 22, It is characterized in that The processing circuit is specifically used for: Performing probability estimation on the rounded value of the first feature in the first to-be-decoded bitstream to obtain an estimated probability distribution of the rounded value of the first feature; The first to-be-decoded bitstream is entropy decoded according to the estimated probability distribution of the rounded value of the first feature to obtain the rounded value of the first feature.

24. The device according to claim 23, It is characterized in that The processing circuit is specifically used for: Probability estimation is performed on the rounded value of the first feature in the first to-be-decoded bitstream according to first information to obtain an estimated probability distribution of the rounded value of the first feature, where the first information includes at least one of context information and side information.

25. The device according to any one of claims 22 to 24, It is characterized in that The processing circuit is specifically used for: Performing probability estimation on the rounded value of the second feature in the second to-be-decoded bitstream to obtain an estimated probability distribution of the rounded value of the second feature; The second to-be-decoded code stream is entropy decoded according to the estimated probability distribution of the rounded value of the second feature to obtain the rounded value of the second feature.

26. The device according to claim 25, It is characterized in that The processing circuit is specifically used for: Probability estimation is performed on the rounded value of the second feature in the second to-be-decoded bitstream according to first information to obtain an estimated probability distribution of the rounded value of the second feature, wherein the first information includes at least one of context information and side information.

27. A decoding device, It is characterized in that comprising a processing circuit for: Get the code stream to be decoded; Decoding the to-be-decoded bitstream to obtain a rounded value of a first feature, wherein the rounded value of the first feature is used to obtain decoded data and a target parameter; Inputting the rounded value of the first feature into a first decoding network to obtain a target parameter; Constructing a second decoding network according to the target parameters; The rounded value of the first feature is input into the second decoding network to obtain decoded data.

28. The device according to claim 27, It is characterized in that The target parameters are parameter weights of all or part of the convolutions and nonlinear activations of the second decoding network.

29. The device according to claim 27 or 28, It is characterized in that The processing circuit is specifically used for: Performing probability estimation on the rounded value of the first feature in the to-be-decoded bitstream to obtain an estimated probability distribution of the rounded value of the first feature; The code stream to be decoded is entropy decoded according to the estimated probability distribution of the rounded value of the first feature to obtain the rounded value of the first feature.

30. The device according to claim 29, It is characterized in that The processing circuit is specifically used for: Probability estimation is performed on the rounded value of the first feature in the to-be-decoded bitstream according to first information to obtain an estimated probability distribution of the rounded value of the first feature, where the first information includes at least one of context information and side information.

31. An encoder, It is characterized in that include: one or more processors; A non-transitory computer-readable storage medium, coupled to the processor and storing a program executed by the processor, wherein the program, when executed by the processor, causes the encoder to perform the method according to any one of claims 1 to 4.

32. A decoder, It is characterized in that include: one or more processors; A non-transitory computer-readable storage medium, coupled to the processor and storing a program executed by the processor, wherein the program, when executed by the processor, causes the encoder to perform the method according to any one of claims 5 to 11 or 12 to 15.

33. A computer readable storage medium, It is characterized in that It comprises a computer program which, when executed on a computer, causes the computer to perform the method of any one of claims 1 to 4, 5 to 11 or 12 to 15.

34. A computer program product, It is characterized in that The computer program product comprises a computer program code, which, when executed on a computer, causes the computer to perform the method of any one of claims 1 to 4, 5 to 11 or 12 to 15.

Images