Methods for management of encoding complexity for image and video encoding, for example for algorithms belonging to the JPEG 2000 family of standards, where the encoding process targets a given compressed size (i.e. a total coded length) for the image or for each frame of a video sequence. Described are a set of methods for complexity constrained encoding of HTJ2K code-streams, involving collection of local or global statistics for each sub-band (not for each code-block), generation of forecasts for the statistics of sub-band samples that have not yet been produced by spatial transformation and quantization processes, and the use of this information to generate a global quantization parameter, from which the coarsest bit-plane to generate in each code-block can be deduced. Coded length estimates can be generated in a manner that enables latency and memory to be separately optimized against encoded image quality, while maintaining low computational complexity.

A deep learning based compression (DLBC) system trains multiple models that, when deployed, generates a compressed binary encoding of an input image that achieves a reconstruction quality and a target compression ratio. The applied models effectively identifies structures of an input image, quantizes the input image to a target bit precision, and compresses the binary code of the input image via adaptive arithmetic coding to a target codelength. During training, the DLBC system reconstructs the input image from the compressed binary encoding and determines the loss in quality from the encoding process. Thus, the models can be continually trained to, when applied to an input image, minimize the loss in reconstruction quality that arises due to the encoding process while also achieving the target compression ratio.

A deep learning based compression (DLBC) system trains multiple models that, when deployed, generates a compressed binary encoding of an input image that achieves a reconstruction quality and a target compression ratio. The applied models effectively identifies structures of an input image, quantizes the input image to a target bit precision, and compresses the binary code of the input image via adaptive arithmetic coding to a target codelength. During training, the DLBC system reconstructs the input image from the compressed binary encoding and determines the loss in quality from the encoding process. Thus, the models can be continually trained to, when applied to an input image, minimize the loss in reconstruction quality that arises due to the encoding process while also achieving the target compression ratio.

Aspects of the disclosure provide a method and an apparatus for video encoding. The apparatus includes processing circuitry configured to perform an iterative update of sample values of a plurality of samples in an initial input image. The iterative update includes generating a coded representation of a final input image based on the final input image by an encoding neural network (NN) and at least one training module. The final input image has been updated from the initial input image by a number of iterations of the iterative update. The iterative update includes generating a reconstructed image of the final input image based on the coded representation of the final input image by a decoding NN. One of a rate-distortion loss for the final input image or the number of iterations of the iterative update satisfies a pre-determined condition. An encoded image corresponding to the final input image is generated.

Aspects of the disclosure provide a method and an apparatus for video encoding. The apparatus includes processing circuitry configured to perform an iterative update of sample values of a plurality of samples in an initial input image. The iterative update includes generating a coded representation of a final input image based on the final input image by an encoding neural network (NN) and at least one training module. The final input image has been updated from the initial input image by a number of iterations of the iterative update. The iterative update includes generating a reconstructed image of the final input image based on the coded representation of the final input image by a decoding NN. One of a rate-distortion loss for the final input image or the number of iterations of the iterative update satisfies a pre-determined condition. An encoded image corresponding to the final input image is generated.

Systems and methods for hinting an encoder are disclosed in which a server monitors for information related to changes in frame rendering, calculates tolerance boundaries, rolling average frame time, and short-term trends in frame time, and uses those calculations to identify a frame time peak. The server then hints a codec (encoder) to modulate the quality settings of frame output in proportion to the size of the frame time peak. In certain embodiments, a renderer records one or more playthroughs in a game environment, sorts a plurality of frames from one or more playthroughs into a plurality of cells on a heatmap, and collects the list of sorted frames. A codec may then encode one or more frames from the list of sorted frames to calculate an average encoded frame size for each cell in the heatmap, and associate each average encoded frame size with a per-cell normalized encoder quality setting.

An image processing apparatus which calculates a code amount obtained upon coding a coding block being obtained by dividing an image to be processed, determines an assigned code amount to be assigned to each of the coding blocks, based on a reference code amount and the code amount calculated for each of coding blocks in a coding group including a plurality of coding blocks, and generates coded data by coding each of the coding blocks using the assigned code amount as a target code amount, wherein the assigned code amount is determined so that a total of the assigned code amounts of the coding blocks in the coding group is the same among a plurality of coding groups, and fixed-length coding is carried out on a coding group-by-coding group basis by coding using the determined assigned code amounts.

Aspects of the disclosure provide a method and an apparatus for video encoding. The apparatus includes processing circuitry configured to generate an initial feature representation from an input image to be encoded and perform an iterative update of values of a plurality of elements in the initial feature representation. The iterative update includes generate a coded representation corresponding to a final feature representation based on the final feature representation that has been updated from the initial feature representation by a number of iterations of the iterative update. A reconstructed image corresponding to the final feature representation is generated based on the coded representation. An encoded image corresponding to the final feature representation having updated values of the plurality of elements is generated. One of (i) a rate-distortion loss corresponding to the final feature representation or (ii) the number of iterations of the iterative update satisfies a pre-determined condition.

Aspects of the disclosure provide a method and an apparatus for video encoding. The apparatus includes processing circuitry configured to generate an initial feature representation from an input image to be encoded and perform an iterative update of values of a plurality of elements in the initial feature representation. The iterative update includes generate a coded representation corresponding to a final feature representation based on the final feature representation that has been updated from the initial feature representation by a number of iterations of the iterative update. A reconstructed image corresponding to the final feature representation is generated based on the coded representation. An encoded image corresponding to the final feature representation having updated values of the plurality of elements is generated. One of (i) a rate-distortion loss corresponding to the final feature representation or (ii) the number of iterations of the iterative update satisfies a pre-determined condition.

Aspects of the disclosure provide methods, apparatuses, and a non-transitory computer-readable storage medium for video encoding and video decoding. An apparatus for video decoding can include processing circuitry. The processing circuitry is configured to decode neural network update information in a coded bitstream for at least one neural network in the video decoder. The at least one neural network is configured with a set of pretrained parameters, and the neural network update information indicates a first modification parameter. The processing circuitry is configured to update the set of pretrained parameters in the at least one neural network in the video decoder based on the first modification parameter. The processing circuitry is configured to decode an encoded image based on the updated at least one neural network.