Abstract: Methods, systems, and bitstream syntax are described for inter-frame coding using end-to-end neural networks used in image and video compression. Inter-frame coding methods include one or more of: joint luma-chroma motion compensation for YUV pictures, joint luma-chroma residual coding for YUV pictures, using attention layers, enabling temporal motion prediction networks for motion vector prediction, using a cross-domain network which combines motion vector and residue information for motion vectors decoding, using the cross-domain network for decoding residuals, using weighted motion-compensated inter prediction, and using temporal only, spatial only, or both temporal and spatial features in entropy decoding. Methods to improve training of neural networks for inter-frame coding are also described.

Abstract: An input image represented in an input domain is received from an input video signal. Forward reshaping is performed on the input image to generate a forward reshaped image represented in a reshaped image domain. Non-reshaping encoding operations are performed to encode the reshaped image into an encoded video signal. At least one of the non-reshaping encoding operations is implemented with an ML model that has been previously trained with training images in one or more training datasets in a preceding training stage. A recipient device of the encoded video signal is caused to generate a reconstructed image from the forward reshaped image.

Abstract: Methods, systems, and bitstream syntax are described for the carriage of neural network topology and parameters as related to neural-network-based post filtering (NNPF) in image and video coding. Examples of NNPF SEI messaging as applicable to the MPEG standards for coding video pictures are described at the sequence layer and at the picture layer.

Abstract: An input image represented in an input domain is received from an input video signal. Forward reshaping is performed on the input image to generate a forward reshaped image represented in a reshaped image domain. Non-reshaping encoding operations are performed to encode the reshaped image into an encoded video signal. At least one of the non-reshaping encoding operations is implemented with an ML model that has been previously trained with training images in one or more training datasets in a preceding training stage. A recipient device of the encoded video signal is caused to generate a reconstructed image from the forward reshaped image.

Abstract: Methods, systems, and bitstream syntax are described for the fusion of latent features in multi-level, end-to-end, neural networks used in image and video compression. The fused architecture may be static or dynamic based on image characteristics (e.g., natural images versus screen content images) or other coding parameters, such as bitrate constrains or rate-distortion optimization. A variety of multi-level fusion architectures are discussed.