A three-dimensional data encoding method is a method of encoding three-dimensional points each having an attribute information item. The three-dimensional data encoding method includes: assigning each of the three-dimensional points to any one of layers; encoding the attribute information item of each three-dimensional point using the layers; and encoding information indicating a total number of three-dimensional points belonging to each of the layers.

A partitioning method comprises determining whether a current block of a picture is a boundary block and whether the size of the current block is larger than a minimum allowed quadtree leaf node size; and if the current block is the boundary block and the size of the current block is not larger than the minimum allowed quadtree leaf node size (MinQTSize), applying forced binary tree (BT) partitioning to the current block. A method comprises making a determination that a current block of a picture is a boundary block and that a size of the current block is less than or equal to a minimum allowed quadtree (QT) leaf node size (MinQTSize); and applying, in response to the determination, forced binary tree (BT) partitioning to the current block.

A partitioning method comprises determining whether a current block of a picture is a boundary block and whether the size of the current block is larger than a minimum allowed quadtree leaf node size; and if the current block is the boundary block and the size of the current block is not larger than the minimum allowed quadtree leaf node size (MinQTSize), applying forced binary tree (BT) partitioning to the current block. A method comprises making a determination that a current block of a picture is a boundary block and that a size of the current block is less than or equal to a minimum allowed quadtree (QT) leaf node size (MinQTSize); and applying, in response to the determination, forced binary tree (BT) partitioning to the current block.

An encoder includes circuitry configured to receive a video frame, partition the video frame into a plurality of blocks, determine a respective spatial activity measure for each block in the plurality of blocks and using a transform matrix, encode the video frame using the spatial activity measure. Related apparatus, systems, techniques and articles are also described.

A video decoder can be configured to determine that a current block of the video data is coded in a bi-prediction inter mode; receive a first syntax element identifying a motion vector predictor from a first candidate list of motion vector predictors; receive a second syntax element identifying a motion vector difference; determine a first motion vector for the current block based on the motion vector predictor and the motion vector difference; determine a second motion vector for the current block from a second list of candidate motion vector predictors based on bilateral matching; and determine a prediction block for the current block using the first motion vector and the second motion vector.

Aspects of the disclosure provide a method, an apparatus, and non-transitory computer-readable storage medium for video decoding. The apparatus includes processing circuitry that reconstructs blocks of an image that is to be reconstructed from a coded video bitstream. The processing circuitry decodes first deblocking information in the coded video bitstream including a first deblocking parameter of a deep neural network (DNN) in a video decoder. The first deblocking parameter of the DNN is an updated parameter that has been previously determined by a content adaptive training process. The processing circuitry determines the DNN for a first boundary region comprising a subset of samples in the reconstructed blocks based on the first deblocking parameter included in the first deblocking information. The processing circuitry deblocks the first boundary region comprising the subset of samples in the reconstructed blocks based on the determined DNN corresponding to the first deblocking parameter.

The present invention provides an image encoding method and an image decoding method. The image encoding method of the present invention comprises: a first dividing step of dividing a current image into a plurality of blocks; and a second dividing step of dividing, into a plurality of sub blocks, a block, which is to be divided and includes a boundary of the current image, among the plurality of blocks, wherein the second dividing step is recursively performed by setting a sub block including the boundary of the current images as the block to be divided, until the sub block including the boundary of the current image does not exist among the sub blocks.

The present invention provides an image encoding method and an image decoding method. The image encoding method of the present invention comprises: a first dividing step of dividing a current image into a plurality of blocks; and a second dividing step of dividing, into a plurality of sub blocks, a block, which is to be divided and includes a boundary of the current image, among the plurality of blocks, wherein the second dividing step is recursively performed by setting a sub block including the boundary of the current images as the block to be divided, until the sub block including the boundary of the current image does not exist among the sub blocks.

An iterative training of neural networks for video coding and decoding using intra prediction is provided that finds a tradeoff between an extreme genericity and an extreme specialization to a codec for the trained neural networks. At the first iteration, the set of neural networks is trained following a partitioning approach. Then, for several iterations, the set of neural networks is inserted into the codec, and pairs of a block and its context are extracted from the partitioning of images via the codec with a single additional neural network-based mode then, the neural networks are retrained on these pairs. This way, from the second iteration, the neural networks learn an intra prediction diverging from that in the codec while still being valuable for the codec in terms of rate-distortion performance.

An iterative training of neural networks for video coding and decoding using intra prediction is provided that finds a tradeoff between an extreme genericity and an extreme specialization to a codec for the trained neural networks. At the first iteration, the set of neural networks is trained following a partitioning approach. Then, for several iterations, the set of neural networks is inserted into the codec, and pairs of a block and its context are extracted from the partitioning of images via the codec with a single additional neural network-based mode then, the neural networks are retrained on these pairs. This way, from the second iteration, the neural networks learn an intra prediction diverging from that in the codec while still being valuable for the codec in terms of rate-distortion performance.