A video coding mechanism is disclosed. The mechanism includes partitioning a picture into a plurality of tiles. A number of the tiles are included in a tile group. The mechanism determines whether the tile group is a raster scan tile group or a rectangular tile group. The number of tiles in the tile group is determined based on whether the tile group is the raster scan tile group or the rectangular tile group. The tiles are encoded into a bitstream based on the tile group. The bitstream is stored for communication toward a decoder.

A video encoder for encoding a video into a data stream using motion compensated prediction for inter predicted blocks, comprising a hypothesis number control, configured to control a number of prediction hypotheses of the inter predicted blocks within a predetermined portion of the video to meet a predetermined criterion.

A method, apparatus, and computer program product provide for solving merge candidate list mismatches. In the context of a method, the method accesses a current coding unit of a picture. The method can also generate a merge candidate list comprising a plurality of coding unit representations in a predefined order. The method also determines whether a particular coding unit representation within the merge candidate list is representative of a coding unit within a dirty area of the picture and prevents the particular coding unit representation and one or more coding unit representations following the particular coding unit in the predefined order from being selected as a merge candidate for the current coding unit.

Systems and methods are described for video coding using affine motion models with adaptive precision. In an example, a block of video is encoded in a bitstream using an affine motion model, where the affine motion model is characterized by at least two motion vectors. A precision is selected for each of the motion vectors, and the selected precisions are signaled in the bitstream. In some embodiments, the precisions are signaled by including in the bitstream information that identifies one of a plurality of elements in a selected predetermined precision set. The identified element indicates the precision of each of the motion vectors that characterize the affine motion model. In some embodiments, the precision set to be used is signaled expressly in the bitstream; in other embodiments, the precision set may be inferred, e.g., from the block size, block shape or temporal layer.

A video decoder that decodes a current block of pixels by using multi-hypothesis combined prediction mode is provided. The video decoder generates a first prediction of the current block based on an inter prediction mode. The video decoder enables the combined prediction mode for the current block based on a block size of the current block determined according to a width and a height of the current block. The combined prediction mode is disabled when the width of or the height of the current block is greater than a threshold length. When the combined prediction mode is enabled, the video decoder generates a second prediction based on an intra prediction mode that is inferred to be a planar mode, and subsequently a combined prediction for the current block based on the first prediction and the second prediction. The video decoder reconstructs the current block by using the combined prediction.

An encoder includes circuitry and memory coupled to the circuitry. The circuitry, in operation, determines whether a first block is available and whether a second block is available, the first block and the second block being defined relative to a current block to be processed; selects a context model based on whether the first block is available, whether the second block is available, which of inter prediction and intra prediction is to be applied to the first block, and which of inter prediction and intra prediction is to be applied to the second block; and encodes, using the context model selected, a parameter indicating which of intra prediction and inter prediction is to be applied to the current block.

In some examples, a method for compressing a spectral reflectance dataset may be performed through compression circuitry. The method may include computing a principal component analysis basis for the spectral reflectance dataset; projecting the spectral reflectance dataset onto the principal component analysis basis to obtain a weight matrix; quantizing the weight matrix; performing a Huffman encoding process on the quantized weight matrix to generate a Huffman table and Huffman codes for the quantized weight matrix; and providing compressed spectral reflectance data as the principal component analysis basis, the Huffman table, and the Huffman codes.

A moving picture coding apparatus includes an inter-pixel filter having filters for filtering decoded image data so as to remove block distortion which is high frequency noise around block boundaries. The inter-pixel filter includes filters having different filtering strengths. The coding apparatus also includes a filter processing control unit for determining a filtering strength of the inter-pixel filter.

A moving picture coding apparatus includes an inter-pixel filter having filters for filtering decoded image data so as to remove block distortion which is high frequency noise around block boundaries. The inter-pixel filter includes filters having different filtering strengths. The coding apparatus also includes a filter processing control unit for determining a filtering strength of the inter-pixel filter.

A hybrid apparatus for coding a video stream includes a first encoder. The first encoder includes a neural network having at least one hidden layer, and the neural network receives source data from the video stream at a first hidden layer of the at least one hidden layer, receives side information correlated with the source data at the first hidden layer, and generates guided information using the source data and the side information. The first encoder outputs the guided information and the side information for a decoder to reconstruct the source data.