Innovations in use of chroma quantization parameter (“QP”) offsets when determining a control parameter for deblock filtering. For example, as part of encoding, an encoder sets a picture-level chroma QP offset and slice-level chroma QP offset for encoding of a slice of a picture. The encoder also performs deblock filtering of at least part of the slice, where derivation of a control parameter considers only the picture-level chroma QP offset. The encoder outputs at least part of a bitstream including the encoded content. As part of decoding, a corresponding decoder sets a picture-level chroma QP offset and a slice-level chroma QP offset for decoding of a slice of a picture, but derivation of a control parameter for deblock filtering considers only the picture-level chroma QP offset.

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.

Various embodiments provide an encoder that performs an up-conversion and a down-conversion on a first quantization matrix to generate a second quantization matrix, and quantizes transform coefficients of a current block using the second quantization matrix. The first quantization matrix has a first number of rows and a first number of columns equal to the first number of rows, and the second quantization matrix has a second number of rows and a second number of columns different from the second number of rows. In the up-conversion, the circuitry generates the second quantization matrix such that one of the second number of rows or the second number of columns is larger than the first number of rows. In the down-conversion, the circuitry generates the second quantization matrix such that the other of the second number of rows or the second number of columns is smaller than the first number of rows.

Various embodiments provide an encoder that performs an up-conversion and a down-conversion on a first quantization matrix to generate a second quantization matrix, and quantizes transform coefficients of a current block using the second quantization matrix. The first quantization matrix has a first number of rows and a first number of columns equal to the first number of rows, and the second quantization matrix has a second number of rows and a second number of columns different from the second number of rows. In the up-conversion, the circuitry generates the second quantization matrix such that one of the second number of rows or the second number of columns is larger than the first number of rows. In the down-conversion, the circuitry generates the second quantization matrix such that the other of the second number of rows or the second number of columns is smaller than the first number of rows.

Techniques and tools for encoding enhancement layer video with quantization that varies spatially and/or between color channels are presented, along with corresponding decoding techniques and tools. For example, an encoding tool determines whether quantization varies spatially over a picture, and the tool also determines whether quantization varies between color channels in the picture. The tool signals quantization parameters for macroblocks in the picture in an encoded bit stream. In some implementations, to signal the quantization parameters, the tool predicts the quantization parameters, and the quantization parameters are signaled with reference to the predicted quantization parameters. A decoding tool receives the encoded bit stream, predicts the quantization parameters, and uses the signaled information to determine the quantization parameters for the macroblocks of the enhancement layer video. The decoding tool performs inverse quantization that can vary spatially and/or between color channels.

Techniques and tools for encoding enhancement layer video with quantization that varies spatially and/or between color channels are presented, along with corresponding decoding techniques and tools. For example, an encoding tool determines whether quantization varies spatially over a picture, and the tool also determines whether quantization varies between color channels in the picture. The tool signals quantization parameters for macroblocks in the picture in an encoded bit stream. In some implementations, to signal the quantization parameters, the tool predicts the quantization parameters, and the quantization parameters are signaled with reference to the predicted quantization parameters. A decoding tool receives the encoded bit stream, predicts the quantization parameters, and uses the signaled information to determine the quantization parameters for the macroblocks of the enhancement layer video. The decoding tool performs inverse quantization that can vary spatially and/or between color channels.

An example method includes receiving (502) a plurality of points that represent a point cloud; representing a position of the point in each dimension of a three-dimensional space as a sequence of bits (504), where the position of the point is encoded according to a tree data structure; partitioning (506) at least one of the sequences of bits into a first portion of bits and a second portion of bits; quantizing (508) each of the second portions of bits according to a quantization step size, where the quantization step size is determined according to an exponential function having a quantization parameter value as an input and the quantization step size as an output; and generating (510) a data structure representing the point cloud and including the quantized second portions of bits.

A method for reconstructing a block of an image, said block comprising a plurality of components and being predictively encoded from a reference block, includes if a single quantized residual block is used to jointly encode at least two components of the plurality of components, deriving at least one quantization matrix from a plurality of scaling lists each defined for one component of the plurality of components; and, applying one of the at least one derived quantization matrix to the single quantized residual block to obtain a reconstructed residual block for each of the at least two components.

A method for reconstructing a block of an image, said block comprising a plurality of components and being predictively encoded from a reference block, includes if a single quantized residual block is used to jointly encode at least two components of the plurality of components, deriving at least one quantization matrix from a plurality of scaling lists each defined for one component of the plurality of components; and, applying one of the at least one derived quantization matrix to the single quantized residual block to obtain a reconstructed residual block for each of the at least two components.