Provided is an encoder including: circuitry; and memory coupled to the circuitry. In operation, the circuitry: performs a mapping process of Luma Mapping with Chroma Scaling (LMCS) for transforming a first pixel value space applied to a luma display image signal into a second pixel value space applied to a luma encoding process signal, using line segments forming a transform curve, each of which corresponds to a different one of sections obtained by partitioning the first pixel value space; and encodes an image, and in the performing of the LMCS, the circuitry determines the transform curve so that among boundary values in the second pixel value space, a first value obtained by dividing a boundary value by a base width defined according to a bit depth of the image is not equal to a second value obtained by dividing another boundary value by the base width.

In a video coding system, it is proposed to transmit only a luma quantization matrix and no chroma quantization matrix when the chroma format is monochrome, and otherwise (i.e. not monochrome) to transmit at least both a luma quantization matrix and a chroma quantization matrix. This allows to avoid the transmission of data elements that are useless. It allows to improve simultaneously the encoding (less operations to perform), the transmission (less data to be transmitted) and decoding (less operations to perform).

The compression system trains a machine-learned encoder and decoder through an autoencoder architecture. The encoder can be deployed by a sender system to encode content for transmission to a receiver system, and the decoder can be deployed by the receiver system to decode the encoded content and reconstruct the original content. The encoder is coupled to receive content and output a tensor as a compact representation of the content. The content may be, for example, images, videos, or text. The decoder is coupled to receive a tensor representing content and output a reconstructed version of the content. The compression system trains the autoencoder with a discriminator to reduce compression artifacts in the reconstructed content. The discriminator is coupled to receive one or more input content, and output a discrimination prediction that discriminates whether the input content is the original or reconstructed version of the content.

Video decoding innovations for multithreading implementations and graphics processor unit (“GPU”) implementations are described. For example, for multithreaded decoding, a decoder uses innovations in the areas of layered data structures, picture extent discovery, a picture command queue, and/or task scheduling for multithreading. Or, for a GPU implementation, a decoder uses innovations in the areas of inverse transforms, inverse quantization, fractional interpolation, intra prediction using waves, loop filtering using waves, memory usage and/or performance-adaptive loop filtering. Innovations are also described in the areas of error handling and recovery, determination of neighbor availability for operations such as context modeling and intra prediction, CABAC decoding, computation of collocated information for direct mode macroblocks in B slices, reduction of memory consumption, implementation of trick play modes, and picture dropping for quality adjustment.

Video decoding innovations for multithreading implementations and graphics processor unit (“GPU”) implementations are described. For example, for multithreaded decoding, a decoder uses innovations in the areas of layered data structures, picture extent discovery, a picture command queue, and/or task scheduling for multithreading. Or, for a GPU implementation, a decoder uses innovations in the areas of inverse transforms, inverse quantization, fractional interpolation, intra prediction using waves, loop filtering using waves, memory usage and/or performance-adaptive loop filtering. Innovations are also described in the areas of error handling and recovery, determination of neighbor availability for operations such as context modeling and intra prediction, CABAC decoding, computation of collocated information for direct mode macroblocks in B slices, reduction of memory consumption, implementation of trick play modes, and picture dropping for quality adjustment.

Provided is an encoder including: circuitry; and memory coupled to the circuitry. In operation, the circuitry: performs a mapping process of Luma Mapping with Chroma Scaling (LMCS) for transforming a first pixel value space applied to a luma display image signal into a second pixel value space applied to a luma encoding process signal, using line segments forming a transform curve, each of which corresponds to a different one of sections obtained by partitioning the first pixel value space; and encodes an image, and in the performing of the LMCS, the circuitry determines the transform curve so that among boundary values in the second pixel value space, a first value obtained by dividing a boundary value by a base width defined according to a bit depth of the image is not equal to a second value obtained by dividing another boundary value by the base width.

Provided is an encoder including: circuitry; and memory coupled to the circuitry. In operation, the circuitry: performs a mapping process of Luma Mapping with Chroma Scaling (LMCS) for transforming a first pixel value space applied to a luma display image signal into a second pixel value space applied to a luma encoding process signal, using line segments forming a transform curve, each of which corresponds to a different one of sections obtained by partitioning the first pixel value space; and encodes an image, and in the performing of the LMCS, the circuitry determines the transform curve so that among boundary values in the second pixel value space, a first value obtained by dividing a boundary value by a base width defined according to a bit depth of the image is not equal to a second value obtained by dividing another boundary value by the base width.

Disclosed are an intra prediction method of a chrominance block using a luminance sample and an apparatus using the same. An image decoding method comprises the steps of calculating an intra prediction mode of a chrominance block on the basis of an LM mapping table when the chrominance block uses an LM; and generating a prediction block for the chrominance block on the basis of the calculated intra prediction mode of the chrominance block. When intra prediction mode information of chrominance blocks are decoded, mutually different tables are used depending on whether or not an LM is used, so that encoding and decoding can be performed without an unnecessary waste of bits.

Disclosed are an intra prediction method of a chrominance block using a luminance sample and an apparatus using the same. An image decoding method comprises the steps of calculating an intra prediction mode of a chrominance block on the basis of an LM mapping table when the chrominance block uses an LM; and generating a prediction block for the chrominance block on the basis of the calculated intra prediction mode of the chrominance block. When intra prediction mode information of chrominance blocks are decoded, mutually different tables are used depending on whether or not an LM is used, so that encoding and decoding can be performed without an unnecessary waste of bits.

Disclosed are an intra prediction method of a chrominance block using a luminance sample and an apparatus using the same. An image decoding method comprises the steps of: calculating an intra prediction mode of a chrominance block on the basis of an LM mapping table when the chrominance block uses an LM; and generating a prediction block for the chrominance block on the basis of the calculated intra prediction mode of the chrominance block. When intra prediction mode information of chrominance blocks are decoded, mutually different tables are used depending on whether or not an LM is used, so that encoding and decoding can be performed without an unnecessary waste of bits.