Embodiments of the application disclose a method and device for picture coding, and a storage medium, the device for picture coding is configured to train an initial feature extraction model with first training data, to obtain a target feature extraction model; train an initial clustering model with second training data, to obtain a first clustering model; and perform picture coding on picture data according to the target feature extraction model and the first clustering model, to obtain coded data corresponding to the picture data.

Computer processor hardware receives a first set of adjustment values. The first set of adjustment values specify adjustments to be made to a predicted rendition of a signal generated at a first level of quality to reconstruct a rendition of the signal at the first level of quality. The computer processor hardware processes the first set of adjustment values and derives a second set of adjustment values based on the first set of adjustment values and a rendition of the signal at a second level of quality. The second level of quality is lower than the first level of quality.

Computer processor hardware receives a first set of adjustment values. The first set of adjustment values specify adjustments to be made to a predicted rendition of a signal generated at a first level of quality to reconstruct a rendition of the signal at the first level of quality. The computer processor hardware processes the first set of adjustment values and derives a second set of adjustment values based on the first set of adjustment values and a rendition of the signal at a second level of quality. The second level of quality is lower than the first level of quality.

A method for partitioning of input vectors for coding is presented. The method comprises obtaining of an input vector. The input vector is segmented, in a non-recursive manner, into an integer number, N.sup.SEG, of input vector segments. A representation of a respective relative energy difference between parts of the input vector on each side of each boundary between the input vector segments is determined, in a recursive manner. The input vector segments and the representations of the relative energy differences are provided for individual coding. Partitioning units and computer programs for partitioning of input vectors for coding, as well as positional encoders, are presented.

A method for partitioning of input vectors for coding is presented. The method comprises obtaining of an input vector. The input vector is segmented, in a non-recursive manner, into an integer number, N.sup.SEG, of input vector segments. A representation of a respective relative energy difference between parts of the input vector on each side of each boundary between the input vector segments is determined, in a recursive manner. The input vector segments and the representations of the relative energy differences are provided for individual coding. Partitioning units and computer programs for partitioning of input vectors for coding, as well as positional encoders, are presented.

A method of compressing image data comprising a set of image values each representing a position in image-value space so as to define an occupied region thereof. The method comprises selectively applying a series of compression transforms to subsets of the image data items to generate a transformed set of image data items occupying a compacted region of value space. The method further comprises identifying a set of one or more reference data items that quantizes the compacted region in value space. For each image data item in the set of image data items, a sequence of decompression transforms from a fixed set of decompression transforms is identified that generates an approximation of that image data item when applied to a selected one of the one or more reference data items. Each image data item in the set of image data items is encoded as a representation of the identified sequence of decompression transforms for that image data item. The encoded image data items, set of reference data items and the fixed set of decompression transforms are stored as compressed image data.

A method of compressing image data comprising a set of image values each representing a position in image-value space so as to define an occupied region thereof. The method comprises selectively applying a series of compression transforms to subsets of the image data items to generate a transformed set of image data items occupying a compacted region of value space. The method further comprises identifying a set of one or more reference data items that quantizes the compacted region in value space. For each image data item in the set of image data items, a sequence of decompression transforms from a fixed set of decompression transforms is identified that generates an approximation of that image data item when applied to a selected one of the one or more reference data items. Each image data item in the set of image data items is encoded as a representation of the identified sequence of decompression transforms for that image data item. The encoded image data items, set of reference data items and the fixed set of decompression transforms are stored as compressed image data.

A video coding device may receive a video bit-stream that carries a video captured in a non-4:4:4 chroma format. A palette mode may be used to decode the video bit-stream. The video bit-stream may include data defining a palette table and a palette index map in a 4:4:4 chroma format for the current block. A luma sample value for a luma sample position in the non-4:4:4 chroma format may be determined based on the luma sample position, the palette index map and the palette table. A chroma sample position associated with the 4:4:4 chroma format on the palette index map may be derived based on the luma component to chroma component resolution ratio in the non-4:4:4 chroma format. A chroma sample value for a chroma sample position in non-444 chroma format may be determined based on the derived chroma sample position, the palette index map and the palette table.

A video coding device may receive a video bit-stream that carries a video captured in a non-4:4:4 chroma format. A palette mode may be used to decode the video bit-stream. The video bit-stream may include data defining a palette table and a palette index map in a 4:4:4 chroma format for the current block. A luma sample value for a luma sample position in the non-4:4:4 chroma format may be determined based on the luma sample position, the palette index map and the palette table. A chroma sample position associated with the 4:4:4 chroma format on the palette index map may be derived based on the luma component to chroma component resolution ratio in the non-4:4:4 chroma format. A chroma sample value for a chroma sample position in non-444 chroma format may be determined based on the derived chroma sample position, the palette index map and the palette table.

Systems and methods are provided for alleviating bandwidth limitations of video transmission and enhancing the quality of videos at a receiver. In particular, an improved video transmission system is provided for generating high-resolution videos. The systems have therein a transmitter and a receiver; the transmitter includes an outer encoder and a core encoder, while the receiver includes a core decoder and an outer decoder. The outer encoder is adapted to receive the video from a source and separately output a salient video and an encoded background, and the outer decoder is adapted to merge the background with the salient video thereby producing an enhanced video. Also provided is a system that simulates pan-tilt-zoom (PTZ) operations without PTZ hardware. Further provided are methods for video transmission whereby a background model is initialized, a background independently encoded, updated incrementally, and the background and the updates transmitted independently from the video.