Abstract: A video coding method, an encoder, and a decoder are disclosed. The method is applied to a decoder and comprises retrieving a bitstream corresponding to a current frame and parsing the bitstream to obtain a current coding tree unit (CTU) of the current frame; determining an availability of at least one neighbouring CTU of the current CTU in the current frame according to a wavefront delay, wherein the wavefront delay is a delay in units of CTUs in a row direction between the current CTU at a current CTU row and the neighbouring CTU at a previous CTU row which are decoded in parallel; determining a prediction block in the at least one neighbouring CTU for a current coding unit (CU) in the current CTU; and decoding the current CU using the prediction block.

Abstract: A method for decoding a video includes that: a decoder decodes a video from a bitstream of the video; the decoder accesses a bitstream of the video and extracts a GCI flag from the bitstream; the decoder determines that one or more general constraints are imposed for the video based on the GCI flag value and extracts, from the bitstream of the video, a value indicating a quantity of additional bits included in the bitstream of the video, the additional bits include flag bits indicating respective additional coding tools to be constrained for the video; if the value is greater than five, the decoder extracts six flags from the bitstream of the video that indicate respective constraints for six additional coding tools; and the decoder decodes the bitstream of the video into images based on the constraints for the six additional coding tools indicated by the six flags.

Abstract: A video decoder decodes a current transform block from a video bitstream. For a transform block encoded with regular residual coding, when a subblock flag sb_coded_flag is not present, the decoder infers the flag to be 1 if the subblock is a DC subblock and/or the last subblock in the transform block containing a non-zero coefficient level. Otherwise, sb_coded_flag is inferred to be 0. For a transform block encoded with regular residual coding, when the sb_coded_flag is present, the decoder determines a context index for an arithmetic decoding process based on the sb_coded_flag of previous subblocks and decodes the sb_coded_flag of the subblock using the arithmetic decoding process. The decoder decodes the transform block based on the determined sb_coded_flag.

Abstract: Video encoding/decoding methods and systems for spatial geometric partitioning mode improvement are disclosed. The video encoding/decoding method includes encoding/decoding a candidate-index code into/from a bitstream, wherein the candidate-index code is associated with intra-partition prediction and a template including one or more index-specified reference lines among a plurality of reference lines having a plurality of reconstructed samples spatially neighboring a block associated with a spatial geometric partitioning mode (SGPM).

Abstract: A system and method of decoding a sub-block of residual coefficients of a transform block from a video bitstream. The method comprises determining whether sign bit hiding is used for the sub-block, the determination based on a value of a transform skip flag determined for the sub-block and a value of a sign bit hiding flag associated with the sub-block; if sign bit hiding is not used, decoding a number of sign bits equal to a number of significant coefficients in the subblock; and decoding the sub-block by reconstructing the residual coefficients of the sub-block using the decoded sign bits.

Abstract: A method for decoding a video includes (i) determining a partition mode of a current block of the video; (ii) identifying corresponding luma blocks of the current block; and (iii) determining whether one or more of the corresponding luma blocks is coded with a pre-determined mode based on a pre-defined order. In response to a determination that one or more of the corresponding luma blocks is coded with the pre-determined mode, the method further comprises applying the pre-determined mode to a chroma block of the present block.

Abstract: A video encoder encodes a video into a video bitstream. The video encoder accesses a set of frames of the video and performs inter prediction for the set of frames using a set of integerized interpolation filters to generate prediction residuals to be encoded into the video bitstream. The set of integerized interpolation filters are generated by integerizing a set of interpolation filters, each of the set of interpolation filters having floating-point filter coefficients. For each interpolation filter, two integerized filter coefficient values are generated for each filter coefficient and a set of filter candidates are generated based on the two integerized values for each filter coefficient. An error metric for each filter candidate is calculated and an integerized interpolation filter having the lowest error metric is selected for the interpolation filter from the set of filter candidates.

Abstract: According to one aspect of the present application, a method of decoding by a decoder is provided. The method may include parsing, by a processor, a bitstream to determine an intra template matching prediction (TMP) mode associated with a current block. The method may include obtaining, by the processor, at least one fractional-pel block vector (BV) for decoding the current block. The method may include obtaining, by the processor, a reference block based on the at least one fractional-pel BV. The method may include decoding, by the processor, the current block based on the reference block. The method may include obtaining, by the processor, a converted fractional-pel BV based on the at least one fractional-pel BV and after the current block is decoded. The method may include storing, by the processor, the converted fractional-pel BV for decoding another block.

Abstract: A system and method of decoding information for data generated by a first part of a neural network. The method comprises decoding information for determining at least a starting layer of a second part of the neural network, the neural network including at least the first part and the second part, the second part being different from the first part; and determining the starting layer of the second part of the neural network based on the decoded information.

Abstract: According to one aspect of the present disclosure, a method of decoding by a decoder is provided. The method includes: parsing, by a processor, a bitstream to decode a plurality of syntax elements associated with intra template matching prediction (intraTMP); decoding, by the processor, a first syntax element from the bitstream; determining, by the processor, whether an intraTMP mode is enabled for a current block based on the first syntax element; in response to the intraTMP mode being enabled for the current block, decoding, by the processor, a second syntax element from the bitstream; determining, by the processor, whether an intraTMP predictor for the current block is determined by an intraTMP fusion mode based on the second syntax element; and decoding, by the processor, the current block based on the intraTMP predictor.

Abstract: In some embodiments, a video encoder encodes a video into a video bitstream. The video encoder accesses a set of frames of the video and performs inter prediction for the set of frames using a set of integerized interpolation filters to generate prediction residuals to be encoded into the video bitstream. The set of integerized interpolation filters are generated by integerizing a set of interpolation filters, each of the set of interpolation filters having floating-point filter coefficients. For each interpolation filter, two integerized filter coefficient values are generated for each filter coefficient and a set of filter candidates are generated based on the two integerized values for each filter coefficient. An error metric for each filter candidate is calculated and an integerized interpolation filter having the lowest error metric is selected for the interpolation filter from the set of filter candidates.

Abstract: A prediction method applied to a video decoder includes decoding an intra prediction mode from a bitstream and performing an intra fusion prediction of a current block to obtain a prediction block, where the intra fusion prediction includes predicting the current block based on a plurality of reference sample lines and the intra prediction mode.

Abstract: A video coding method, an encoder, and a decoder are disclosed. The method is applied to a decoder and comprises retrieving a bitstream corresponding to a current frame and parsing the bitstream to obtain a current coding tree unit (CTU) of the current frame; determining an availability of at least one neighbouring CTU of the current CTU in the current frame according to a wavefront delay, wherein the wavefront delay is a delay in units of CTUs in a row direction between the current CTU at a current CTU row and the neighbouring CTU at a previous CTU row which are decoded in parallel; determining a prediction block in the at least one neighbouring CTU for a current coding unit (CU) in the current CTU; and decoding the current CU using the prediction block.

Abstract: A system and method of decoding information for data generated by a first part of a neural network. The method comprises decoding information for determining at least a starting layer of a second part of the neural network, the neural network including at least the first part and the second part, the second part being different from the first part; and determining the starting layer of the second part of the neural network based on the decoded information.

Abstract: In some embodiments, a video decoder decodes a video bitstream into video frames. A decoder decodes frames of a video from a video bitstream. The decoder further performs inter prediction to decode a current frame of the video by using the decoded frames as reference frames. Performing the inter prediction includes performing reference picture resampling by upsampling a reference frame for the current frame using one or more filters selected from a set of 32 6-tap interpolation filters. This set of interpolation filters is also used for interpolating chroma components for motion compensation. The decoded frame and the decoded current frame are output for display.

Abstract: A method of decoding a video, a method of encoding a video, and a non-transitory computer-readable storage medium storing a bitstream are provided. In the method of decoding, an additional bit count M indicating a quantity of addition general constraints information (GCI) bits included in a bitstream of the video is decoded from the bitstream of the video. Here, an expected value of the additional bit count M is 0, 6 or greater than 6. In response to determining that a value of the additional bit count M is equal to 6, six flag bits representing six respective flags indicating six respective additional coding tools to be constrained for the video are decoded from the bitstream of the video. A remaining portion of the bitstream of the video is decoded into images based, at least in part, upon constraints for the six additional coding tools indicated by the six flags.

Abstract: In some embodiments, a video encoder encodes a video into a video bitstream. The video encoder accesses a set of frames of the video and performs inter prediction for the set of frames using a set of integerized interpolation filters to generate prediction residuals to be encoded into the video bitstream. The set of integerized interpolation filters are generated by integerizing a set of interpolation filters, each of the set of interpolation filters having floating-point filter coefficients. For each interpolation filter, two integerized filter coefficient values are generated for each filter coefficient and a set of filter candidates are generated based on the two integerized values for each filter coefficient. An error metric for each filter candidate is calculated and an integerized interpolation filter having the lowest error metric is selected for the interpolation filter from the set of filter candidates.

Abstract: A video decoder reconstructs a current frame of a video from a video bitstream based on a reconstructed reference frame. For a block of the current frame, the video decoder identifies a reference block in the reference frame based on a motion vector associated with the block. The decoder determines the slope and offset parameters of a local illumination compensation model based on reconstructed pixels in the current frame and the reference frame. The video decoder decodes, from the video bitstream, an adjustment to the slope and updates the slope by applying the decoded adjustment. The decoder further determines an adjusted offset parameter for the local illumination compensation model. The decoder generates predicted pixels for the block by at least applying, to the reference block, the local illumination compensation model with the updated parameters.

Abstract: A system and method of decoding a sub-block of residual coefficients of a transform block from a video bitstream. The method comprises determining whether sign bit hiding is used for the sub-block, the determination based on a value of a transform skip flag determined for the sub-block and a value of a sign bit hiding flag associated with the sub-block; if sign bit hiding is not used, decoding a number of sign bits equal to a number of significant coefficients in the subblock; and decoding the sub-block by reconstructing the residual coefficients of the sub-block using the decoded sign bits.

Abstract: A system and method of decoding a sub-block of residual coefficients of a transform block from a video bitstream. The method comprises determining whether sign bit hiding is used for the sub-block, the determination based on a value of a transform skip flag determined for the sub-block and a value of a sign bit hiding flag associated with the sub-block; if sign bit hiding is not used, decoding a number of sign bits equal to a number of significant coefficients in the subblock; and decoding the sub-block by reconstructing the residual coefficients of the sub-block using the decoded sign bits.