Abstract: A method of decoding a bitstream to get one or more pictures for a video stream includes: receiving a bitstream; and decoding the bitstream to get the one or more pictures. The decoding includes: decoding a picture unit comprising one or more supplemental enhancement information (SEI) messages; and generating the one or more pictures based on a key picture and the one or more SEI messages, respectively.

Abstract: Methods and systems implement interpolation filters for motion prediction, and more specifically interpolation filters for template matching and decoder-side motion vector refinement (“DMVR”). A VVC and later standard encoder and a VVC and later standard decoder can configure one or more processors of a computing system to signal that at least one of a first filter derived by discrete cosine transform-based interpolation filter, a second filter derived by a cubic-based interpolation filter, and a third filter derived by a cubic-based interpolation filter are applied in a template matching-based mode, applied in DMVR search, or applied in both.

Abstract: Methods and systems implement application of chained motion vector prediction (“CMVP”). A VVC and later standard encoder and a VVC and later standard decoder, and/or an AVS3 and later-standard encoder and an AVS3 and later-standard decoder, can configure one or more processors of a computing system to apply CMVP in conjunction with Advanced Motion Vector Prediction (“AMVP”) mode while constructing spatially neighboring MVP candidates; apply CMVP in conjunction with Affine merge mode when inheriting Affine candidates; and apply CMVP in conjunction with subblock-based temporal motion vector prediction (“SbTMVP”) to obtain new motion shifts.

Abstract: The present disclosure provides a computer-implemented method for encoding or decoding video. The method includes encoding or decoding, in a plurality of picture parameter sets (PPS) associated with pictures of a coded layer video sequence (CLVS), corresponding first PPS flags indicating whether pictures are allowed to be partitioned into a plurality of tiles or slices. In a first PPS, a corresponding first PPS flag with a first value indicates a first picture of the CLVS is unpartitioned, and in a second PPS, another corresponding first PPS flag with a second value being different from the first value indicates that a second picture of the CLVS is allowed to be partitioned.

Abstract: Embodiments of the present disclosure provide a pixel value mapping method, including: determining a to-be-processed image and a mapping table corresponding to the to-be-processed image; performing a table lookup on pixel values of multiple pixels in the to-be-processed image according to the mapping table in parallel to obtain mapped values each corresponding to a pixel of the multiple pixels; and determining a mapped image corresponding to the to-be-processed image according to the mapped values obtained based on the table lookup.

Abstract: A video decoding method includes receiving a bitstream; and decoding, using coded information of the bitstream, one or more pictures. The decoding includes decoding a first face feature of a facial image in a first type from the bitstream; translating the first face feature to a second face feature in a second type; and reconstructing the facial image based on the second face feature.

Abstract: The present disclosure provides a method of encoding a video sequence. The method includes receiving a video sequence; encoding the video sequence using an extrapolation filter-based intra prediction (EIP) fusion mode. The encoding the video sequence using the EIP fusion mode includes obtaining a first predictor by an extrapolation filter-based intra prediction (EIP) mode; obtaining a second predictor by an intra prediction mode; generating a fused predictor by fusing the first predictor and the second predictor; and predicting one or more pictures using the fused predictor.

Abstract: A VVC and later standard encoder and a VVC and later standard decoder are provided, configuring one or more processors of a computing system to perform motion vector refinement for geometric partitioning for motion prediction, and more specifically application of first-pass and second-pass Decoder-side Motion Vector Refinement (“DMVR”) in GPM motion prediction. The VVC and later standard encoder and decoder implement performing motion prediction upon two partitions of a geometric partitioning mode (GPM)-coded coding block, based on respective motion information of each partition, and applying weighted blending to respective motion predictions of each partition of the GPM-coded coding block based on a blending matrix, wherein the blending matrix depends on a split mode.

Abstract: A method and apparatus for video processing include: determining to skip a transform process for a prediction residual based on a maximum transform size of a prediction block; and signaling the maximum transform size in a sequence parameter set (SPS).

Abstract: An AVS3 and later-standard encoder and an AVS3 and later-standard decoder are provided, configuring one or more processors of a computing system to perform motion vector refinement in motion prediction by inter prediction in skip mode or direct mode. The encoder and the decoder are configured to implement preliminary searching before reordering motion candidates of a motion candidate list; prioritized candidate reordering and weighted candidate reordering; an Inter TM candidate list including one or more SBTMVP candidates and ETMVP candidates; TM-based refinement based on combined reference templates; conditional motion vector derivation for TMVP candidates; and converting a bi-predicted block to a uni-predicted block.

Abstract: An AVS3 and later-standard encoder and an AVS3 and later-standard decoder are provided, configuring one or more processors of a computing system to perform decoder-side motion vector refinement and affine motion compensation upon a same coding block. The encoder and the decoder are configured to implement one or both of refining a base motion vector of the affine model and refining non-translational parameters of the affine model by searching to minimize bilateral matching (“BM”) cost.

Abstract: A VVC-standard encoder and a VVC-standard decoder are provided, configuring one or more processors of a computing system to apply additional transform cores for inter coded blocks and apply a decoder side intra mode derivation (“DIMD”) process to inter prediction samples or residual samples to derive an intra prediction angular mode.

Abstract: A computer-implemented method for training spatial resampling modules includes: down-sampling, by a down-sampling module, an input image data to generate a down-sampled image data; up-sampling, by an up-sampling module, the down-sampled image data to generate a first up-sampled image data; analyzing, by a plurality of analysis models corresponding to a plurality of tasks, the first up-sampled image data; and training the down-sampling module based on a loss function associated with the plurality of analysis models according to the input image data and the first up-sampled image data.

Abstract: A video decoding method includes: selecting a first intra prediction mode and a second intra prediction mode from a most probable mode (MPM) list; determining a first predictor based on the first intra prediction mode; determining a second predictor based on the second intra prediction mode; blending the first predictor and the second predictor to obtain a blended predictor for intra prediction; and decoding one or more pictures using the blended predictor.

Abstract: Systems and methods are described for video coding using generalized bi-prediction. In an exemplary embodiment, to code a current block of a video in a bitstream, a first reference block is selected from a first reference picture and a second reference block is selected from a second reference picture. Each reference block is associated with a weight, where the weight may be an arbitrary weight ranging, e.g., between 0 and 1. The current block is predicted using a weighted sum of the reference blocks. The weights may be selected from among a plurality of candidate weights. Candidate weights may be signaled in the bitstream or may be derived implicitly based on a template. Candidate weights may be pruned to avoid out-of-range or substantially duplicate candidate weights. Generalized bi-prediction may additionally be used in frame rate up conversion.

Abstract: Systems and methods are disclosed for encoding and for decoding of video data, including predicting a video block of the video data using decoder-side intra mode derivation (DIMD). The disclosed predicting techniques include selecting candidate intra prediction modes based on intra prediction modes used by neighboring video blocks. Techniques disclosed further include determining respective costs of using the selected candidate intra prediction modes to predict samples in a template region adjacent to the video block, deriving an intra prediction mode from the selected candidate intra prediction modes having the lowest cost, and predicting samples in the video block using the derived intra prediction mode.

Abstract: Processing a 360-degree video content for video coding may include receiving the video content in a first geometry. The video content may include unaligned chroma and luma components associated with a first chroma sampling scheme. The unaligned chroma and luma components may be aligned to a sampling grid associated with a second chroma sampling scheme that has aligned chroma and luma components. A geometric conversion to the video content may be performed. The video content, that may comprise the aligned chroma and luma components, in the first geometry may be converted to a second geometry. The first geometry may be a stitched geometry, and the second geometry may be a coding geometry. The converted video content in the second geometry may include the chroma and luma components aligned to the sampling grid associated with the second chroma sampling scheme.

Abstract: Methods and apparatuses are provided for encoding and decoding video data based on a supplemental enhancement information (SEI) message. An exemplary method includes: generating a reconstructed frame sequence based on a compressed video; decoding a supplemental enhancement information (SEI) message with respect to the reconstructed frame sequence, according to the compressed video; and performing temporal upsampling to the reconstructed frame sequence based on the SEI message by using a neural network.

Abstract: Methods and apparatuses are provided for processing video data by using an object mask information (OMI) supplemental enhancement information (SEI) message. An exemplary encoding method includes: receiving a video sequence; and encoding one or more pictures of the video sequence to generate a bitstream, comprising: encoding an auxiliary picture indicating a mask of an object in a primary picture, the mask of the object being represented by a sample value of the auxiliary picture; and generating a supplemental enhancement information (SEI) message indicating an attribute of the mask of the object.

Abstract: A system may receive an input image block, and input the input image block into multiple models which may be trained using a plurality of different datasets of image blocks. Each model of the multiple models may be trained using a dataset having similar attributes. The system may determine a model having a highest compression efficiency from among the multiple models, and encode the input image block using the determined model.