Abstract: The present disclosure provides methods and devices of processing a block according to a merge candidate list, the method comprising: constructing a first list according to motion information of neighboring blocks of a current block; obtaining prediction information of the current block; when the prediction information of the current block indicates that a sub-block prediction is applied to the current block, obtaining a uni-prediction candidate for the current block according to the first list; using, the uni-prediction candidate for the current block to perform inter prediction of the current block. According to embodiment of the present disclosure, the regular merge list can be directly used and there is no need to explicitly generate the uni-prediction merge candidate list for sub-block prediction.

Abstract: Motion vectors (MVs) are used as predictors for prediction of an image for a current coding unit (CU) within a current video frame. The MVs are from a list of motion vector candidates (MVCs), which is generated. The list includes MVs determined from a first or second pattern, each pattern specifying MVC positions. The first MV positions are within a current video frame, while the second MV positions are for a video frame different from the current frame. The MVC list is generated for a current CU with the MV positions being relative to a position of the current CU. In particular, the MVC list is generated in dependence on a size of the current CU and a size of a grid specifying a minimum distance between two MV positions. One or more MVs as specified by the MV positions of said pattern are included into the MVC list.

Abstract: A method of determining a distance table of a merge with motion vector difference (MMVD) mode, wherein the method comprises determining a reference picture from at least one reference picture list of a current processing unit based on at least one parameter of the reference picture, and obtaining the distance table for the current processing unit based on the reference picture, wherein the at least one parameter of the reference picture comprises a picture order count (POC) number of the reference picture, a number of MMVD blocks of the reference picture, a reference picture list index of the reference picture, a reference picture index of the reference picture, and a quantization parameter (QP) of the reference picture.

Abstract: The present disclosure relates to a method and apparatus for motion vector derivation for affine based inter prediction of chroma subblocks based on a chroma format. The method includes: determining chroma scaling factors in horizontal and vertical directions based on chroma format information, wherein the chroma format information indicates a chroma format of a current picture which the current image block belongs to; determining a set of luma subblocks of the luma block based on values of the chroma scaling factors; and determining a motion vector for a chroma subblock of the co-located chroma block based on motion vectors of one or more luma subblocks in the set of luma subblocks.

Abstract: The present disclosure relates to video encoding and decoding, and in particular, a method for inter prediction for a block in a frame of a video signal includes: constructing a history-based motion information candidate list, wherein the list is an ordered list comprising N history-based motion information candidates Hk containing motion information of N preceding blocks preceding the block, wherein each history-based motion information candidate comprises: one or more motion vectors (MVs), one or more reference picture indices corresponding to the MVs, and an interpolation filter index; adding one or more history-based motion information candidates from the history-based motion information candidate list into a motion information candidate list for the block; and deriving motion information for the block based on the motion information candidate list.

Abstract: The present disclosure provides methods and devices of processing a block according to a merge candidate list, the method comprising: constructing a first list according to motion information of neighboring blocks of a current block; obtaining prediction information of the current block; when the prediction information of the current block indicates that a sub-block prediction is applied to the current block, obtaining a uni-prediction candidate for the current block according to the first list; using, the uni-prediction candidate for the current block to perform inter prediction of the current block. According to embodiment of the present disclosure, the regular merge list can be directly used and there is no need to explicitly generate the uni-prediction merge candidate list for sub-block prediction.

Abstract: A sparse motion field exchanges motion information between encoder and decoder. Side information indicates a suitable interpolation approach for interpolating the motion vectors of the dense motion field different from the signaled sparse motion field motion vectors. The side information is provided on a segment basis. The segments are derived at the encoder side and the decoder side similarly, based on the reference images and the sparse motion field.

Abstract: The disclosure provides a motion vector compression method, comprising: obtaining a temporal motion vector; determining a compressed motion vector using a binary representation of the temporal motion vector comprising an exponent part and/or a mantissa part, wherein the exponent part comprises N bits, the mantissa part comprises M bits, and wherein N is a non-negative integer and M is a positive integer; and performing a temporal motion vector prediction (TMVP) using the compressed motion vector.

Abstract: This application provides methods and apparatuses for processing of picture data or picture feature data using a neural network with two or more layers. The present disclosure may be applied in the field of artificial intelligence (AI)-based video or picture compression technologies, and in particular, to the field of neural network-based video compression technologies. According to some embodiments, position within the neural network, at which auxiliary information may be entered for processing is selectable based on a gathering condition. The gathering condition may assess whether some prerequisite is fulfilled. Some of the advantages may include better performance in terms of rate and/or disclosure due to the effect of increased flexibility in neural network configurability.

Abstract: The present disclosure relates to video encoding and decoding, and in particular to determining motion information for a current block using a history-based motion vector predictor, HMVP, list. The HMVP list is constructed, with said list being an ordered list of N HMVP candidates Hk, k=0, . . . , N?1, which are associated with motion information of N preceding blocks of the frame and precede the current block. Each HMVP candidate has motion information including elements of one or more motion vectors, MVs, one or more reference picture indices corresponding to the MVs, and one or more bi-prediction weight indices. One or more HMVP candidates from the HMVP list are added into a motion information candidate list for the current block; and the motion information is derived based on the motion information candidate list.

Abstract: An apparatus and method for inter prediction of a block includes estimating local illumination compensation (LIC) parameters using first reference samples of a current block and second reference samples of a reference block, wherein a third reference sample of the second reference samples is based on an integer part of a fractional motion vector (MV), and obtaining inter prediction of the current block according to the LIC parameters.

Abstract: The present disclosure relates to methods and apparatuses for encoding video data into a bitstream and for decoding video data received in a bitstream. A second control flag indicating whether or not to use multi-hypothesis prediction for intra and inter mode is generated and transmitted only conditionally, upon a determination whether or not separate merge list technique for subblock merge candidates is used. On the other hand, a decoder is capable of deciding usage of multi-hypothesis prediction for intra and inter mode and separate merge list technique for subblock merge candidates even though the second control flag is transmitted only conditionally.

Abstract: A method of obtaining quantization parameter (QP) for chrominance components based on QP for luminance component, wherein the method is performed by a decoder or encoder, and wherein the method comprises obtaining a luminance QP for a luma component of a coding unit; obtaining a QP index (QPi) based at least in a part on the luminance QP; and obtaining a chrominance QP (QPc) for a chroma component of the coding unit based on the QP index by using a preset lookup table, wherein the maximum difference between the QP index and the chrominance QP is equal to 3.

Abstract: Methods and apparatuses for compression of feature tensors of a neural network are provided. One or more encoding parameters for encoding the channels of a feature tensor are selected according to the importance of the channels. This enables unequal bit allocation according to the importance. Furthermore, the deployed neural network may be trained or fine-tuned considering the effect of encoding noise applied to the intermediate feature tensors. According to the present disclosure, the encoding and modified training methods are advantageous at least for employment in a collaborative intelligence framework.

Abstract: Apparatuses and methods for Intra Sub-Partitions (ISP) are provided. The method includes: obtaining information of ISP, and determining a size of a chroma transform block (TB) of the coding unit based on SubWidthC and SubHeightC when at least a first condition is fulfilled. The first condition includes the information of ISP indicates that ISP is used for splitting the luma coding block. SubWidthC and SubHeightC are variables depending on chroma format information. The chroma format information indicates a chroma format of a picture the coding unit belongs to. The method can apply to all chroma format. The chroma format includes at least one of: 4:2:0, or 4:2:2, or 4:4:4. An accurate and versatile way to determine the size of the chroma transform block for the ISP is achieved.

Abstract: The disclosure provides a motion vector compression method, comprising: obtaining a temporal motion vector; determining a compressed motion vector using a binary representation of the temporal motion vector comprising an exponent part and/or a mantissa part, wherein the exponent part comprises N bits, the mantissa part comprises M bits, and wherein N is a non-negative integer and M is a positive integer; and performing a temporal motion vector prediction (TMVP) using the compressed motion vector.

Abstract: A method and apparatus for decoding data for still or video processing into a bitstream are provided. In particular, two or more sets of feature map elements are obtained from the bitstream. Each set of feature map elements relates to a feature map. Each of the two or more sets of feature map elements is then respectively inputted into two or more feature map processing layers out of a plurality of cascaded layers. The decoded data for picture or video processing is then obtained as a result of the processing by the plurality of cascaded layers. According to the present disclosure, the data may be decoded from the bitstream in an efficient manner in the layered structure.

Abstract: The present disclosure relates to methods and apparatuses for encoding video data into a bitstream and for decoding video data received in a bitstream. A second control flag indicating whether or not to use multi-hypothesis prediction for intra and inter mode is generated and transmitted only conditionally, upon a determination whether or not separate merge list technique for subblock merge candidates is used. On the other hand, a decoder is capable of deciding usage of multi-hypothesis prediction for intra and inter mode and separate merge list technique for subblock merge candidates even though the second control flag is transmitted only conditionally.

Abstract: The present disclosure relates to methods and apparatuses for decoding data for (still or video processing into a bitstream). Two or more sets of segmentation information elements are obtained from the bitstream. Then, each of the two or more sets of segmentation information elements are inputted respectively into two or more segmentation information processing layers out of a plurality of cascaded layers. In each of the two or more segmentation information processing layers, the respective sets of segmentation information are processed. The decoded data for picture or video processing are obtained based on the segmentation information processed by the plurality of cascaded layers. Accordingly, the data may be decoded from the bitstream in an efficient manner in the layered structure.

Abstract: The present disclosure relates to methods and apparatuses for encoding data for (still or video processing into a bitstream). In particular, the data are processed by a network which includes a plurality of cascaded layers. In the processing, feature maps are generated by the layers. The feature maps processed (output) by at least two different layers have different resolutions. In the processing, a layer is selected, out of the cascaded layers, which is different from the layer generating the feature map of the lowest resolution (e.g. latent space). The bitstream includes information related to the selected layer. With this approach, scalable processing which may operate on different resolutions is provided so that the bitstream may convey information relating to such different resolutions. Accordingly, the data may be efficiently coded within the bitstream, depending on the resolution which may vary depending on the content of the picture data coded.