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 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 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: A method for inverse quantization of a current block of a picture is performed by a decoder, and the picture comprises a luminance component and a chrominance component, wherein the luminance component and the chrominance component are partitioned into multiple blocks. The method includes: obtaining one or more existing quantization parameter (QP) values from a received bitstream, wherein the one or more existing QP values relate to a current block in the chrominance component; determining a QP value for the current block in the chrominance component based on the one or more existing QP values; and performing inverse quantization on the current block in the chrominance component by using the determined QP value.

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 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.

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 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: A method for inverse quantization of a current block of a picture is provided. The method is performed by a decoder, and the picture comprises a luminance component and a chrominance component, where the luminance component and the chrominance component are partitioned into multiple blocks. The method includes obtaining one or more existing quantization parameter (QP) values from a received bitstream, wherein the one or more existing QP values are associated with a current block in the chrominance component; determining a QP value for the current block in the chrominance component based on the one or more existing QP values; performing inverse quantization on the current block in the chrominance component using the determined QP value.

Abstract: The present disclosure relates to efficient signaling of feature map information for a system employing a neural network. In particular, at the decoder side, a presence indicator is obtained based on information parsed from a bitstream. Based on the value of the obtained presence indicator, further data related to a feature map region are parsed or the parsing is bypassed. The presence indicator may be, for instance, a region presence indicator indicating whether feature map data is included in the bitstream or may be a side information presence indicator indicating whether a side information related to the feature map data is included in the bitstream. Similarly, an encoding method, as well as encoding and decoding devices, are provided. Accordingly, feature map data may be processed more efficiently, by reducing decoding complexity, and the amount of transmitted data can be reduced by applying the bypassing.

Abstract: A method for inverse quantization of a current block of a picture is provided. The method is performed by a decoder, and the picture comprises a luminance component and a chrominance component, where the luminance component and the chrominance component are partitioned into multiple blocks. The method includes obtaining one or more existing quantization parameter (QP) values from a received bitstream, wherein the one or more existing QP values are associated with a current block in the chrominance component; determining a QP value for the current block in the chrominance component based on the one or more existing QP values; performing inverse quantization on the current block in the chrominance component using the determined QP value.

Abstract: Methods and apparatuses are provided for estimating motion vectors of a dense motion field based on subsampled sparse motion field. The sparse motion field includes two or more motion vectors with their respective start positions. For each of the motion vectors, a transformation is derived which transforms the motion vector from its start point into a target point. The transformed motion vectors then contribute to the estimated motion vector on the target position. The contribution of each motion vector is weighted. Such motion estimation may be readily used for video encoding and decoding.