Abstract: An encoding method for a video signal is provided. Partition constraint syntax elements are obtained at a sequence parameter set (SPS) level, including intra prediction-related syntax elements and inter prediction-related syntax elements. The partition constraint syntax elements are arranged such that the intra prediction-related syntax elements are defined before the inter prediction-related syntax elements. Partition constraint syntax elements for dual-tree chroma are grouped together under dual-tree conditions and defined before the inter prediction-related syntax elements. A bitstream including the SPS is generated and sent based on the arranged partition constraint syntax elements.

Abstract: A method for video decoding is provided. The method includes obtaining a current coding unit (CU) of a current picture, wherein the coding unit is partitioned into a plurality of regions; deriving respective motion models for the plurality of regions by using respective coding information; and determining motion information for the current CU based on the respective motion models.

Abstract: A method for video decoding is provided. The method includes determining a first reference picture and/or a second reference picture associated with a current picture comprising a current block; determining an adaptive optical model used in an optical flow based refinement based on the first reference picture and/or the second reference picture; determining an adaptive sliding window size for the current block used in the optical flow based refinement; and deriving a respective motion refinement of each subblock of the current block based on the adaptive optical model and the adaptive sliding window.

Abstract: A method for video coding is provided. The method includes: setting, by an encoder, a first syntax element in a picture parameter set (PPS) specifying whether a picture corresponding to the PPS comprises more than one network abstraction layer (NAL) units and whether the more than one NAL units have a same NAL unit type; setting, by the encoder, a second syntax element in a picture header (PH) specifying whether the picture corresponding to the PH is an intra random access point (IRAP) picture or a gradual decoding refresh (GDR) picture, where a value of the second syntax element is set based on a value of the first syntax element; and forming, by the encoder, a bitstream with the first syntax element and the second syntax element.

Abstract: A method and an apparatus for image filtering in video coding using a neural network are provided. The method includes generating a deblocking strength map indicating boundaries of prediction blocks or partition blocks. The deblocking strength map is input into a neural network, and the neural network filters an input frame based on the deblocking strength map.

Abstract: A method of video decoding, apparatuses and non-transitory computer-readable storage media thereof are provided. The method of video decoding includes obtaining a first parameter based on a first neighbor block of a current block; obtaining a second parameter based on the first neighbor block and/or a second neighbor block of the current block; constructing an affine model using the first parameter and the second parameter; and obtaining a control point motion vector (CPMV) for the current block based on the affine model. The first neighbor block and the second neighbor block are obtained from a plurality of neighbor blocks to the current block based on at least one scanning area and at least one scanning distance. The first neighbor block and the second neighbor block are obtained by scanning the at least one scanning area at the at least one scanning distance.

Abstract: Methods for video decoding and encoding, apparatuses and non-transitory storage media are provided. In one decoding method, the decoder obtains, based on a storage granularity, a normalized position for an affine coding unit (CU) at a non-adjacent position obtained by scanning area that is not adjacent to a current CU. Furthermore, the decoder determines whether valid affine model information is stored for the normalized position, where the valid affine model information includes a position of the affine CU and derives affine model information for the affine CU based on the valid affine model information that is stored for the normalized position in response to determining that the valid affine model information is stored for the normalized position.

Abstract: Implementations of the disclosure provide a video processing apparatus and method for performing intra prediction on a video block. The video processing method may include receiving, by a processor, reference samples from a video frame of a video comprising the video block. The video processing method may further include determining, by the processor, a reference sample filter based on a size of each video block. The reference sample filter is among a plurality of reference sample filters each derived for a different video block size. The video processing method may also include applying, by the processor, the determined reference sample filter to the received reference samples. The video processing method may additionally include performing, by the processor, the intra prediction on the video block using the filtered reference samples.

Abstract: A method for video encoding, a method for video decoding, apparatuses and non-transitory computer-readable storage media thereof are provided. In the method for video decoding, the decoder may obtain one or more filtering parameters, wherein the one or more filtering parameters are from a filtering parameter set comprising a number of similar blocks, a search range, and a window size; obtain, based on the one or more filtering parameters, one or more similar pixels for a first pixel that has been filtered in a picture and the first pixel; and obtain an original pixel associated with the first pixel based on the one or more similar pixels.

Abstract: A time-series InSAR method for monitoring multi-dimensional deformation of a landslide includes the following steps: firstly, obtaining a deformation observation of a target landslide in a line-of-sight direction; and subsequently inputting the deformation observation into a monitoring model with a fractal composite structure deformation constraint model to thereby obtain deformation time series of a sliding mass in vertical, east-west, downslope, and perpendicular-to-downslope directions. This method can simultaneously obtain characteristics of the deformation time series of the sliding mass along four dimensions, namely the vertical, east-west, downslope, and perpendicular-to-downslope directions. A model constructed by the method covers linear, acceleration, periodicity, high frequency, and thermal expansion deformation, fully considering complexity of landslide deformation and having strong adaptability.

Abstract: A method and an apparatus for hybrid training of neural networks for video coding are provided. The method includes: obtaining, in an offline training stage, an offline trained network by training a first neural network offline using a plurality of first data sets; refining, in an online training stage, a plurality of neural network layers using a plurality of second data sets, wherein the plurality of neural network layers comprise at least one neural network layer in the offline trained network or in a second neural network connected to the offline trained network.

Abstract: A method for video encoding, a method for video decoding, and apparatuses thereof are provided. A template-based coding scheme is applied to derive one or more coding parameters associated with a video block from a video frame based on a template of the video block. Reference-picture-resampling (RPR) prediction samples for the video block are generated based on the one or more coding parameters. The RPR prediction samples are filtered by using a filter to generate filtered RPR prediction samples for the video block. The filter is adaptively determined based on the template of the video block.

Abstract: Methods for video decoding and encoding, apparatuses and non-transitory storage media are provided. In one decoding method, the decoder obtains one or more motion vector (MV) candidates from one or more candidate lists according to a predetermined order. The candidate lists include an affine advanced motion vector prediction (AMVP) candidate list, a regular merge candidate list, and an affine merge candidate list, and the one or more MV candidates are derived from a plurality of neighbor blocks of a current block. The decoder may obtain one or more control point motion vectors (CPMVs) for the current block based on the one or more MV candidates.

Abstract: A method for video encoding comprises determining a mode of Local Illumination Compensation (LIC) for the video encoding to be enabled; calculating LIC parameters for the mode of LIC with a limited number of reference sample pairs, wherein a reference sample pair refers to a luma reference sample and a chroma reference sample; enabling the mode of LIC for the video encoding with the calculated LIC parameters to perform LIC for inter prediction to generate a prediction residual; and forming and outputting a bit-stream encoded with the prediction residual and prediction mode information indicating the mode of LIC.

Abstract: A method for video coding is provided. The method includes: setting, by an encoder, a first syntax element in a picture parameter set (PPS) specifying whether a picture corresponding to the PPS comprises more than one network abstraction layer (NAL) units and whether the more than one NAL units have a same NAL unit type; setting, by the encoder, a second syntax element in a picture header (PH) specifying whether the picture corresponding to the PH is an intra random access point (IRAP) picture or a gradual decoding refresh (GDR) picture, wherein a value of the first syntax element is set based on a value of the second syntax element being 1; and forming, by the encoder, a bitstream with the first syntax element and the second syntax element.

Abstract: Methods for video decoding and encoding, apparatuses and non-transitory storage media are provided. In one decoding method, the decoder obtains one or more first parameters based on a first neighbor block selected from a plurality of inter-coded neighbor blocks of a current block, and obtains one or more second parameters based on a second neighbor block selected from a plurality of affine-coded neighbor blocks or a plurality of historically affine-coded neighbor blocks. The decoder constructs an affine model based on the one or more first parameters and the one or more second parameters. The decoder may project the affine model onto the current block to obtain a translational motion vector based on a specific position within the current block or a plurality of control point motion vectors for the current block, depending on whether the current block is coded in a regular inter mode or an affine mode.

Abstract: The present application provides an SFGT storage array, a storage chip, and a data-reading method. The SFGT storage array includes a true semi-floating gate array, a reference semi-floating gate array and a sense amplifier. The true semi-floating gate array includes a plurality of true semi-floating gate storage units, a plurality of first bit lines and a plurality of first word lines. Each of the plurality of first bit lines and each of the plurality of first word lines intersect to operate on one of the true semi-floating gate storage units. Each of the plurality of first bit lines is connected to a first input end of the sense amplifier. The reference semi-floating gate array includes a plurality of second bit lines. Each of the plurality of second bit lines is connected to a second input end of the sense amplifier.

Abstract: Methods for video decoding and encoding, apparatuses and non-transitory computer-readable storage media thereof are provided. One method for video decoding includes obtaining, by a decoder, a current coding unit (CU) coded with a Geometric Partition Mode (GPM); selecting, by the decoder, a candidate from a set of Merge candidates with Block Vector Difference (MBVD) candidates based on a distance index and a direction index; obtaining, by the decoder, a first Intra Block Copy (IBC) prediction using the candidate and a second prediction; and obtaining, by the decoder, a final prediction for the current CU using the first IBC prediction and the second prediction.

Abstract: Methods for video decoding and encoding, apparatuses and non-transitory storage media are provided. In one decoding method, the decoder obtains a set of blending strengths for a current block, where the current block is partitioned into two parts along a partition line for prediction in a geometric partitioning mode. Furthermore, the decoder obtains a mapping relationship between a plurality of blending indices and the blending strengths in the set of blending strengths. Moreover, the decoder obtains a binarized value indicating one of the blending indices, where the blending indices are binarized with variable length code. Further, the decoder determines a blending strength of the current block based on the binarized value and the mapping relationship.

Abstract: An electronic apparatus performs a method of decoding video data. The method comprises, receiving, from bitstream, video data corresponding to a palette-mode coded block; determining a quantization parameter value from information included in a parameter set associated with the palette-mode coded block; identifying escape samples in the palette-mode coded block; in accordance with a determination that the quantization parameter value is greater than a threshold value: performing de-quantization on quantized escape samples according to a predefined formula to obtain reconstructed escape sample values; and in accordance with a determination that the quantization parameter value is less than or equal to the threshold value: setting the reconstructed escape samples to be the quantized escape sample values.