Abstract: Embodiments of the present disclosure provide an inter-frame prediction method performed at a computing device. The method includes: determining at least one reference encoded block spatially adjacent to a to-be-processed prediction unit of a to-be-processed encoded block; for each preset reference frame, separately determining a corresponding AMVP of the to-be-processed prediction unit according to reference information of each reference encoded block; determining a target AMVP under the reference frames, and using a reference frame corresponding to the target AMVP as a candidate reference frame; when the candidate reference frame is different from the first reference frame, performing motion estimation on the to-be-processed prediction unit separately and determining a target reference frame from the candidate reference frame and the first reference frame according to their corresponding encoding costs obtained through the motion estimation.

Abstract: Embodiments of the present disclosure provide an intra-frame prediction method and apparatus, and a non-transitory computer-readable storage medium. In the method, pixel main directions of reference coded blocks that spatially neighbor a target to-be-coded block are determined. For each of the pixel main directions, a search is performed for an intra-frame prediction direction that is within a set distance value of the respective pixel main direction. Candidate intra-frame prediction directions are formed at least according to the intra-frame prediction directions. Prediction and coding are performed on the target to-be-coded block according to the candidate intra-frame prediction directions. Further, a target intra-frame prediction direction in the candidate intra-frame prediction directions is determined according to results of the prediction and coding on the target to-be-coded block according to the candidate intra-frame prediction directions.

Abstract: An encoding method, a decoding method, an encoding apparatus, a decoding apparatus, for a video image. The encoding method includes: determining an optimal merged neighboring block for a current block based on a motion vector merging technology; determining, based a prediction direction of the optimal merged neighboring block, a motion vector derivation mode that needs to be used by a decoder; correcting a motion vector of the current block based on the motion vector derivation mode; and determining a residual between a predicted value and an original value of the current block based on the corrected motion vector, thereby encoding the current block. According to the technical solutions, a more accurate predicted value is obtained by correcting the motion vector, and a smaller residual is generated.

Abstract: Embodiments of a picture prediction method and a related apparatus are disclosed. A picture prediction method includes: determining K1 pixel samples in a picture block x, and determining a candidate motion information unit set corresponding to each pixel sample in the K1 pixel samples, where the candidate motion information unit set corresponding to each pixel sample includes at least one candidate motion information unit; determining a merged motion information unit set i including K1 motion information units, where each motion information unit in the merged motion information unit set i is selected from at least a part of motion information units in candidate motion information unit sets corresponding to different pixel samples in the K1 pixel samples; and predicting a pixel value of the picture block x by using a non-translational motion model and the merged motion information unit set i.

Abstract: A picture prediction method and a related apparatus are disclosed. A picture prediction method includes: determining K1 pixel samples in a picture block x, and determining a candidate motion information unit set corresponding to each pixel sample in the K1 pixel samples, where the candidate motion information unit set corresponding to each pixel sample includes at least one candidate motion information unit; determining a merged motion information unit set i including K1 motion information units, where each motion information unit in the merged motion information unit set i is selected from at least a part of motion information units in candidate motion information unit sets corresponding to different pixel samples in the K1 pixel samples; and predicting a pixel value of the picture block x by using a non-translational motion model and the merged motion information unit set i.

Abstract: A picture prediction method includes: determining two pixel samples in a current picture block, and determining a candidate motion information unit set corresponding to each of the two pixel samples; determining a merged motion information unit set i including two motion information units; and predicting a pixel value of the current picture block by using an affine motion model and the merged motion information unit set i.

Abstract: A picture prediction method includes: determining two pixel samples in a current picture block, and determining a candidate motion information unit set corresponding to each of the two pixel samples; determining a merged motion information unit set i including two motion information units; and predicting a pixel value of the current picture block by using an affine motion model and the merged motion information unit set i.

Abstract: A coding unit (CU) depth determining method and apparatus are provided. The method includes determining a residual coefficient of a current optimal mode of a to-be-processed CU; and respectively obtaining, when the residual coefficient is not 0, coding information features of the to-be-processed CU corresponding to a specific frame type and coding information features of a neighboring coding tree unit (CTU) corresponding to the specific frame type of a CTU in which the to-be-processed CU is located, to form prediction feature vector samples. The method also includes inputting the prediction feature vector samples to a pre-trained predictive model corresponding to the specific frame type, to obtain a prediction result. The prediction result indicates whether depth division needs to be performed on the to-be-processed CU.

Abstract: Embodiments of the present application relate to a video image encoding method, a video image decoding method, an encoding device, and a decoding device. The method includes: determining a motion vector group of a current encoding block; determining prediction values of a first component set of a motion model initialization vector; determining values of the first component set according to the prediction values of the first component set; and encoding the values of the first component set, and transmitting encoded values of the first component set. According to the video image encoding method in the embodiments of the present application, a motion model initialization vector is determined according to a motion vector group; values of a motion model are determined according to the motion model initialization vector. In this way, a volume of data and a quantity of occupied bits in encoding and decoding transmission can be reduced.

Abstract: An image encoding method includes: determining N encoded units from adjacent encoded units of a to-be-encoded unit according to a first preset rule, where a motion prediction mode of the N encoded units is the same as that of the to-be-encoded unit; generating an nth motion vector group by using a first preset algorithm and based on a motion vector of an nth encoded unit; determining, from obtained N motion vector groups according to a second preset rule, one motion vector group as an optimal motion vector group; determining a prediction sample value of each sample unit in the to-be-encoded unit by using a second preset algorithm and based on the optimal motion vector group; and encoding a prediction residual of each sample unit and an index identifier of the optimal motion vector group, to obtain a bitstream corresponding to the to-be-encoded unit.

Abstract: The present invention relates to the field of video image processing, and provides a filtering method and an apparatus, to resolve a problem that subjective quality and objective quality of an image deteriorate because filtering processing cannot be performed on internal blocks of a non-translational motion prediction unit.

Abstract: An image processing method includes acquiring N pieces of motion information from N adjacent image blocks adjacent to a current image block, where the N adjacent image blocks are in a one-to-one correspondence with the N pieces of motion information, and the N pieces of motion information are in a one-to-one correspondence with the N reference image blocks, determining candidate motion information from the N pieces of motion information according to a preset rule, determining, in the reference image, a location range of a to-be-stored pixel, and storing all pixels in the location range, where the location range covers all pixels of a candidate reference image block, and reading the pixels in the location range, and performing encoding processing on the current image block according to the pixels in the location range.

Abstract: A method and device for generating a predicted value of image to generate a predicted value of a current block during image encoding or decoding is disclosed, where the method includes determining a searching scope, wherein a plurality of motion vectors are included in the searching scope, performing up-sampling interpolations on first reference blocks corresponding to the motion vector in the searching scope, in a reference image of the current block using a first filter to obtain up-sampled first reference blocks, obtaining, using the up-sampled first reference blocks, at least one candidate motion vector corresponding to the current block, performing up-sampling interpolations on second reference blocks, corresponding to the at least one candidate motion vector, in the reference image of the current block using a second filter to obtain up-sampled second reference blocks, combining the up-sampled second reference blocks to obtain a predicted value of the current block.

Abstract: A reference frame decoding method includes obtaining a first reference frame, where the first reference frame is a first picture frame on which decoding reconstruction has been performed or a first interpolated picture frame obtained by pixel interpolation on the first picture frame, parsing a bitstream to obtain mapping parameters, determining to-be-determined coefficients of a preset mapping function according to the mapping parameters, obtaining, in the first reference frame according to the mapping function whose to-be-determined coefficients have been determined, a first pixel unit having a mapping relationship with a second pixel unit of a second reference frame, and assigning a pixel value of the first pixel unit to the second pixel unit.

Abstract: An image prediction method and apparatus is disclosed. The image prediction method includes: determining, according to information about adjacent image units adjacent to a to-be-processed image unit, whether a set of candidate prediction modes for the to-be-processed image unit includes an affine merge mode, where the affine merge mode indicates that respective predicted images of the to-be-processed image unit and the adjacent image units of the to-be-processed image unit are obtained by using a same affine model; parsing a bitstream to obtain first indication information; determining, in the set of candidate prediction modes, a prediction mode for the to-be-processed image unit according to the first indication information; and determining a predicted image of the to-be-processed image unit according to the prediction mode. The method reduces a bit rate of encoding a prediction mode, thereby improving encoding efficiency.

Abstract: A video encoding and decoding method and apparatus are provided. The video encoding method includes: obtaining a first statistical characteristic of previous K frames of images of a video sequence; determining a first background frame; determining, according to the first statistical characteristic, a QP used for encoding the first background frame; encoding the first background frame according to the QP, to obtain a first background long-term reference frame; and encoding the (K+1)th frame of image of the video sequence to the (K+L)th frame of image of the video sequence according to the first background long-term reference frame. When encoding is performed on the (K+1)th frame of image of the video sequence to the (K+L)th frame of image of the video sequence, the used QP for encoding the background long-term reference frame is determined according to the first statistical characteristic related to video content of the previous K frames of images.

Abstract: A picture prediction method includes: determining motion vectors of W control points in a current picture block; obtaining motion vectors of P pixel units of the current picture block by using a motion model and the motion vectors of the W control points, where precision of the determined motion vectors of the W control points is 1/n of pixel precision, precision of the motion vector of each of the P pixel units is 1/N of the pixel precision, the motion vector of each of the P pixel units is used to determine a corresponding reference pixel unit in a reference picture of a corresponding pixel unit; and performing interpolation filtering on a pixel of the corresponding reference pixel unit by using an interpolation filter with a phase of Q, to obtain a predicted pixel value of each of the P pixel units.

Abstract: A method and device for generating a predicted value of image to generate a predicted value of a current block during image encoding or decoding is disclosed, where the method includes determining a searching scope, wherein a plurality of motion vectors are included in the searching scope, performing up-sampling interpolations on first reference blocks corresponding to the motion vector in the searching scope, in a reference image of the current block using a first filter to obtain up-sampled first reference blocks, obtaining, using the up-sampled first reference blocks, at least one candidate motion vector corresponding to the current block, performing up-sampling interpolations on second reference blocks, corresponding to the at least one candidate motion vector, in the reference image of the current block using a second filter to obtain up-sampled second reference blocks, combining the up-sampled second reference blocks to obtain a predicted value of the current block.

Abstract: Embodiments of the present invention provide an encoding method, a decoding method, an encoding apparatus, a decoding apparatus, for a video image. The encoding method includes: determining an optimal integrated neighboring block for a current block based on a motion vector integration technology; determining, based a prediction direction of the optimal integrated neighboring block, a motion vector derivation mode that needs to be used by a decoder; correcting a motion vector of the current block based on the motion vector derivation mode; and determining a residual between a predicted value and an original value of the current block based on the corrected motion vector, thereby encoding the current block. According to the technical solutions, a more accurate predicted value is obtained by correcting the motion vector, and a smaller residual is generated.

Abstract: A method and device for generating a predicted value of image that are mostly used to generate a predicted value of a current block during image encoding or decoding. The method includes: determining a searching scope, wherein multiple motion vectors are included in the searching scope; performing up-sampling interpolations on first reference blocks, corresponding to the motion vector in the searching scope, in a reference image of the current block by using a first filter to obtain up-sampled first reference blocks; by using the up-sampled first reference blocks, obtaining at least one candidate motion vector corresponding to the current block; performing up-sampling interpolations on second reference blocks, corresponding to the at least one candidate motion vector, in the reference image of the current block by using a second filter to obtain up-sampled second reference blocks; combining the up-sampled second reference blocks to obtain a predicted value of the current block.