Abstract: A prediction mode determining method includes determining a split mode for a current picture block, determining whether a first picture subblock that meets a preset condition is obtained after the current picture block is split in the split mode, splitting the current picture block in the split mode to obtain a plurality of picture subblocks in response to determining that the first picture subblock is obtained after the current picture block is split, and determining that a same prediction mode is used for the plurality of picture subblocks. The plurality of picture subblocks comprise the first picture subblock. The prediction mode for the plurality of picture subblocks is an intra prediction mode or an inter prediction mode.

Abstract: A method of determining one or more candidate prediction modes, the method comprises deriving, by a processor, a first indicator by parsing a bitstream, wherein the first indicator specifies whether any affine model is a candidate motion model for an image block in a preset area; determining, by the processor, that the first indicator is set to 1; deriving, by the processor and based on the determination that the first indicator is set to 1, a second indicator by parsing the bitstream, wherein the second indicator specifies whether a 6-parameter affine model is a candidate motion model for the image block; and determining, by the processor, one or more candidate prediction modes for the image block based on the first indicator and the second indicator.

Abstract: A motion information candidate list construction method includes: performing a first processing process on all neighboring image blocks of a current image block until a quantity of candidate motion information sets in a candidate motion information list is equal to a first preset value or all the neighboring image blocks are traversed; then traversing at least two extra to be selected motion information sets, and storing, in the candidate motion information list, an extra to be selected motion information set that satisfies a preset condition, until the quantity of candidate motion information sets in the candidate motion information list is equal to a preset quantity value or the extra to be selected motion information sets are traversed extra to be selected motion.

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: A picture encoding/decoding method and a related apparatus are provided. The picture decoding method includes obtaining a current picture from a video, the current picture being segmented using random access points into multiple video segments supporting a random access function; selecting, from a knowledge base, K reference pictures of the current picture, wherein at least one reference picture in the knowledge base does not belong to a random access segment in which the current picture is located, the random access segment comprising a picture sequence arranged in a decoding order from a closest random access point before the current picture to a closest random access point after the current picture; and decoding the current picture according to the K reference pictures.

Abstract: This disclosure discloses a method for obtaining a candidate motion vector list, an apparatus, an encoder, and a decoder. The method for obtaining a candidate motion vector list comprises: when a first candidate picture block is encoded/decoded and an inter prediction mode is used, determining whether a reference picture of the first candidate picture block is the same as a reference picture of a current block; and constructing a candidate motion vector list of the current block based on a determining result; when the reference picture of the first candidate picture block is different from the reference picture of the current block, the MV of the first candidate picture block is not used to construct the list. Implementing this disclosure can reduce complexity of a motion information derivation process, and improve coding efficiency.

Abstract: An image processing method includes: obtains a to-be-processed image, performs feature extraction on the to-be-processed image by using a feature extraction layer included in a convolutional neural network, to obtain a first feature map, and compresses the first feature map by using a feature compression layer included in the convolutional neural network, to obtain a second feature map, where a channel quantity of the second feature map is less than a channel quantity of the first feature map; and the sending node sends the second feature map to a receiving node. The first feature map of the to-be-processed image is obtained through extraction by using the feature extraction layer, and the first feature map is compressed by using the feature compression layer, to obtain the second feature map.

Abstract: A video coding mechanism is disclosed. The mechanism includes receiving a video signal partitioned into a chroma block and a first neighboring luma block. The mechanism also includes encoding prediction information for chroma samples of the chroma block into a bitstream. The prediction information for the chroma samples is determined via intra-prediction based on down-sampled neighboring luma samples. The down-sampled neighboring luma samples are generated from a single row of luma samples from the first neighboring luma block. A bitstream including the prediction information for the chroma samples is transmitted to support decoding and display of the chroma samples.

Abstract: A high dynamic range image processing method and apparatus, to improve a display effect of a high dynamic range image. The method includes: obtaining image information of a to-be-processed high dynamic range (HDR) image, the image information includes a maximum RGB component value of a first pixel corresponding to a first percentage and a maximum RGB component value of a second pixel corresponding to a second percentage; determining a maximum reference value of the HDR image; determining a maximum luminance modification value of the HDR image based on the maximum reference value and a plurality of preset hierarchy intervals, where the maximum luminance modification value is used to modify a largest value in maximum RGB component values of the plurality of pixels included in the HDR image; and adjusting a dynamic range of the HDR image based on the maximum luminance modification value.

Abstract: An intra-frame decoding method includes obtaining, from a video code stream, prediction mode information of a first signal component of a current block, determining a prediction mode of the first signal component of the current block from a prediction mode set of the first signal component of the current block according to the prediction mode information of the first signal component of the current block, where the prediction mode set of the first signal component of the current block includes at least one of a linear model above (LMA) mode and a linear model left (LML) mode; obtaining a predicted value of a first signal component sampling point of the current block; and obtaining a reconstructed value of the first signal component sampling point of the current block according to the predicted value of the first signal component sampling point of the current block.

Abstract: This application relates to the field of artificial intelligence (AI)-based video or picture compression technologies. The decoding method includes: performing probability estimation on input data by using a neural network, to obtain probability distribution of residual values of a plurality of samples and included in a residual of a current picture, where the input data includes at least a residual of a reference picture, and the reference picture is a decoded picture obtained before the current picture is decoded; performing arithmetic entropy decoding on a bitstream based on the probability distribution of the residual values of the plurality of samples and included in the residual of the current picture, to obtain first entropy decoding data, where the first entropy decoding data represents the residual of the current picture; and obtaining a reconstructed sample value of the current picture based on the residual of the current picture.

Abstract: This application provides a video picture prediction method and apparatus, to resolve a problem in a conventional technology that a length of a coded video sequence is increased. The first type of identifier may be added to a bitstream. The first type of identifier is used to indicate whether an affine motion model-based inter prediction mode is enabled for a video picture. For a video picture or a picture block included in the slice for which the affine motion model does not need to be used, a parameter, related to the affine motion model, of the picture block may not need to be transmitted. On a decoder side, during decoding of the picture block, the parameter related to the affine motion model does not need to be parsed. This can reduce load of a decoder, increase a processing speed, and decrease a processing time.

Abstract: This application provides a scalable encoding and decoding method and apparatus. The encoding method includes: applying a control signal of a first signal component of a video signal to a first feature map of the first signal component, to obtain a second feature map of the first signal component, where the control signal of the first signal component is obtained through learning; applying a control signal of a second signal component of the video signal to a first feature map of the second signal component, to obtain a second feature map of the second signal component, where the control signal of the second signal component is obtained through learning; and obtaining a bitstream of the video signal based on the second feature map of the first signal component and the second feature map of the second signal component.

Abstract: Embodiments of this application disclose a bi-directional inter prediction method and apparatus. The method includes: determining a reference picture index i1 of a first reference picture list as a first reference picture index; determining a reference picture index i2 of a second reference picture list as a second reference picture index; and predicting the current block based on the first reference picture index and the second reference picture index. A POC corresponding to i1 is a POC, closest to a POC of a current picture, in all POCs that are in the first reference picture list and that are less than the POC of the current picture, a POC corresponding to i2 is a POC, closest to the POC of the current picture, in all POCs that are in the second reference picture list and that are greater than the POC of the current picture. Coding efficiency can be improved.

Abstract: An image prediction method, apparatus, and system, a device, and a storage medium are provided. The method includes: (401) obtaining a split mode of a current node, where the current node is an image block in a coding tree unit in a current image; (402) determining, based on the split mode of the current node and a size of the current node, whether the current node satisfies a first condition; and (403) when it is determined that the current node satisfies the first condition, performing intra prediction on all coding blocks belonging to the current node, to obtain predictors of all the coding blocks belonging to the current node.

Abstract: Embodiments of this application relate to the field of video picture coding technologies, and disclose a bidirectional inter prediction method and apparatus, to improve coding efficiency. The method includes: obtaining a first motion vector difference of a current picture block; determining a second motion vector difference of the current picture block based on the first motion vector difference, where the first motion vector difference belongs to motion information of the current picture block in a first direction, and the second motion vector difference belongs to motion information of the current picture block in a second direction; and determining prediction samples of the current picture block based on the obtained first motion vector difference and the determined second motion vector difference.

Abstract: This application discloses an encoding method, a decoding method, and a device. The encoding method includes: determining an index of an intra prediction mode syntax element value set of a current picture block; performing, by using a neural network, probability estimation on input data that represents a feature of the current picture block, to obtain probability distribution of a plurality of candidate intra prediction mode syntax element value sets, where the probability distribution represents respective probability values of the plurality of candidate intra prediction mode syntax element value sets; and performing entropy encoding on a probability value related to the index of the intra prediction mode syntax element value set of the current picture block based on the probability distribution of the plurality of candidate intra prediction mode syntax element value sets, to obtain a bitstream.

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 motion vector prediction method includes parsing a bitstream to obtain an index value of a candidate motion vector list and constructing the candidate motion vector list that includes. candidate motion vectors of K control points of a current block. The candidate motion vectors of K control points are obtained based on a 2N-parameter affine transform model used for a neighboring block of the current block, where N and K are integers greater than or equal to 2 and less than or equal to 4 with N not being equal to K. The method further includes determining, in the candidate motion vector list, target candidate motion vectors of the K control points based on the index value and obtaining a predicted motion vector of each subblock of the current block based on the target candidate motion vectors of the K control points.

Abstract: A motion vector prediction method includes parsing a bitstream to obtain an index value of a candidate motion vector list and constructing the candidate motion vector list that includes. candidate motion vectors of K control points of a current block. The candidate motion vectors of K control points are obtained based on a 2N-parameter affine transform model used for a neighboring block of the current block, where N and K are integers greater than or equal to 2 and less than or equal to 4 with N not being equal to K. The method further includes determining, in the candidate motion vector list, target candidate motion vectors of the K control points based on the index value and obtaining a predicted motion vector of each subblock of the current block based on the target candidate motion vectors of the K control points.