Lin Sixin

Bio: Lin Sixin is an academic researcher from Huawei. The author has contributed to research in topics: Motion vector & Decoding methods. The author has an hindex of 6, co-authored 24 publications receiving 150 citations. Previous affiliations of Lin Sixin include MediaTech Institute.

An Efficient Four-Parameter Affine Motion Model for Video Coding

Abstract: In this paper, we study a simplified affine motion model-based coding framework to overcome the limitation of a translational motion model and maintain low-computational complexity. The proposed framework mainly has three key contributions. First, we propose to reduce the number of affine motion parameters from 6 to 4. The proposed four-parameter affine motion model can not only handle most of the complex motions in natural videos, but also save the bits for two parameters. Second, to efficiently encode the affine motion parameters, we propose two motion prediction modes, i.e., an advanced affine motion vector prediction scheme combined with a gradient-based fast affine motion estimation algorithm and an affine model merge scheme, where the latter attempts to reuse the affine motion parameters (instead of the motion vectors) of neighboring blocks. Third, we propose two fast affine motion compensation algorithms. One is the one-step sub-pixel interpolation that reduces the computations of each interpolation. The other is the interpolation-precision-based adaptive block size motion compensation that performs motion compensation at the block level rather than the pixel level to reduce the number of interpolation. Our proposed techniques have been implemented based on the state-of-the-art high-efficiency video coding standard, and the experimental results show that the proposed techniques altogether achieve, on average, 11.1% and 19.3% bits saving for random access and low-delay configurations, respectively, on typical video sequences that have rich rotation or zooming motions. Meanwhile, the computational complexity increases of both the encoder and the decoder are within an acceptable range.

Image prediction method and related device

Abstract: To provide an image prediction method and a related device.SOLUTION: An image prediction method and a related device are disclosed. The image prediction method comprises: determining K1 pixel samples in an image block x, and determining a candidate movement information unit set corresponding to each pixel sample in the K1 pixel samples, the candidate movement information unit set corresponding to each pixel sample comprising at least one candidate movement information unit; determining a merged movement information unit set i comprising the K1 movement information units, each movement information unit in the merged movement information unit set i being selected from at least a part of movement information units in the candidate movement information unit set corresponding to different pixel samples in the K1 pixel samples; and utilizing a non-translational motion model and the merged movement information unit set i to predict a pixel value of the image block x. The present invention helps to reduce complexity on calculation of image prediction performed on the basis of the non-translational motion model.SELECTED DRAWING: Figure 1-c

Image forecasting method and related device

Abstract: The invention discloses an image forecasting method and a related device. The image forecasting method includes: confirming K1 pixel samples in an image block x, and confirming a candidate movement information unit set corresponding to each of the K1 pixel samples; enabling each candidate movement information unit set corresponding to each pixel sample to include at least one candidate movement information unit; confirming a merger movement information unit set i which includes K1 movement information units; using a non-translation movement model and the merger movement information unit set i to forecast pixel values of the image block x, wherein all the movement information units in the merger movement information unit set i are respectively selected from at least a part of the movement information units in the candidate movement information unit sets corresponding to the different pixel samples in the K1 pixel samples. The image forecasting method and the related device facilitate reduction of computation complexity of image forecasting based on the non-translation movement model.

Method for coding and decoding video image, coding equipment and decoding equipment

Abstract: An embodiment of the invention relates to a method for coding and decoding a video image, coding equipment and decoding equipment. The method comprises steps as follows: determining a motion vector group of a current coding block; determining a prediction value of a first component set of a motion model initial vector of the current coding block according to the motion vector group; determining a to-be-transmitted value of the first component set according to the prediction value of the first component set; coding the to-be-transmitted value of the first component set and sending the coded to-be-transmitted value to a decoding end. According to the method for coding and decoding the video image, the coding equipment and the decoding equipment, the motion model initial vector of the current coding block is determined according to the motion vector group, the to-be-transmitted value of a motion model is determined according to the motion model initial vector and is coded and transmitted, so that the decoding end can decode according to the to-be-transmitted value of the motion model, and the volume of data transmitted during coding and decoding and occupied bit number can be reduced.

An Efficient Four-Parameter Affine Motion Model for Video Coding

Abstract: In this paper, we study a simplified affine motion model based coding framework to overcome the limitation of translational motion model and maintain low computational complexity. The proposed framework mainly has three key contributions. First, we propose to reduce the number of affine motion parameters from 6 to 4. The proposed four-parameter affine motion model can not only handle most of the complex motions in natural videos but also save the bits for two parameters. Second, to efficiently encode the affine motion parameters, we propose two motion prediction modes, i.e., advanced affine motion vector prediction combined with a gradient-based fast affine motion estimation algorithm and affine model merge, where the latter attempts to reuse the affine motion parameters (instead of the motion vectors) of neighboring blocks. Third, we propose two fast affine motion compensation algorithms. One is the one-step sub-pixel interpolation, which reduces the computations of each interpolation. The other is the interpolation-precision-based adaptive block size motion compensation, which performs motion compensation at the block level rather than the pixel level to reduce the interpolation times. Our proposed techniques have been implemented based on the state-of-the-art high efficiency video coding standard, and the experimental results show that the proposed techniques altogether achieve on average 11.1% and 19.3% bits saving for random access and low delay configurations, respectively, on typical video sequences that have rich rotation or zooming motions. Meanwhile, the computational complexity increases of both encoder and decoder are within an acceptable range.

Method and apparatus of video coding with affine motion compensation

Abstract: An encoding or decoding method with affine motion compensation includes receiving input data associated with a current block in a current picture, and deriving a first affine candidate for the current block including three affine motion vectors for predicting motion vectors at control points of the current block if the current block is coded or to be coded in affine Merge mode. The affine motion vectors are derived from three different neighboring coded blocks of the current block. An affine motion model is derived according to the affine motion vectors if the first affine candidate is selected. Moreover, the method includes encoding or decoding the current block by locating a reference block in a reference picture according to the affine motion model. The current block is restricted to be coded in uni-directional prediction if the current block is coded or to be coded in affine Inter mode.

Affine motion prediction for video coding

Abstract: An example method includes obtaining, for a current block of video data, values of motion vectors (MVs) of an affine motion model of a neighboring block of video data; deriving, from the values of the MVs of the affine motion model of the neighboring block, values of predictors for MVs of an affine motion model of the current block; decoding, from a video bitstream, a representation of differences between the values of the MVs of the affine motion model for the current block and the values of the predictors; determining the values of the MVs of the affine motion model for the current block from the values of the predictors and the decoded differences; determining, based on the determined values of the MVs of the affine motion model for the current block, a predictor block of video data; and reconstructing the current block based on the predictor block.

Motion vector prediction for affine motion models in video coding

Abstract: A video decoder selects a source affine block. The source affine block is an affine-coded block that spatially neighbors a current block. Additionally, the video decoder extrapolates motion vectors of control points of the source affine block to determine motion vector predictors for control points of the current block. The video decoder inserts, into an affine motion vector predictor (MVP) set candidate list, an affine MVP set that includes the motion vector predictors for the control points of the current block. The video decoder also determines, based on an index signaled in a bitstream, a selected affine MVP set in the affine MVP set candidate list. The video decoder obtains, from the bitstream, motion vector differences (MVDs) that indicate differences between motion vectors of the control points of the current block and motion vector predictors in the selected affine MVP set.

Inter-prediction method and apparatus in video coding system

Abstract: An inter-prediction method performed by a decoding apparatus according to the present invention comprises the steps of: deriving a motion information candidate list of a current block on the basis of neighboring blocks of the current block; selecting a specific candidate on the basis of the comparison of the candidates in the motion information candidate list; deriving a motion vector of the current block on the basis of the specific candidate; and generating a prediction sample of the current block on the basis of the motion vector of the current block. The present invention is capable of reducing the data amount of the prediction mode information indicating an inter-prediction mode, and reducing the process of searching for a motion vector of the current block by selecting motion vector candidates of the current block, thereby improving coding efficiency.

Enhanced Bi-Prediction With Convolutional Neural Network for High-Efficiency Video Coding

Abstract: In this paper, we propose an enhanced bi-prediction scheme based on the convolutional neural network (CNN) to improve the rate-distortion performance in video compression. In contrast to the traditional bi-prediction strategy which computes the linear superposition as the predictive signals with pixel-to-pixel correspondence, the proposed scheme employs CNN to directly infer the predictive signals in a data-driven manner. As such, the predicted blocks are fused in a nonlinear fashion to improve the coding performance. Moreover, the patch-to-patch inference strategy with CNN also improves the prediction accuracy since the patch-level information for the prediction of each individual pixel can be exploited. The proposed enhanced bi-prediction scheme is further incorporated into the high-efficiency video coding standard, and the experimental results exhibit a significant performance improvement under different coding configurations.