Hyundai Motor Company

Kia Corporation

Kwangwoon University Industry-academic Collaboration Foundation

Ewha University-Industry Collaboration Foundation

Sungkyunkwan University

Kia Motors Corporation

Digitalinsights Inc.

Korea University Research and Business Foundation

Hyundai Autoever Corporation

Seung Wook Park

Jin Seong Heo

Jong Ho Lee

Dong Gyu Sim

In Yong Jung

Wha Pyeong Lim

Sang Min Lee

Sea Nae Park

Je Won Kang

Jong Seok Lee

Byeung Woo Jeon

Yong Jo Ahn

Na Young Kim

Jin Ho Park

Min Byeong Lee

Chang Ho Kim

Sang Hyo Park

Yu Jin Lee

Gene Back Hahn

Yoon Soo Kim

Dae Joong Yoon

Woo Sung Kim

Jae Seob Choi

Kyoung Jun Lee

Ho Choul Jung

Eu Gene Chang

Joo Hyung Byeon

Dong Hyun Sung

Joo Woong Yang

Kang Hoon Lee

Tae Young Lee

Wan Jae Lee

Jun Taek Park

Jee Yoon Park

A Ram Cho

Eung Seo Kim

Suk Ki Min

Jae Hwan Jeon

Kyung Soo Ha

Jong Gyu Kim

Yong Seok Kwon

Han Sol Choi

Bum Yoon Kim

Jung Kyung Lee

Young Bin Min

Huy Kang Kim

Jung Hei Ryu

Seong Hoon Jeong

Tae Guen Kim

Ju Yeon Lim

Jeong Gi Gong

Myung Oh Hong

Hwapyeong Lim

A block splitting structure is disclosed for efficient prediction and transform, and a method and an apparatus are disclosed for video encoding and decoding using the block Splitting structure. In particular, the method and apparatus are capable of splitting a video data block into two regions or blocks including an L-shaped block and a rectangular block and thus efficiently perform prediction on each block.

Block splitting structure for efficient prediction and transform, and method and apparatus for video encoding and decoding using the same

A video decoding method, a video encoding method, and a method of transmitting a bitstream containing encoded video data are disclosed. The methods include determining first and second reference pictures and first and second motion vectors for bi-prediction by decoding a bitstream; generating a first reference block from the first reference picture referenced by the first motion vector and generating a second reference block from the second reference picture referenced by the second motion vector; and generating a prediction block of the target block using the first and second reference blocks. The methods also include generating a residual block of the target block and reconstructing the target block based on the prediction block of the target block and the residual block of the target block.

Method and apparatus for encoding and decoding video using inter-prediction

A video coding method and an apparatus for refining predicted signals in intra prediction are disclosed. The video coding method and apparatus generate refined prediction signals approximating original video signals from predicted signals of intra prediction using a variable and fixed coefficient-based deep learning model to reduce the amount of data for residual signals, which are to be encoded.

Method and apparatus for video coding for improving predicted signals of intra prediction

A video encoding method, video decoding method, and an apparatus are disclosed. The methods and the apparatus are configured to: determine first and second reference pictures and first and second motion vectors for bi-prediction by decoding a bitstream; generate a first reference block from the first reference picture referenced by the first motion vector and generate a second reference block from the second reference picture referenced by the second motion vector; and generate a prediction block of the target block using the first and second reference blocks. The predictor includes a first coding tool configured to generate the prediction block of the target block by performing a bi-directional optical flow process using the first and second reference blocks.

A method and an apparatus are disclosed for video coding using a block vector with an adaptive spatial resolution. The video coding method and the apparatus signal the spatial resolution of a block vector (BV) indicating the position of a reference block adaptively or signal the sign of a block vector difference adaptively in order to improve coding efficiency when intra block copy (IBC) is applied to a current block.

Method and apparatus for video coding using block vector with adaptive spatial resolution

A method and an apparatus for video coding using a deep learning-based in-loop filter for inter-prediction are disclosed. The video coding method and the apparatus utilize a deep learning-based in-loop filter for inter-prediction of a predictive frame (P-frame) and a bipredictive frame (B-frame) in order to mitigate various levels of image distortion according to a QP (quantization parameter) value present in the P-frame and the B-frame.

Method and apparatus for video coding using deep learning based in-loop filter for inter prediction

A method and an apparatus are disclosed for video coding using a mapping of residual signals. The video coding method and the apparatus enable the video encoding device to transmit mapping data related to a mapping of the residual signals of the current block to improve video coding efficiency and enhance video quality. The video coding method and the apparatus enable the video decoding device to decode the residual signals based on the mapping data.

Method and apparatus for video coding using mapping of residual signals

A video coding method and an apparatus using a spiral scan order are disclosed. The video coding method and the apparatus perform encode/decode target blocks in a spiral scan order for allowing the blocks located centrally of a video frame to make use of more previously reconstructed neighboring blocks.

Method and apparatus for video coding using spiral scan order

A method and an apparatus for video coding using a video-characteristic-based context model are disclosed. The video coding method and the video coding apparatus determine a context model optimized for an individual video on the basis of information in which various characteristics of the individual video are reflected in entropy encoding and decoding using context adaptive binary arithmetic coding (CABAC).

Method and apparatus for video coding using versatile information-based context model

A method and an apparatus for video coding based on mapping are disclosed. The video coding method and the apparatus generate a prediction block of a current block with reference to a mapped image when a video encoding apparatus transmits mapping data related to a mapping of the image and a video decoding apparatus decodes the current block based on the mapping data.

Method and apparatus for video coding based on mapping

A video decoding apparatus, a video encoding apparatus, and an apparatus for transmitting a bitstream containing encoded video data are disclosed. The apparatuses are configured to: determine first and second reference pictures and first and second motion vectors for bi-prediction by decoding a bitstream; generate a first reference block from the first reference picture referenced by the first motion vector and generate a second reference block from the second reference picture referenced by the second motion vector; generate a prediction block of the target block using the first and second reference blocks; generate a residual block based on the prediction block of the target block; and encode the residual block. The apparatuses are configured to generate the prediction block of the target block by performing a bi-directional optical flow process using the first and second reference blocks.

A video decoding method, a video encoding method, and a method for transmitting a bitstream containing encoded video data are disclosed. The methods are configured to: determine first and second reference pictures and first and second motion vectors for bi-prediction by decoding a bitstream; generate a first reference block from the first reference picture referenced by the first motion vector and generate a second reference block from the second reference picture referenced by the second motion vector; and generate a prediction block of the target block using the first and second reference blocks. The methods are also configured to generate the prediction block for a subblock of size 4×4 split from the target block by performing a bi-directional optical flow process using the first and second reference blocks.

A video encoding or decoding apparatus and method perform existing inter prediction on a current block to generate a motion vector and predicted samples. The video encoding or decoding apparatus and method generate enhanced predicted samples for the current block using a deep learning-based video prediction network (VPN) on the basis of the motion vector, the reference samples, the predicted samples, and the like to improve encoding efficiency.

Video encoding and decoding using deep learning based inter prediction

A video decoding method for decoding a target block using intra prediction comprises decoding, from a bitstream, boundary line information specifying at least one boundary line for partitioning the target block. The boundary line information allows partitioning the target block into a plurality of non-rectangular blocks. The method further comprises determining intra prediction modes for the non-rectangular blocks based on the boundary line information; generating a prediction block of the target block by performing intra prediction on each of the non-rectangular blocks using the intra prediction modes; reconstructing a residual block of the target block from the bitstream; and reconstructing the target block by adding the prediction block and the residual block.

Video encoding and decoding using arbitrary block partitioning

A method and a device for inversely transforming transform coefficients of a current block are disclosed. A method for predicting a current block according to a first mode, includes the steps of: on the basis of a partition mode syntax element, partitioning the current block into non-rectangular blocks; determining an intra-predicted intra block and an inter-predicted inter block among the non-rectangular blocks; and deriving prediction samples of a first area including the inter block on the basis of motion information, and deriving prediction samples of a second area including the intra block on the basis of an intra prediction mode.

Decoding device and method for predicting block partitioned into random shape

Growing community of inventors

Gyeonggi-do, South Korea

Seung Wook Park