-
公开(公告)号:US20240179324A1
公开(公告)日:2024-05-30
申请号:US18426793
申请日:2024-01-30
发明人: Je Won Kang , Jung Kyung Lee , Seung Wook Park , Jin Heo
IPC分类号: H04N19/154 , H04N19/172 , H04N19/46
CPC分类号: H04N19/154 , H04N19/172 , H04N19/46
摘要: A method and an apparatus are disclosed for video coding using an improved in-loop filter. The video coding method and the apparatus generate a residual frame from a reconstructed frame using a deep learning model. The video coding method and the apparatus improve performance of an in-loop filter by approximating an original residual frame by applying the generated residual frame to a linear model.
-
公开(公告)号:US20230239462A1
公开(公告)日:2023-07-27
申请号:US18126623
申请日:2023-03-27
发明人: Je Won Kang , Na Young Kim , Jung Kyung Lee , Seung Wook Park , Wha Pyeong Lim
IPC分类号: H04N19/105 , H04N19/176 , H04N19/159 , H04N19/139 , H04N19/513 , H04N19/109
CPC分类号: H04N19/105 , H04N19/176 , H04N19/159 , H04N19/139 , H04N19/513 , H04N19/109
摘要: An inter prediction method allows a variable coefficient deep learning model to adaptively learn characteristics of a video; transmits a variable coefficient deep learning model parameter generated from the learning from an image encoding device to an image decoding device; and refers to a virtual reference frame generated by the variable coefficient deep learning model.
-
3.
公开(公告)号:US20240031580A1
公开(公告)日:2024-01-25
申请号:US18373113
申请日:2023-09-26
发明人: Je Won Kang , Na Young Kim , Jung Kyung Lee , Seung Wook Park
IPC分类号: H04N19/159 , G06T5/00 , G06T5/20 , G06V10/771 , H04N19/124 , H04N19/132
CPC分类号: H04N19/159 , G06T5/002 , G06T5/20 , G06V10/771 , H04N19/124 , H04N19/132
摘要: 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.
-
4.
公开(公告)号:US20230412798A1
公开(公告)日:2023-12-21
申请号:US18240888
申请日:2023-08-31
发明人: Je Won Kang , Jung Kyung Lee , Na Young Kim , Seung Wook Park
IPC分类号: H04N19/11 , H04N19/176 , H04N19/593 , H04N19/91 , H04N19/119 , H04N19/42 , H04N19/70
CPC分类号: H04N19/11 , H04N19/176 , H04N19/593 , H04N19/91 , H04N19/119 , H04N19/42 , H04N19/70
摘要: 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.
-
公开(公告)号:US20230269399A1
公开(公告)日:2023-08-24
申请号:US18020375
申请日:2021-08-24
发明人: Je Won Kang , Na Young Kim , Jung Kyung Lee , Seung Wook Park , Wha Pyeong Lim
IPC分类号: H04N19/86 , H04N19/172 , H04N19/105 , H04N19/82
CPC分类号: H04N19/86 , H04N19/172 , H04N19/105 , H04N19/82
摘要: A video encoding method and a video decoding method is provided for generating improved picture quality for a current frame and improving encoding efficiency. The video encoding method and the video decoding method further include an in-loop filter that detects a reference region from a current frame and a reference frame using a deep learning-based detection model and then combines the detected reference region with the current frame.
-
6.
公开(公告)号:US20240364904A1
公开(公告)日:2024-10-31
申请号:US18766140
申请日:2024-07-08
发明人: Je Won Kang , Jung Kyung Lee , Jin Heo , Seung Wook Park
IPC分类号: H04N19/192 , H04N19/105 , H04N19/159 , H04N19/176
CPC分类号: H04N19/192 , H04N19/105 , H04N19/159 , H04N19/176
摘要: A method is disclosed for modifying a decoder-side motion vector list in inter prediction. A video coding method and an apparatus use a template matching method or a bilateral matching (BM) method in a merge mode and an advanced motion vector prediction (AMVP) mode of inter prediction. The video coding method and the apparatus perform at least one of adding, pruning, or reordering candidates with respect to a motion vector list at the decoder side.
-
-
-
-
-