-
公开(公告)号：US11812013B2
公开(公告)日：2023-11-07
申请号：US17955278
申请日：2022-09-28
IPC: H04N19/105 , H04N19/70 , H04N19/174 , H04N19/169 , H04N19/46
CPC classification number: H04N19/105 , H04N19/174 , H04N19/188 , H04N19/70 , H04N19/46
Abstract: Disclosed herein are a method, an apparatus and a storage medium for performing encoding/decoding on an image using a subpicture. A picture may be partitioned into various units such as subpictures and slices, and various syntax elements and structures may be used to specify the units. In an embodiment, there is a method for configuring a reference picture list for motion compensation in the case where the location of a reference subpicture to be referred to for motion compensation is different from the location of a target subpicture. Further, in an embodiment, there is provided a method for providing the configuration of a reference picture list and an override on the number of activated reference indexes.
-
2.发明授权公开(公告)号：US11019355B2
公开(公告)日：2021-05-25
申请号：US16374601
申请日：2019-04-03
Inventor： Seung-Hyun Cho , Je-Won Kang , Na-Young Kim , Jung-Kyung Lee , Joo-Young Lee , Hyunsuk Ko , Youn-Hee Kim , Jong-Ho Kim , Jin-Wuk Seok , Dae-Yeol Lee , Woong Lim , Se-Yoon Jeong , Hui-Yong Kim , Jin-Soo Choi
IPC: H04N19/513 , G06N20/00 , H04N19/132 , H04N19/105
Abstract: An inter-prediction method and apparatus uses a reference frame generated based on deep learning. In the inter-prediction method and apparatus, a reference frame is selected, and a virtual reference frame is generated based on the selected reference frame. A reference picture list is configured to include the generated virtual reference frame, and inter prediction for a target block is performed based on the virtual reference frame. The virtual reference frame may be generated based on a deep-learning network architecture, and may be generated based on video interpolation and/or video extrapolation that use the selected reference frame.
-
3.发明授权公开(公告)号：US11985325B2
公开(公告)日：2024-05-14
申请号：US17629281
申请日：2020-07-23
Applicant: Electronics and Telecommunications Research Institute , INDUSTRY-ACADEMIA COOPERATION GROUP OF SEJONG UNIVERSITY
Inventor： Woong Lim , Jin-Young Lee , Gun Bang , Hui-Yong Kim
IPC: H04N19/137 , H04N19/159 , H04N19/176 , H04N19/182
CPC classification number: H04N19/137 , H04N19/159 , H04N19/176 , H04N19/182
Abstract: Disclosed herein are a method, an apparatus, and a storage medium for image encoding/decoding using geometric partitioning. A target block may be geometrically partitioned, and multiple partitioned regions may be generated from geometric partitioning. Each partitioned region may have a non-square and a non-rectangular shape. Different prediction schemes may be applied to different partitioned regions. The different prediction schemes for multiple partitioned regions may be signaled as explicit information, and may be derived using information about a coding parameter for the target block or the like.
-
公开(公告)号：US11838506B2
公开(公告)日：2023-12-05
申请号：US17978732
申请日：2022-11-01
IPC: H04N19/119 , H04N19/184 , H04N19/174 , H04N19/70 , H04N19/172 , H04N19/176
CPC classification number: H04N19/119 , H04N19/172 , H04N19/174 , H04N19/184 , H04N19/70 , H04N19/176
Abstract: Disclosed herein are a method, an apparatus and a storage medium for image encoding/decoding. For efficient image compression, efficient syntax is required. Pieces of information required for image decoding may be structurally or semantically associated with each other. Based on this association, whether signaling of one piece of information is to be performed may be determined based on another piece of information. Further, based on this association, the signaling order or priority of multiple pieces of information may be determined. Depending on this determination, based on the number of subpictures present in a picture in high-level syntax, the number of slices present in the picture may be selectively signaled.
-
公开(公告)号：US11778169B2
公开(公告)日：2023-10-03
申请号：US17134092
申请日：2020-12-24
IPC: H04N19/176 , H04N19/105 , H04N19/46 , H04N19/119
CPC classification number: H04N19/105 , H04N19/119 , H04N19/176 , H04N19/46
Abstract: Disclosed herein are a method, apparatus and storage medium for image encoding/decoding using a reference picture. A picture is divided into multiple sub-pictures. The sub-pictures of the picture share a reference picture list. In order to determine sub-pictures that share the reference picture list, specific information is signaled from an encoding apparatus to a decoding apparatus. For each sub-picture that does not share a reference picture list for an additional sub-picture, a reference picture list for the sub-picture is separately configured.
-
Patent Agency Ranking
公开(公告)号：US12231634B2
公开(公告)日：2025-02-18
申请号：US17621151
申请日：2020-06-22
Applicant: Electronics and Telecommunications Research Institute , INDUSTRY-ACADEMIA COOPERATION GROUP OF SEJONG UNIVERSITY
Inventor： Gun Bang , Jin-Young Lee , Woong Lim , Hui-Yong Kim
IPC: H04N19/119 , H04N19/117 , H04N19/172 , H04N19/86 , H04N19/96
Abstract: Disclosed herein are a method and apparatus for image encoding and image decoding using region segmentation. A picture is divided into multiple sub-pictures, and encoding and/or decoding are performed on the multiple sub-pictures resulting from division. Encoding operations and/or decoding operations on the sub-pictures may be independently performed. Merging and filtering are applied to reconstructed sub-pictures generated by decoding, and a reconstructed picture is generated after processing of merging and filtering.
-
7.发明授权公开(公告)号：US12034915B2
公开(公告)日：2024-07-09
申请号：US17621174
申请日：2020-06-22
Applicant: Electronics and Telecommunications Research Institute , UNIVERSITY-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITY
Inventor： Gun Bang , Gwang-Hoon Park , Woong Lim , Hui-Yong Kim , Woo-Woen Gwun , Tae-Hyun Kim , Dae-Young Lee , Won-Jun Lee
IPC: H04N19/105 , H04N19/119 , H04N19/159 , H04N19/176
CPC classification number: H04N19/105 , H04N19/119 , H04N19/159 , H04N19/176
Abstract: Disclosed herein are a method and apparatus for image encoding and decoding using prediction based on a block shape. Whether a prediction mode is available for a target block is determined. The determination is performed based on the shape of the target block. When the prediction mode is determined to be unavailable for the target block, signaling related to the prediction mode may be omitted, and determination of an additional prediction mode is performed. When the prediction mode is determined to be available for the target block, information indicating whether the prediction mode is to be used for the target block is signaled.
-
公开(公告)号：US11663476B2
公开(公告)日：2023-05-30
申请号：US16772557
申请日：2018-12-13
Inventor： Seung-Hyun Cho , Youn-Hee Kim , Jin-Wuk Seok , Joo-Young Lee , Woong Lim , Jong-Ho Kim , Dae-Yeol Lee , Se-Yoon Jeong , Hui-Yong Kim , Jin-Soo Choi , Je-Won Kang
IPC: G06V10/75 , G06N3/08 , G06N3/04 , G06V10/82 , G06F18/214
CPC classification number: G06V10/751 , G06F18/214 , G06N3/04 , G06N3/08 , G06V10/82
Abstract: Disclosed herein are a method and apparatus for compressing learning parameters for training of a deep-learning model and transmitting the compressed parameters in a distributed processing environment. Multiple electronic devices in the distributed processing system perform training of a neural network. By performing training, parameters are updated. The electronic device may share the updated parameter thereof with additional electronic devices. In order to efficiently share the parameter, the residual of the parameter is provided to the additional electronic devices. When the residual of the parameter is provided, the additional electronic devices update the parameter using the residual of the parameter.
-
公开(公告)号：US11412225B2
公开(公告)日：2022-08-09
申请号：US16585658
申请日：2019-09-27
Inventor： Joo-Young Lee , Seung-Hyun Cho , Seung-Kwon Beack , Hyunsuk Ko , Youn-Hee Kim , Jong-Ho Kim , Jin-Wuk Seok , Woong Lim , Se-Yoon Jeong , Hui-Yong Kim , Jin-Soo Choi
IPC: H04N19/13 , H04N19/184 , H04N19/196 , H04N19/149
Abstract: Disclosed herein is a context-adaptive entropy model for end-to-end optimized image compression. The entropy model exploits two types of contexts. The two types of contexts are a bit-consuming context and a bit-free context, respectively, and these contexts are classified depending on the corresponding context requires the allocation of additional bits. Based on these contexts, the entropy model may more accurately estimate the distribution of each latent representation using a more generalized form of entropy models, thus improving compression performance.
-
10.发明公开公开(公告)号：US20240314297A1
公开(公告)日：2024-09-19
申请号：US18676050
申请日：2024-05-28
Applicant: Electronics And Telecommunications Research Institute , University-Industry Cooperation Group Of Kyung Hee University
Inventor： Gun BANG , Gwang-Hoon Park , Woong Lim , Hui-Yong KIm , Woo-Woen Gwun , Tae-Hyun Kim , Dae-Young Lee , Won-Jun Lee
IPC: H04N19/105 , H04N19/119 , H04N19/159 , H04N19/176
CPC classification number: H04N19/105 , H04N19/119 , H04N19/159 , H04N19/176
Abstract: Disclosed herein are a method and apparatus for image encoding and decoding using prediction based on a block shape. Whether a prediction mode is available for a target block is determined. The determination is performed based on the shape of the target block. When the prediction mode is determined to be unavailable for the target block, signaling related to the prediction mode may be omitted, and determination of an additional prediction mode is performed. When the prediction mode is determined to be available for the target block, information indicating whether the prediction mode is to be used for the target block is signaled.
-
-
-
-
-
-
-
-
-
Search Results
22
records
(took 0.019 seconds)
