-
公开(公告)号：US20250071263A1
公开(公告)日：2025-02-27
申请号：US18944364
申请日：2024-11-12
Inventor： Sung Chang LIM , Jong Ho KIM , Hae Chul CHOI , Hui Yong KIM , Ha Hyun LEE , Jin Ho LEE , Se Yoon JEONG , Suk Hee CHO , Jin Soo CHOI , Jin Woo HONG , Jin Woong KIM
IPC: H04N19/105 , H04N19/11 , H04N19/157 , H04N19/176 , H04N19/46 , H04N19/503 , H04N19/593
Abstract: Provided are an imaging encoding method and device. When carrying out image encoding for a block within a slice, at least one block in a restored block of the slice is set as a reference block. When this is done, the encoding parameters of the reference block are distinguished, and the block to be encoded is encoded adaptively based on the encoding parameter.
-
公开(公告)号：US20250063181A1
公开(公告)日：2025-02-20
申请号：US18938538
申请日：2024-11-06
Inventor： Ha Hyun LEE , Jung Won KANG , Jin Ho LEE , Jin Soo CHOI , Jin Woong KIM
IPC: H04N19/187 , H04N19/105 , H04N19/176 , H04N19/31 , H04N19/33 , H04N19/463 , H04N19/52 , H04N19/70
Abstract: Disclosed are a method and an apparatus for image encoding/decoding that support a plurality of layers. The method for image decoding that supports a plurality of layers includes decoding information of a first layer which a picture of a second layer including a current decoding target block refers to; mapping the information of the first layer to a picture size of the second layer, configuring a reference picture list for the picture of the second layer by adding the mapped information of the first layer and generating prediction samples of the current decoding target block by predicting the current decoding target block of the second layer based on the reference picture list, and the information of the first layer includes at least one of a sample value and motion information of the first layer picture.
-
193.发明申请公开(公告)号：US20250054224A1
公开(公告)日：2025-02-13
申请号：US18798982
申请日：2024-08-09
Applicant: Electronics and Telecommunications Research Institute , UIF (University Industry Foundation), Yonsei University
Inventor： Ha Hyun LEE , Gun Bang , Soo Woong Kim , Ji Hoon Do , Seong Jun Bae , Jin Ho Lee , Jung Won Kang , Young Jung Uh , Seo Ha Kim , Jung Min Bae , Young Sik Yun
Abstract: The present disclosure relates to a method and apparatus for representing dynamic neural radiance fields from unsynchronized videos. A method of acquiring a video at an arbitrary viewpoint based on a dynamic neural radiance fields model according to an embodiment of the present disclosure may comprise: inputting one or more videos acquired from one or more views for one scene into the dynamic neural radiance fields model; inputting a time embedding for the one or more videos into the dynamic neural radiance fields model; and rendering the video at the arbitrary viewpoint based on color information and density information output by the dynamic neural radiance fields model. Herein, time synchronization related to the time embedding may be performed by applying an individual time offset learned for each view, for the one or more views.
-
公开(公告)号：US20250039399A1
公开(公告)日：2025-01-30
申请号：US18916567
申请日：2024-10-15
Inventor： Ha Hyun LEE , Jung Won KANG , Sung Chang LIM , Jin Ho LEE , Hui Yong KIM
IPC: H04N19/139 , H04N19/159 , H04N19/167 , H04N19/176 , H04N19/593
Abstract: An image decoding method is disclosed in the present specification. An image decoding method according to the present invention may include: determining a position of a co-located block of a current block within a co-located picture (co-located picture); determining a representative motion vector of the current block by using motion information at the position of the co-located block; and deriving motion information on a sub-block included in the current block by using the representative motion vector.
-
公开(公告)号：US20240406398A1
公开(公告)日：2024-12-05
申请号：US18799371
申请日：2024-08-09
Inventor： Sung Chang LIM , Jung Won KANG , Ha Hyun LEE , Jin Ho LEE , Hui Yong KIM , Dae Yeon KIM , Wook Je JEONG , Hyun Gyu KIM
IPC: H04N19/13 , H04N19/176 , H04N19/70
Abstract: An image decoding method is disclosed in the present specification. A method of decoding an image, the method may comprises determining whether to perform a context update for a first syntax element of a current block, updating, on the basis of the determination, a context for entropy decoding of the first syntax element and generating, on the basis of the updated context, a bin for the first syntax element, and wherein whether to perform the context update is determined on the basis of the number of pre-decoded predetermined syntax elements for the current block.
-
Patent Agency Ranking
公开(公告)号：US20240397090A1
公开(公告)日：2024-11-28
申请号：US18794394
申请日：2024-08-05
Inventor： Ha Hyun LEE , Jung Won KANG , Sung Chang LIM , Jin Ho LEE , Hui Yong KIM
IPC: H04N19/593 , H04N19/105 , H04N19/139 , H04N19/169 , H04N19/176 , H04N19/52
Abstract: Disclosed herein is an image encoding/decoding method. The image decoding method includes a step of comparing block vector information included in a history-based candidate list with a block vector of a neighboring block used as an intra block copy (IBC) block vector candidate for IBC prediction of a current block, and a step of adding the block vector information included in the history-based candidate list to an IBC block vector candidate list based on the comparing. The step of comparing is performed only with respect to a candidate lastly included in the history-based candidate list.
-
公开(公告)号：US20240364892A1
公开(公告)日：2024-10-31
申请号：US18767885
申请日：2024-07-09
Inventor： Ha Hyun LEE , Jung Won KANG , Sung Chang LIM , Jin Ho LEE , Hui Yong KIM
IPC: H04N19/132 , H04N19/105 , H04N19/119 , H04N19/137 , H04N19/176
CPC classification number: H04N19/132 , H04N19/105 , H04N19/119 , H04N19/137 , H04N19/176
Abstract: Disclosed herein are a video encoding/decoding method and apparatus. The video decoding method of the present disclosure includes: obtaining block partitioning information of a current block; based on the block partitioning information, partitioning the current block into a first sub-block and a second sub-block; deriving motion information of the first sub-block and motion information of the second sub-block respectively; based on the motion information of the first sub-block and the motion information of the second sub-block, generating a prediction sample of the first sub-block and a prediction sample of the second sub-block respectively; and through a weighted-sum of the prediction sample of the first sub-block and the prediction sample of the second sub-block, generating a prediction sample of the current block. Herein, the block partitioning information is index information indicating an index of a table including information indicating a plurality of predefined asymmetric partition shapes.
-
198.发明公开公开(公告)号：US20240357109A1
公开(公告)日：2024-10-24
申请号：US18762081
申请日：2024-07-02
Applicant: Electronics and Telecommunications Research Institute , INDUSTRY-UNIVERSITY COOPERATION FOUNDATION KOREA AEROSPACE UNIVERSITY , HANBAT NATIONAL UNIVERSITY INDUSTRY-ACADEMIC COOPERATION FOUNDATION
Inventor： Jin Ho LEE , Jung Won KANG , Hyun Suk KO , Sung Chang LIM , Ha Hyun LEE , Dong San JUN , Seung Hyun CHO , Hui Yong KIM , Hae Chul CHOI , Aram BACK , Jin Soo CHOI , Jae Gon KIM
IPC: H04N19/119 , H04N19/105 , H04N19/176 , H04N19/186 , H04N19/46
CPC classification number: H04N19/119 , H04N19/105 , H04N19/176 , H04N19/186 , H04N19/46
Abstract: An image encoding/decoding method and apparatus are provided. An image decoding method performed by an image decoding apparatus of the present invention may comprise decoding an indicator indicating whether or not partition information of a current block is derived from partition information of a corresponding block of the current block, obtaining the partition information of the current block based on the decoded indicator, and partitioning the current block based on the obtained partition information.
-
199.发明公开公开(公告)号：US20240340447A1
公开(公告)日：2024-10-10
申请号：US18747300
申请日：2024-06-18
Inventor： Ha Hyun LEE , Jung Won KANG , Sung Chang LIM , Jin Ho LEE , Hui Yong KIM
IPC: H04N19/593 , H04N19/105 , H04N19/176 , H04N19/513
CPC classification number: H04N19/593 , H04N19/105 , H04N19/176 , H04N19/513
Abstract: An image encoding/decoding method and apparatus are disclosed. The image decoding method includes acquiring prediction mode information of a current block from a bitstream, decoding an intra block copy prediction mode of the current block using the prediction mode information of the current block, and reconstructing the current block based on the intra block copy prediction mode. The intra block copy prediction mode is at least one of a block copy based SKIP mode, a block copy based MERGE mode or a block copy based AMVP mode.
-
200.发明公开公开(公告)号：US20240333969A1
公开(公告)日：2024-10-03
申请号：US18744023
申请日：2024-06-14
Applicant: Electronics and Telecommunications Research Institute , UNIVERSITY-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITY
Inventor： Jung Won KANG , Ha Hyun LEE , Sung Chang LIM , Jin Ho LEE , Hui Yong KIM , Gwang Hoon PARK , Tae Hyun KIM , Dae Young LEE
IPC: H04N19/56 , H04N19/105 , H04N19/139 , H04N19/176 , H04N19/96
CPC classification number: H04N19/56 , H04N19/105 , H04N19/139 , H04N19/176 , H04N19/96
Abstract: An image is decoded by deriving a first candidate list for the current block by using motion information of neighboring blocks of the current block; deriving a second candidate list for the current block by using previously reconstructed motion information; deriving a third candidate list by using the first candidate list and the second candidate list; and deriving a prediction block for the current block by using the third candidate list.
-
-
-
-
-
-
-
-
-
Search Results
356
records
(took 0.025 seconds)
