-
公开(公告)号:EP4198878A1
公开(公告)日:2023-06-21
申请号:EP22189533.7
申请日:2022-08-09
发明人: CHOI, Jae Seok , CHO, Minsu , KIM, Sanghyun , LEE, Jongmin , KWON, Kinam , SEO, Geonseok , LEE, Hyong Euk
摘要: A method and apparatus for image restoration based on burst images. The method includes generating a plurality of feature representations corresponding to individual images of a burst image set by encoding the individual images (810), determining a reference feature representation from among the plurality of feature representations (820), determining a first comparison pair including the reference feature representation and a first feature representation of the plurality of feature representations (830), generating a first motion-embedding feature representation of the first comparison pair based on a similarity score map of the reference feature representation and the first feature representation (840), generating a fusion result by fusing a plurality of motion-embedding feature representations including the first motion-embedding feature representation (850), and generating at least one restored image by decoding the fusion result (860).
-
公开(公告)号:EP4105876A1
公开(公告)日:2022-12-21
申请号:EP21218448.5
申请日:2021-12-31
发明人: CHOI, Jae Seok , LEE, Hyong Euk , SEO, Geonseok , YOO, Byung In
IPC分类号: G06T5/00
摘要: Methods and apparatuses with training or image enhancement are disclosed. The image enhancement method includes obtaining an input image, estimating a noise distribution of the input image by implementing a noise model based on the input image, and generating an enhanced image by implementing an image enhancement model dependent on the input image and the estimated noise distribution.
-
公开(公告)号:EP4322103A1
公开(公告)日:2024-02-14
申请号:EP23189386.8
申请日:2023-08-03
发明人: SEO, Geonseok , KI, Sehwan , CHOI, Jae Seok , KIM, Insoo , LEE, Hyong Euk
摘要: A processor-implemented method includes: obtaining a plurality of image frames acquired for a scene within a predetermined time; determining loss values respectively corresponding to the plurality of image frames; determining a reference frame among the plurality of image frames based on the loss values; and generating a final image of the scene based on the reference frame.
-
-