-
公开(公告)号:US11907835B2
公开(公告)日:2024-02-20
申请号:US16765886
申请日:2018-11-26
Applicant: YEDA RESEARCH AND DEVELOPMENT CO. LTD.
Inventor: Michal Irani , Assaf Shocher
CPC classification number: G06N3/08 , G06T3/4053 , G06T5/001 , G06T2207/20016 , G06T2207/20081 , G06T2207/20084 , G06T2207/20132
Abstract: Given an input image, an image enhancement task, and no external examples available to train on, an Image-Specific Deep Network is constructed tailored to solve the task for this specific image. Since there are no external examples available to train on, the network is trained on examples extracted directly from the input image itself. The current solution solves the problem of Super-Resolution (SR), whereas the framework is more general and is not restricted to SR.