DC Field | Value | Language |
---|---|---|
dc.contributor.author | Chung, Hyungjin | ko |
dc.contributor.author | Kim, Jeongsol | ko |
dc.contributor.author | Kim, Sehui | ko |
dc.contributor.author | Ye, Jong Chul | ko |
dc.date.accessioned | 2023-12-12T11:00:57Z | - |
dc.date.available | 2023-12-12T11:00:57Z | - |
dc.date.created | 2023-12-08 | - |
dc.date.issued | 2023-06 | - |
dc.identifier.citation | IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, pp.6059 - 6069 | - |
dc.identifier.issn | 1063-6919 | - |
dc.identifier.uri | http://hdl.handle.net/10203/316320 | - |
dc.description.abstract | Diffusion model-based inverse problem solvers have demonstrated state-of-the-art performance in cases where the forward operator is known (i.e. non-blind). However, the applicability of the method to blind inverse problems has yet to be explored. In this work, we show that we can indeed solve a family of blind inverse problems by constructing another diffusion prior for the forward operator. Specifically, parallel reverse diffusion guided by gradients from the intermediate stages enables joint optimization of both the forward operator parameters as well as the image, such that both are jointly estimated at the end of the parallel reverse diffusion procedure. We show the efficacy of our method on two representative tasks - blind deblurring, and imaging through turbulence - and show that our method yields state-of-the-art performance, while also being flexible to be applicable to general blind inverse problems when we know the functional forms. Code available: https://github.com/BlindDPS/blind-dps | - |
dc.language | English | - |
dc.publisher | IEEE Computer Society | - |
dc.title | Parallel Diffusion Models of Operator and Image for Blind Inverse Problems | - |
dc.type | Conference | - |
dc.identifier.wosid | 001058542606040 | - |
dc.identifier.scopusid | 2-s2.0-85171366228 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 6059 | - |
dc.citation.endingpage | 6069 | - |
dc.citation.publicationname | IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023 | - |
dc.identifier.conferencecountry | CN | - |
dc.identifier.conferencelocation | Vancouver, BC | - |
dc.identifier.doi | 10.1109/CVPR52729.2023.00587 | - |
dc.contributor.localauthor | Ye, Jong Chul | - |
dc.contributor.nonIdAuthor | Kim, Sehui | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.