Publications
Detailed Information
Kernel Estimation for super-resolution with Flow-based Kernel Prior
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Cho, Sunwoo | - |
dc.contributor.author | Cho, Nam Ik | - |
dc.date.accessioned | 2022-10-12T01:12:07Z | - |
dc.date.available | 2022-10-12T01:12:07Z | - |
dc.date.created | 2022-09-30 | - |
dc.date.issued | 2022-01 | - |
dc.identifier.citation | INTERNATIONAL WORKSHOP ON ADVANCED IMAGING TECHNOLOGY (IWAIT) 2022, Vol.12177, p. 1217739 | - |
dc.identifier.issn | 0277-786X | - |
dc.identifier.uri | https://hdl.handle.net/10371/185938 | - |
dc.description.abstract | Single-Image Super-Resolution methods typically assume that a low-resolution image is degraded from a high-resolution one through "bicubic" kernel convolution followed by downscaling. However, this induces a domain gap between training image datasets and the real scenario's test images, which are down-sampled from the images that underwent convolution with arbitrary unknown kernels. Hence, correct kernel estimation for a given real-world image is necessary for its better super-resolution. One of the kernel estimation methods, KernelGAN(1) locates the input image in the same domain of high-resolution image for accurate estimation. However, using only a low-resolution image cannot fully utilize the high-frequency information in the original image. To increase the estimation accuracy, we adopt a superresolved image for kernel estimation. Also, we use a flow-based kernel prior to getting a reasonable super-resolved image and stabilize the whole estimation process. | - |
dc.language | 영어 | - |
dc.publisher | SPIE-INT SOC OPTICAL ENGINEERING | - |
dc.title | Kernel Estimation for super-resolution with Flow-based Kernel Prior | - |
dc.type | Article | - |
dc.identifier.doi | 10.1117/12.2625958 | - |
dc.citation.journaltitle | INTERNATIONAL WORKSHOP ON ADVANCED IMAGING TECHNOLOGY (IWAIT) 2022 | - |
dc.identifier.wosid | 000836377300116 | - |
dc.identifier.scopusid | 2-s2.0-85131804710 | - |
dc.citation.startpage | 1217739 | - |
dc.citation.volume | 12177 | - |
dc.description.isOpenAccess | N | - |
dc.contributor.affiliatedAuthor | Cho, Nam Ik | - |
dc.type.docType | Proceedings Paper | - |
dc.description.journalClass | 1 | - |
- Appears in Collections:
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.