DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Hyun-Ho | ko |
dc.contributor.author | Choi, Jae-Seok | ko |
dc.contributor.author | Kim, Munchurl | ko |
dc.date.accessioned | 2023-07-28T07:01:03Z | - |
dc.date.available | 2023-07-28T07:01:03Z | - |
dc.date.created | 2023-07-07 | - |
dc.date.issued | 2017-01 | - |
dc.identifier.citation | Computational Imaging XV 2017, pp.81 - 86 | - |
dc.identifier.issn | 2470-1173 | - |
dc.identifier.uri | http://hdl.handle.net/10203/310949 | - |
dc.description.abstract | Super-resolution (SR) is an elegant technique that can reconstruct high-resolution (HR) videos/images from their low-resolution (LR) counterparts. Most of the conventional SR methods utilize linear mappings to learn complex LR-to-HR relationships, where these linear mappings are often learned from training. Inspired by our previous linear mapping based SR method [1], we propose a novel super-interpolation based SR method that utilizes adjusted self-exemplars. That is, in order to find sufficient amounts of LR-HR patch pairs in self-exemplars, we iteratively augment self-exemplars from an LR input image to create additional self-exemplars. In doing so, our proposed SR method is able to find well-learned linear mappings on-line from self-exemplars without using external training images, and outperforms other conventional SR methods. | - |
dc.language | English | - |
dc.publisher | Society for Imaging Science and Technology | - |
dc.title | Single image super-interpolation using adjusted self-exemplars | - |
dc.type | Conference | - |
dc.identifier.scopusid | 2-s2.0-85041506579 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 81 | - |
dc.citation.endingpage | 86 | - |
dc.citation.publicationname | Computational Imaging XV 2017 | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Burlingame | - |
dc.identifier.doi | 10.2352/ISSN.2470-1173.2017.17.COIMG-429 | - |
dc.contributor.localauthor | Kim, Munchurl | - |
dc.contributor.nonIdAuthor | Kim, Hyun-Ho | - |
dc.contributor.nonIdAuthor | Choi, Jae-Seok | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.