There are no files associated with this item.
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.citation.endPage | 1805 | - |
dc.citation.number | 9 | - |
dc.citation.startPage | 1792 | - |
dc.citation.title | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | - |
dc.citation.volume | 37 | - |
dc.contributor.author | Kwon, Younghee | - |
dc.contributor.author | Kim, Kwang In | - |
dc.contributor.author | Tompkin, James | - |
dc.contributor.author | Kim, Jin Hyung | - |
dc.contributor.author | Theobalt, Christian | - |
dc.date.accessioned | 2023-12-22T00:42:14Z | - |
dc.date.available | 2023-12-22T00:42:14Z | - |
dc.date.created | 2019-02-25 | - |
dc.date.issued | 2015-09 | - |
dc.description.abstract | Improving the quality of degraded images is a key problem in image processing, but the breadth of the problem leads to domain-specific approaches for tasks such as super-resolution and compression artifact removal. Recent approaches have shown that a general approach is possible by learning application-specific models from examples; however, learning models sophisticated enough to generate high-quality images is computationally expensive, and so specific per-application or per-dataset models are impractical. To solve this problem, we present an efficient semi-local approximation scheme to large-scale Gaussian processes. This allows efficient learning of task-specific image enhancements from example images without reducing quality. As such, our algorithm can be easily customized to specific applications and datasets, and we show the efficiency and effectiveness of our approach across five domains: single-image super-resolution for scene, human face, and text images, and artifact removal in JPEG- and JPEG 2000-encoded images. | - |
dc.identifier.bibliographicCitation | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, v.37, no.9, pp.1792 - 1805 | - |
dc.identifier.doi | 10.1109/TPAMI.2015.2389797 | - |
dc.identifier.issn | 0162-8828 | - |
dc.identifier.scopusid | 2-s2.0-84939248816 | - |
dc.identifier.uri | https://scholarworks.unist.ac.kr/handle/201301/26245 | - |
dc.identifier.url | https://ieeexplore.ieee.org/document/7005530 | - |
dc.identifier.wosid | 000359216600005 | - |
dc.language | 영어 | - |
dc.publisher | IEEE COMPUTER SOC | - |
dc.title | Efficient Learning of Image Super-Resolution and Compression Artifact Removal with Semi-Local Gaussian Processes | - |
dc.type | Article | - |
dc.description.isOpenAccess | FALSE | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence; Engineering, Electrical & Electronic | - |
dc.relation.journalResearchArea | Computer Science; Engineering | - |
dc.type.docType | Article | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordAuthor | Image enhancement | - |
dc.subject.keywordAuthor | super-resolution | - |
dc.subject.keywordAuthor | image compression | - |
dc.subject.keywordAuthor | Gaussian process | - |
dc.subject.keywordAuthor | regression | - |
dc.subject.keywordPlus | CODED IMAGES | - |
dc.subject.keywordPlus | REGRESSION | - |
dc.subject.keywordPlus | RECONSTRUCTION | - |
dc.subject.keywordPlus | LIMITS | - |
dc.subject.keywordPlus | JPEG | - |
dc.subject.keywordPlus | DCT | - |
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Tel : 052-217-1404 / Email : scholarworks@unist.ac.kr
Copyright (c) 2023 by UNIST LIBRARY. All rights reserved.
ScholarWorks@UNIST was established as an OAK Project for the National Library of Korea.