dc.citation.conferencePlace |
UK |
- |
dc.citation.conferencePlace |
Guildford, Surrey |
- |
dc.citation.endPage |
14.12 |
- |
dc.citation.startPage |
14.1 |
- |
dc.citation.title |
British Machine Vision Conference |
- |
dc.contributor.author |
Kwon, Younghee |
- |
dc.contributor.author |
Kim, Kwang In |
- |
dc.contributor.author |
Kim, Jin Hyung |
- |
dc.contributor.author |
Theobalt, Christian |
- |
dc.date.accessioned |
2023-12-20T01:41:20Z |
- |
dc.date.available |
2023-12-20T01:41:20Z |
- |
dc.date.created |
2019-02-28 |
- |
dc.date.issued |
2012-09-03 |
- |
dc.description.abstract |
In this paper, we describe a framework for learning-based image enhancement. At the core of our algorithm lies a generic regularization framework that comprises a prior on natural images, as well as an application-specific conditional model based on Gaussian processes. In contrast to prior learning-based approaches, our algorithm can instantly learn task-specific degradation models from sample images which enables users to easily adopt the algorithm to a specific problem and data set of interest. This is facilitated by our efficient approximation scheme of large-scale Gaussian processes. We demonstrate the efficiency and effectiveness of our approach by applying it to two example enhancement applications: single-image super-resolution as well as artifact removal in JPEG-encoded images. |
- |
dc.identifier.bibliographicCitation |
British Machine Vision Conference, pp.14.1 - 14.12 |
- |
dc.identifier.doi |
10.5244/C.26.14 |
- |
dc.identifier.issn |
0000-0000 |
- |
dc.identifier.scopusid |
2-s2.0-84898438108 |
- |
dc.identifier.uri |
https://scholarworks.unist.ac.kr/handle/201301/32629 |
- |
dc.identifier.url |
http://www.bmva.org/bmvc/2012/BMVC/paper014/index.html |
- |
dc.language |
영어 |
- |
dc.publisher |
British Machine Vision Association, BMVA |
- |
dc.title |
Efficient learning-based image enhancement: Application to super-resolution and compression artifact removal |
- |
dc.type |
Conference Paper |
- |
dc.date.conferenceDate |
2012-09-03 |
- |