DC Field | Value | Language |
---|---|---|
dc.contributor.author | Vu, Thang | ko |
dc.contributor.author | Luu, Tung M | ko |
dc.contributor.author | Yoo, Chang-Dong | ko |
dc.date.accessioned | 2023-08-24T10:00:19Z | - |
dc.date.available | 2023-08-24T10:00:19Z | - |
dc.date.created | 2023-07-06 | - |
dc.date.issued | 2019-09 | - |
dc.identifier.citation | 15th European Conference on Computer Vision, ECCV 2018, pp.98 - 113 | - |
dc.identifier.issn | 0302-9743 | - |
dc.identifier.uri | http://hdl.handle.net/10203/311798 | - |
dc.description.abstract | This paper considers a deep Generative Adversarial Networks (GAN) based method referred to as the Perception-Enhanced Super-Resolution (PESR) for Single Image Super Resolution (SISR) that enhances the perceptual quality of the reconstructed images by considering the following three issues: (1) ease GAN training by replacing an absolute with a relativistic discriminator, (2) include in the loss function a mechanism to emphasize difficult training samples which are generally rich in texture and (3) provide a flexible quality control scheme at test time to trade-off between perception and fidelity. Based on extensive experiments on six benchmark datasets, PESR outperforms recent state-of-the-art SISR methods in terms of perceptual quality. The code is available at https://github.com/thangvubk/PESR. | - |
dc.language | English | - |
dc.publisher | Springer Verlag | - |
dc.title | Perception-enhanced image super-resolution via relativistic generative adversarial networks | - |
dc.type | Conference | - |
dc.identifier.wosid | 000594394700007 | - |
dc.identifier.scopusid | 2-s2.0-85061724416 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 98 | - |
dc.citation.endingpage | 113 | - |
dc.citation.publicationname | 15th European Conference on Computer Vision, ECCV 2018 | - |
dc.identifier.conferencecountry | GE | - |
dc.identifier.conferencelocation | Munich | - |
dc.identifier.doi | 10.1007/978-3-030-11021-5_7 | - |
dc.contributor.localauthor | Yoo, Chang-Dong | - |
dc.contributor.nonIdAuthor | Luu, Tung M | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.