Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Jaewon | - |
dc.contributor.author | Jin, Kyong Hwan | - |
dc.date.accessioned | 2023-12-26T18:13:15Z | - |
dc.date.available | 2023-12-26T18:13:15Z | - |
dc.date.created | 2022-12-30 | - |
dc.date.issued | 2022-06-21 | - |
dc.identifier.isbn | 9781665469463 | - |
dc.identifier.issn | 1063-6919 | - |
dc.identifier.uri | http://hdl.handle.net/20.500.11750/46830 | - |
dc.description.abstract | Recent works with an implicit neural function shed light on representing images in arbitrary resolution. However, a standalone multi-layer perceptron shows limited performance in learning high-frequency components. In this paper, we propose a Local Texture Estimator (LTE), a dominant-frequency estimator for natural images, enabling an implicit function to capture fine details while reconstructing images in a continuous manner. When jointly trained with a deep super-resolution (SR) architecture, LTE is capable of characterizing image textures in 2D Fourier space. We show that an LTE-based neuralfunction achieves favorable performance against existing deep SR methods within an arbitrary-scale factor. Furthermore, we demonstrate that our implementation takes the shortest running time compared to previous works. © 2022 IEEE. | - |
dc.language | English | - |
dc.publisher | IEEE Computer Society | - |
dc.title | Local Texture Estimator for Implicit Representation Function | - |
dc.type | Conference Paper | - |
dc.identifier.doi | 10.1109/CVPR52688.2022.00197 | - |
dc.identifier.scopusid | 2-s2.0-85141304166 | - |
dc.identifier.bibliographicCitation | Conference on Computer Vision and Pattern Recognition (poster), pp.1919 - 1928 | - |
dc.identifier.url | https://cvpr2022.thecvf.com/posters-621-am | - |
dc.citation.conferencePlace | US | - |
dc.citation.conferencePlace | New Orleans | - |
dc.citation.endPage | 1928 | - |
dc.citation.startPage | 1919 | - |
dc.citation.title | Conference on Computer Vision and Pattern Recognition (poster) | - |
There are no files associated with this item.