WDFSR: Normalizing flow based on the wavelet-domain for super-resolution
We propose a normalizing flow based on the wavelet framework for super-resolution (SR) called WDFSR. It learns the conditional distribution mapping between low-resolution images in the RGB domain and high-resolution images in the wavelet domain to simultaneously generate high-resolution images of di...
Сохранить в:
| Главные авторы: | , , , |
|---|---|
| Формат: | Artigo |
| Язык: | Inglês |
| Опубликовано: |
Tsinghua University Press
2025-04-01
|
| Серии: | Computational Visual Media |
| Предметы: | |
| Online-ссылка: | https://www.sciopen.com/article/10.26599/CVM.2025.9450374 |
| Метки: |
Нет меток, Требуется 1-ая метка записи!
|