Explorable Super Resolution

Yuval Bahat; Tomer Michaeli

doi:10.1109/cvpr42600.2020.00279

CVPR2020顶会

Explorable Super Resolution

Yuval Bahat, Tomer Michaeli

arXiv DOI 出版方

2020年份

15顶会引用

摘要

Low-res input Other perfectly consistent reconstructions produced with our approach Figure 1: Exploring HR explanations to an LR image. Existing SR methods (e.g. ESRGAN [26] ) output only one explanation to the input image. In contrast, our explorable SR framework allows producing infinite different perceptually satisfying HR images, that all identically match a given LR input, when down-sampled. Please zoom-in to view subtle details.