Name
Abstract | ||
|---|---|---|
Convolution neural networks have achieved unprecedented success for image super resolution (SR). However, such methods typically assume a predetermined degradation that deviates from real-world cases, resulting in poor performance frequently. To improve upon this, researchers have proposed various methods to handle super resolution under multiple degradations. Despite, such methods fail to capture an accurate image prior, which is a crucial part of reconstructing image details. In this work, we propose a novel framework called Decoupled Super Resolver (DSR) with both promising performance and applicability. DSR employs a LR Finer to project a degraded image back to its clean version and a Combinational Super Resolver to retrieve a more comprehensive and accurate prior. The latter module further enables DSR to output high-resolution images by combining both image-specific knowledge and external statistics. Extensive experiments under various degradation settings demonstrate the effectiveness of DSR by setting new state-of-the-arts on multiple benchmarks. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/ICME46284.2020.9102941 | 2020 IEEE International Conference on Multimedia and Expo (ICME) |
Keywords | DocType | ISSN |
Single Image Super Resolution | Conference | 1945-7871 |
ISBN | Citations | PageRank |
978-1-7281-1332-6 | 1 | 0.37 |
References | Authors | |
6 | 3 | |