Abstract | ||
---|---|---|
Existing single image super-resolution (SISR) methods usually focus on Low-Resolution (LR) images which are artificially generated from High-Resolution (HR) images by a down-sampling process, but are not robust for unmatched training set and testing set. This paper proposes a GAN Flexible Lmser (GFLmser) network that bidirectionally learns the High-to-Low (H2L) process that degrades HR images to LR images and the Low-to-High (L2H) process that recovers the LR images back to HR images. The two directions share the same architecture, added with the gated skip connections from the H2L-net to the L2H-net in order to enhance information transferring for super-resolution. In comparison with several related state-of-the-art methods, experiments demonstrate that not only GFLmser is the most robust method on images of unmatched training set and testing set, but also its performance on real-world face LR images is best in PSNR and reasonably good in FID.
|
Year | DOI | Venue |
---|---|---|
2019 | 10.1145/3343031.3350952 | Proceedings of the 27th ACM International Conference on Multimedia |
Keywords | Field | DocType |
gan, image super-resolution, lmser | Computer vision,Computer science,Artificial intelligence,Superresolution | Conference |
ISBN | Citations | PageRank |
978-1-4503-6889-6 | 1 | 0.43 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Peiying Li | 1 | 1 | 0.43 |
Shikui Tu | 2 | 39 | 14.25 |
Lei Xu | 3 | 3590 | 387.32 |