Abstract | ||
---|---|---|
Deep Convolution Neural Networks (CNN) have achieved significant performance on single image super-resolution (SR) recently. However, existing CNN-based methods use artificially synthetic low-resolution (LR) and high-resolution (HR) image pairs to train networks, which cannot handle real-world cases since the degradation from HR to LR is much more complex than manually designed. To solve this problem, we propose a real-world LR images guided bi-cycle network for single image super-resolution, in which the bidirectional structural consistency is exploited to train both the degradation and SR reconstruction networks in an unsupervised way. Specifically, we propose a degradation network to model the real-world degradation process from HR to LR via generative adversarial networks, and these generated realistic LR images paired with real-world HR images are exploited for training the SR reconstruction network, forming the first cycle. Then in the second reverse cycle, consistency of real-world LR images are exploited to further stabilize the training of SR reconstruction and degradation networks. Extensive experiments on both synthetic and real-world images demonstrate that the proposed algorithm performs favorably against state-of-the-art single image SR methods. |
Year | Venue | DocType |
---|---|---|
2018 | arXiv: Computer Vision and Pattern Recognition | Journal |
Volume | Citations | PageRank |
abs/1812.04240 | 3 | 0.38 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tianyu Zhao | 1 | 3 | 3.42 |
Wenqi Ren | 2 | 335 | 27.14 |
Changqing Zhang | 3 | 730 | 36.91 |
Dongwei Ren | 4 | 103 | 12.26 |
Qinghua Hu | 5 | 4028 | 171.50 |