Two Heads Better than One: Dual Degradation Representation for Blind Super-Resolution
By: Hsuan Yuan , Shao-Yu Weng , I-Hsuan Lo and more
Potential Business Impact:
Makes blurry pictures sharp, even with unknown damage.
Previous methods have demonstrated remarkable performance in single image super-resolution (SISR) tasks with known and fixed degradation (e.g., bicubic downsampling). However, when the actual degradation deviates from these assumptions, these methods may experience significant declines in performance. In this paper, we propose a Dual Branch Degradation Extractor Network to address the blind SR problem. While some blind SR methods assume noise-free degradation and others do not explicitly consider the presence of noise in the degradation model, our approach predicts two unsupervised degradation embeddings that represent blurry and noisy information. The SR network can then be adapted to blur embedding and noise embedding in distinct ways. Furthermore, we treat the degradation extractor as a regularizer to capitalize on differences between SR and HR images. Extensive experiments on several benchmarks demonstrate our method achieves SOTA performance in the blind SR problem.
Similar Papers
Adaptive Blind Super-Resolution Network for Spatial-Specific and Spatial-Agnostic Degradations
CV and Pattern Recognition
Fixes blurry, noisy, or small pictures better.
Dual-domain Adaptation Networks for Realistic Image Super-resolution
CV and Pattern Recognition
Makes blurry photos sharp and clear.
Undertrained Image Reconstruction for Realistic Degradation in Blind Image Super-Resolution
Image and Video Processing
Makes blurry pictures clear, even real ones.