Unsupervised Degradation Learning for Single Image Super-Resolution

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.

9 pages, 9 figures

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
• Residual Dense Network for Image Super-Resolution
• Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform
• Unsupervised Image Super-Resolution using Cycle-in-Cycle Generative Adversarial Networks
• Simple, Accurate, and Robust Nonparametric Blind Super-Resolution

Cited by in corpus (9)

• RR-DnCNN v2.0: Enhanced Restoration-Reconstruction Deep Neural Network for Down-Sampling Based Video Coding
• Toward Real-World Super-Resolution via Adaptive Downsampling Models
• Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolution
• Real-World Single Image Super-Resolution: A Brief Review
• SRDGAN: learning the noise prior for Super Resolution with Dual Generative Adversarial Networks
• EventSR: From Asynchronous Events to Image Reconstruction, Restoration, and Super-Resolution via End-to-End Adversarial Learning
• Unpaired Image Super-Resolution using Pseudo-Supervision
• Multi-modality super-resolution loss for GAN-based super-resolution of clinical CT images using micro CT image database
• Rethinking conditional GAN training: An approach using geometrically structured latent manifolds