Unsupervised Image Super-Resolution using Cycle-in-Cycle Generative Adversarial Networks
arXiv:1809.00437
Abstract
We consider the single image super-resolution problem in a more general case that the low-/high-resolution pairs and the down-sampling process are unavailable. Different from traditional super-resolution formulation, the low-resolution input is further degraded by noises and blurring. This complicated setting makes supervised learning and accurate kernel estimation impossible. To solve this problem, we resort to unsupervised learning without paired data, inspired by the recent successful image-to-image translation applications. With generative adversarial networks (GAN) as the basic component, we propose a Cycle-in-Cycle network structure to tackle the problem within three steps. First, the noisy and blurry input is mapped to a noise-free low-resolution space. Then the intermediate image is up-sampled with a pre-trained deep model. Finally, we fine-tune the two modules in an end-to-end manner to get the high-resolution output. Experiments on NTIRE2018 datasets demonstrate that the proposed unsupervised method achieves comparable results as the state-of-the-art supervised models.
arXiv comment10 pages (reference included), 6 figures
References in corpus (6)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
- Learning a Single Convolutional Super-Resolution Network for Multiple Degradations
- Benchmarking Super-Resolution Algorithms on Real Data
- Simple, Accurate, and Robust Nonparametric Blind Super-Resolution
Cited by in corpus (5)
- ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
- A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
- Unsupervised Degradation Learning for Single Image Super-Resolution
- Unsupervised Image Noise Modeling with Self-Consistent GAN
- Unsupervised Single Image Deraining with Self-supervised Constraints