Learning a Single Convolutional Super-Resolution Network for Multiple Degradations
arXiv:1712.06116
Abstract
Recent years have witnessed the unprecedented success of deep convolutional neural networks (CNNs) in single image super-resolution (SISR). However, existing CNN-based SISR methods mostly assume that a low-resolution (LR) image is bicubicly downsampled from a high-resolution (HR) image, thus inevitably giving rise to poor performance when the true degradation does not follow this assumption. Moreover, they lack scalability in learning a single model to non-blindly deal with multiple degradations. To address these issues, we propose a general framework with dimensionality stretching strategy that enables a single convolutional super-resolution network to take two key factors of the SISR degradation process, i.e., blur kernel and noise level, as input. Consequently, the super-resolver can handle multiple and even spatially variant degradations, which significantly improves the practicability. Extensive experimental results on synthetic and real LR images show that the proposed convolutional super-resolution network not only can produce favorable results on multiple degradations but also is computationally efficient, providing a highly effective and scalable solution to practical SISR applications.
CVPR 2018, code: https://github.com/cszn/SRMD
References in corpus (3)
Cited by in corpus (8)
- Residual Dense Network for Image Super-Resolution
- Unsupervised Image Super-Resolution using Cycle-in-Cycle Generative Adversarial Networks
- Bridging Component Learning with Degradation Modelling for Blind Image Super-Resolution
- Learning A Single Network for Scale-Arbitrary Super-Resolution
- Deep Network Interpolation for Continuous Imagery Effect Transition
- Unsupervised Real Image Super-Resolution via Generative Variational AutoEncoder
- Image Formation Model Guided Deep Image Super-Resolution
- Deep Likelihood Network for Image Restoration with Multiple Degradation Levels