Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolution
arXiv:2003.07018
Abstract
Deep neural networks have exhibited promising performance in image super-resolution (SR) by learning a nonlinear mapping function from low-resolution (LR) images to high-resolution (HR) images. However, there are two underlying limitations to existing SR methods. First, learning the mapping function from LR to HR images is typically an ill-posed problem, because there exist infinite HR images that can be downsampled to the same LR image. As a result, the space of the possible functions can be extremely large, which makes it hard to find a good solution. Second, the paired LR-HR data may be unavailable in real-world applications and the underlying degradation method is often unknown. For such a more general case, existing SR models often incur the adaptation problem and yield poor performance. To address the above issues, we propose a dual regression scheme by introducing an additional constraint on LR data to reduce the space of the possible functions. Specifically, besides the mapping from LR to HR images, we learn an additional dual regression mapping estimates the down-sampling kernel and reconstruct LR images, which forms a closed-loop to provide additional supervision. More critically, since the dual regression process does not depend on HR images, we can directly learn from LR images. In this sense, we can easily adapt SR models to real-world data, e.g., raw video frames from YouTube. Extensive experiments with paired training data and unpaired real-world data demonstrate our superiority over existing methods.
This paper is accepted by CVPR 2020
References in corpus (12)
- Sketch-based Manga Retrieval using Manga109 Dataset
- Dual Learning for Machine Translation
- Blind Super-Resolution Kernel Estimation using an Internal-GAN
- Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis
- Discrimination-aware Network Pruning for Deep Model Compression
- Super-Resolution 1H Magnetic Resonance Spectroscopic Imaging utilizing Deep Learning
- NAT: Neural Architecture Transformer for Accurate and Compact Architectures
- Multi-marginal Wasserstein GAN
- Adversarial Learning with Local Coordinate Coding
- Unsupervised Degradation Learning for Single Image Super-Resolution
- Dual Reconstruction Nets for Image Super-Resolution with Gradient Sensitive Loss
- The Shallow End: Empowering Shallower Deep-Convolutional Networks through Auxiliary Outputs