Real-World Image Super-Resolution by Exclusionary Dual-Learning
Abstract
Real-world image super-resolution is a practical image restoration problem that aims to obtain high-quality images from in-the-wild input, has recently received considerable attention with regard to its tremendous application potentials. Although deep learning-based methods have achieved promising restoration quality on real-world image super-resolution datasets, they ignore the relationship between L1- and perceptual- minimization and roughly adopt auxiliary large-scale datasets for pre-training. In this paper, we discuss the image types within a corrupted image and the property of perceptual- and Euclidean- based evaluation protocols. Then we propose a method, Real-World image Super-Resolution by Exclusionary Dual-Learning (RWSR-EDL) to address the feature diversity in perceptual- and L1- based cooperative learning. Moreover, a noise-guidance data collection strategy is developed to address the training time consumption in multiple datasets optimization. When an auxiliary dataset is incorporated, RWSR-EDL achieves promising results and repulses any training time increment by adopting the noise-guidance data collection strategy. Extensive experiments show that RWSR-EDL achieves competitive performance over state-of-the-art methods on four in-the-wild image super-resolution datasets.
Cite
@article{arxiv.2206.02609,
title = {Real-World Image Super-Resolution by Exclusionary Dual-Learning},
author = {Hao Li and Jinghui Qin and Zhijing Yang and Pengxu Wei and Jinshan Pan and Liang Lin and Yukai Shi},
journal= {arXiv preprint arXiv:2206.02609},
year = {2022}
}
Comments
IEEE TMM 2022; Considering large volume of RealSR datasets, a multi-dataset sampling scheme is developed