Real-World Image Super-Resolution by Exclusionary Dual-Learning

TL;DR

This paper introduces RWSR-EDL, a novel dual-learning approach for real-world image super-resolution that effectively balances perceptual and Euclidean-based evaluations, utilizing a noise-guidance strategy to optimize training efficiency.

Contribution

The paper proposes a new exclusionary dual-learning framework for real-world image super-resolution, addressing feature diversity and training efficiency with a noise-guidance data collection method.

Findings

RWSR-EDL outperforms state-of-the-art methods on four datasets.

The noise-guidance strategy reduces training time without sacrificing quality.

The method effectively balances perceptual and L1-based evaluations.

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.