Existing image super-resolution (SR) techniques often fail to generalize effectively in complex real-world settings due to the significant divergence between training data and practical scenarios. To address this challenge, previous efforts have either manually simulated intricate physical-based degradations or utilized learning-based techniques, yet these approaches remain inadequate for producing large-scale, realistic, and diverse data simultaneously. In this paper, we introduce a novel Realistic Decoupled Data Generator (RealDGen), an unsupervised learning data generation framework designed for real-world super-resolution. We meticulously develop content and degradation extraction strategies, which are integrated into a novel content-degradation decoupled diffusion model to create realistic low-resolution images from unpaired real LR and HR images. Extensive experiments demonstrate that RealDGen excels in generating large-scale, high-quality paired data that mirrors real-world degradations, significantly advancing the performance of popular SR models on various real-world benchmarks.
@article{arxiv.2406.07255,
title = {Towards Realistic Data Generation for Real-World Super-Resolution},
author = {Long Peng and Wenbo Li and Renjing Pei and Jingjing Ren and Jiaqi Xu and Yang Wang and Yang Cao and Zheng-Jun Zha},
journal= {arXiv preprint arXiv:2406.07255},
year = {2025}
}