Pairwise Distance Distillation for Unsupervised Real-World Image Super-Resolution

TL;DR

This paper introduces a novel pairwise distance distillation framework for unsupervised real-world image super-resolution, enabling models to adapt to real degradations without paired data, outperforming existing methods.

Contribution

It presents a new distillation-based approach that specializes models for real-world degradations by transferring intra- and inter-model distances, improving super-resolution quality.

Findings

Significantly improves fidelity and perceptual quality in real-world super-resolution.

Outperforms state-of-the-art methods on diverse datasets.

Effectively adapts synthetic models to real-world degradations.

Abstract

Standard single-image super-resolution creates paired training data from high-resolution images through fixed downsampling kernels. However, real-world super-resolution (RWSR) faces unknown degradations in the low-resolution inputs, all the while lacking paired training data. Existing methods approach this problem by learning blind general models through complex synthetic augmentations on training inputs; they sacrifice the performance on specific degradation for broader generalization to many possible ones. We address the unsupervised RWSR for a targeted real-world degradation. We study from a distillation perspective and introduce a novel pairwise distance distillation framework. Through our framework, a model specialized in synthetic degradation adapts to target real-world degradations by distilling intra- and inter-model distances across the specialized model and an auxiliary generalized model. Experiments on diverse datasets demonstrate that our method significantly enhances fidelity and perceptual quality, surpassing state-of-the-art approaches in RWSR. The source code is available at https://github.com/Yuehan717/PDD.