Dual-domain Adaptation Networks for Realistic Image Super-resolution

TL;DR

This paper presents Dual-domain Adaptation Networks that effectively adapt pre-trained super-resolution models from synthetic to real-world images by combining spatial and frequency domain adaptation, improving results on realistic SR benchmarks.

Contribution

The paper introduces a novel dual-domain adaptation approach that combines spatial and frequency domain strategies to enhance real-world image super-resolution performance.

Findings

Outperforms existing state-of-the-art models on benchmark datasets.

Effectively adapts pre-trained models to real-world degradation patterns.

Demonstrates improved high-frequency detail recovery in SR results.

Abstract

Realistic image super-resolution (SR) focuses on transforming real-world low-resolution (LR) images into high-resolution (HR) ones, handling more complex degradation patterns than synthetic SR tasks. This is critical for applications like surveillance, medical imaging, and consumer electronics. However, current methods struggle with limited real-world LR-HR data, impacting the learning of basic image features. Pre-trained SR models from large-scale synthetic datasets offer valuable prior knowledge, which can improve generalization, speed up training, and reduce the need for extensive real-world data in realistic SR tasks. In this paper, we introduce a novel approach, Dual-domain Adaptation Networks, which is able to efficiently adapt pre-trained image SR models from simulated to real-world datasets. To achieve this target, we first set up a spatial-domain adaptation strategy through selectively updating parameters of pre-trained models and employing the low-rank adaptation technique to adjust frozen parameters. Recognizing that image super-resolution involves recovering high-frequency components, we further integrate a frequency domain adaptation branch into the adapted model, which combines the spectral data of the input and the spatial-domain backbone's intermediate features to infer HR frequency maps, enhancing the SR result. Experimental evaluations on public realistic image SR benchmarks, including RealSR, D2CRealSR, and DRealSR, demonstrate the superiority of our proposed method over existing state-of-the-art models. Codes are available at: https://github.com/dummerchen/DAN.