Dual Adversarial Adaptation for Cross-Device Real-World Image Super-Resolution

TL;DR

This paper introduces DADA, an unsupervised domain adaptation method for real-world image super-resolution across different devices, effectively transferring models trained on one camera to others without requiring paired high-resolution data.

Contribution

The paper proposes a novel Dual Adversarial Adaptation (DADA) framework with domain-invariant attention and dual adversarial training for cross-device super-resolution, addressing the lack of paired data.

Findings

DADA outperforms existing methods in six real-to-real camera adaptation settings.

The dual adversarial framework enhances model transferability across different imaging devices.

Experimental results demonstrate superior super-resolution performance on diverse camera datasets.

Abstract

Due to the sophisticated imaging process, an identical scene captured by different cameras could exhibit distinct imaging patterns, introducing distinct proficiency among the super-resolution (SR) models trained on images from different devices. In this paper, we investigate a novel and practical task coded cross-device SR, which strives to adapt a real-world SR model trained on the paired images captured by one camera to low-resolution (LR) images captured by arbitrary target devices. The proposed task is highly challenging due to the absence of paired data from various imaging devices. To address this issue, we propose an unsupervised domain adaptation mechanism for real-world SR, named Dual ADversarial Adaptation (DADA), which only requires LR images in the target domain with available real paired data from a source camera. DADA employs the Domain-Invariant Attention (DIA) module to establish the basis of target model training even without HR supervision. Furthermore, the dual framework of DADA facilitates an Inter-domain Adversarial Adaptation (InterAA) in one branch for two LR input images from two domains, and an Intra-domain Adversarial Adaptation (IntraAA) in two branches for an LR input image. InterAA and IntraAA together improve the model transferability from the source domain to the target. We empirically conduct experiments under six Real to Real adaptation settings among three different cameras, and achieve superior performance compared with existing state-of-the-art approaches. We also evaluate the proposed DADA to address the adaptation to the video camera, which presents a promising research topic to promote the wide applications of real-world super-resolution. Our source code is publicly available at https://github.com/lonelyhope/DADA.git.