RFormer: Transformer-based Generative Adversarial Network for Real Fundus Image Restoration on A New Clinical Benchmark

TL;DR

This paper introduces RFormer, a transformer-based GAN that effectively restores real clinical fundus images, improving image quality and aiding clinical diagnosis, validated on a newly established dataset and downstream tasks.

Contribution

The paper presents a novel Transformer-based GAN architecture for real fundus image restoration and introduces a new clinical benchmark dataset for this task.

Findings

RFormer outperforms state-of-the-art methods on clinical fundus image restoration

Restored images improve downstream tasks like vessel segmentation

The dataset and models are publicly available for research

Abstract

Ophthalmologists have used fundus images to screen and diagnose eye diseases. However, different equipments and ophthalmologists pose large variations to the quality of fundus images. Low-quality (LQ) degraded fundus images easily lead to uncertainty in clinical screening and generally increase the risk of misdiagnosis. Thus, real fundus image restoration is worth studying. Unfortunately, real clinical benchmark has not been explored for this task so far. In this paper, we investigate the real clinical fundus image restoration problem. Firstly, We establish a clinical dataset, Real Fundus (RF), including 120 low- and high-quality (HQ) image pairs. Then we propose a novel Transformer-based Generative Adversarial Network (RFormer) to restore the real degradation of clinical fundus images. The key component in our network is the Window-based Self-Attention Block (WSAB) which captures non-local self-similarity and long-range dependencies. To produce more visually pleasant results, a Transformer-based discriminator is introduced. Extensive experiments on our clinical benchmark show that the proposed RFormer significantly outperforms the state-of-the-art (SOTA) methods. In addition, experiments of downstream tasks such as vessel segmentation and optic disc/cup detection demonstrate that our proposed RFormer benefits clinical fundus image analysis and applications. The dataset, code, and models are publicly available at https://github.com/dengzhuo-AI/Real-Fundus