Fundus image enhancement through direct diffusion bridges

TL;DR

FD3 is a novel diffusion-based fundus image enhancement method that effectively improves low-quality retinal images affected by various degradations, outperforming previous approaches and applicable to real clinical data.

Contribution

The paper introduces FD3, a diffusion-based enhancement technique trained with a synthetic forward model incorporating ophthalmologist feedback, enabling superior enhancement of complex degradations in fundus images.

Findings

FD3 outperforms existing methods on synthetic degradations.

FD3 improves real clinical fundus images with cataracts or small pupils.

The approach is open-source for further research.

Abstract

We propose FD3, a fundus image enhancement method based on direct diffusion bridges, which can cope with a wide range of complex degradations, including haze, blur, noise, and shadow. We first propose a synthetic forward model through a human feedback loop with board-certified ophthalmologists for maximal quality improvement of low-quality in-vivo images. Using the proposed forward model, we train a robust and flexible diffusion-based image enhancement network that is highly effective as a stand-alone method, unlike previous diffusion model-based approaches which act only as a refiner on top of pre-trained models. Through extensive experiments, we show that FD3 establishes \add{superior quality} not only on synthetic degradations but also on in vivo studies with low-quality fundus photos taken from patients with cataracts or small pupils. To promote further research in this area, we open-source all our code and data used for this research at https://github.com/heeheee888/FD3