# Fundus image enhancement through direct diffusion bridges

arXiv: https://arxiv.org/abs/2409.12377 · HTML: https://mlsanity.com/paper/2409.12377/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 24 of its 55 references that are in the map.
- First posted on arXiv 19 Sep 2024.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 24 of 24)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Diffusion Posterior Sampling for General Noisy Inverse Problems](https://mlsanity.com/paper/2209.14687/) (2022)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Denoising Diffusion Restoration Models](https://mlsanity.com/paper/2201.11793/) (2022)
- [Pseudo Numerical Methods for Diffusion Models on Manifolds](https://mlsanity.com/paper/2202.09778/) (2022)
- [The Perception-Distortion Tradeoff](https://mlsanity.com/paper/1711.06077/) (2017)
- [Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction](https://mlsanity.com/paper/2112.05146/) (2021)
- [Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restoration](https://mlsanity.com/paper/2303.11435/) (2023)
- [Parallel Diffusion Models of Operator and Image for Blind Inverse Problems](https://mlsanity.com/paper/2211.10656/) (2022)
- [Direct Diffusion Bridge using Data Consistency for Inverse Problems](https://mlsanity.com/paper/2305.19809/) (2023)
- [GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restoration](https://mlsanity.com/paper/2301.12686/) (2023)
- [Evaluation of Retinal Image Quality Assessment Networks in Different Color-spaces](https://mlsanity.com/paper/1907.05345/) (2019)
- [IterNet: Retinal Image Segmentation Utilizing Structural Redundancy in Vessel Networks](https://mlsanity.com/paper/1912.05763/) (2019)
- [An Annotation-free Restoration Network for Cataractous Fundus Images](https://mlsanity.com/paper/2203.07737/) (2022)
- [Degradation-invariant Enhancement of Fundus Images via Pyramid Constraint Network](https://mlsanity.com/paper/2210.09606/) (2022)
- [Structure-consistent Restoration Network for Cataract Fundus Image Enhancement](https://mlsanity.com/paper/2206.04684/) (2022)
- [Structure-preserving Guided Retinal Image Filtering and Its Application for Optic Disc Analysis](https://mlsanity.com/paper/1805.06625/) (2018)
- [Learning Enhancement From Degradation: A Diffusion Model For Fundus Image Enhancement](https://mlsanity.com/paper/2303.04603/) (2023)

## Abstract (arXiv)

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 addsuperior 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