# Diffusion Autoencoder for Unsupervised Artifact Restoration in Handheld Fundus Images

arXiv: https://arxiv.org/abs/2604.15723 · HTML: https://mlsanity.com/paper/2604.15723/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 18 references that are in the map.
- First posted on arXiv 17 Apr 2026.

## Builds on (most cited first, 7 of 7)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Diffusion Autoencoders: Toward a Meaningful and Decodable Representation](https://mlsanity.com/paper/2111.15640/) (2021)
- [EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning](https://mlsanity.com/paper/1901.00212/) (2019)
- [Shift-Net: Image Inpainting via Deep Feature Rearrangement](https://mlsanity.com/paper/1801.09392/) (2018)
- [MISF: Multi-level Interactive Siamese Filtering for High-Fidelity Image Inpainting](https://mlsanity.com/paper/2203.06304/) (2022)
- [PVBM: A Python Vasculature Biomarker Toolbox Based On Retinal Blood Vessel Segmentation](https://mlsanity.com/paper/2208.00392/) (2022)
- [PosDiffAE: Position-aware Diffusion Auto-encoder For High-Resolution Brain Tissue Classification Incorporating Artifact Restoration](https://mlsanity.com/paper/2507.02405/) (2025)

## Abstract (arXiv)

The advent of handheld fundus imaging devices has made ophthalmologic diagnosis and disease screening more accessible, efficient, and cost-effective. However, images captured from these setups often suffer from artifacts such as flash reflections, exposure variations, and motion-induced blur, which degrade image quality and hinder downstream analysis. While generative models have been effective in image restoration, most depend on paired supervision or predefined artifact structures, making them less adaptable to unstructured degradations commonly observed in handheld fundus images. To address this, we propose an unsupervised diffusion autoencoder that integrates a context encoder with the denoising process to learn semantically meaningful representations for artifact restoration. The model is trained only on high-quality table-top fundus images and infers to restore artifact-affected handheld acquisitions. We validate the restorations through quantitative and qualitative evaluations, and have shown that diagnostic accuracy increases to 81.17% on an unseen dataset and multiple artifact conditions