无需配对数据，用扩散模型自动修复手持眼底图的模糊与光斑
Diffusion Autoencoder for Unsupervised Artifact Restoration in Handheld Fundus Images
- 用扩散自编码器融合上下文编码，无监督学习图像修复特征
- 在未见数据上诊断准确率达81.17%，跨多种伪影条件有效
- 适合缺乏标注数据的眼底影像修复，尤其手持设备场景
手持眼底成像设备使眼科诊断更便捷、高效且成本更低。然而，此类设备拍摄的图像常受闪光反射、曝光不均和运动模糊等伪影影响，降低图像质量并阻碍后续分析。尽管生成模型在图像修复中表现良好，但多数依赖成对监督或预设伪影结构，难以适应手持眼底图像中常见的非结构化退化。为此，我们提出一种无监督扩散自编码器，将上下文编码器融入去噪过程，学习语义有意义的表示以实现伪影修复。模型仅在高质量台式眼底图像上训练，即可推断恢复受伪影影响的手持采集图像。通过定量与定性评估验证，该方法在未见数据集及多种伪影条件下，使诊断准确率提升至81.17%。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。