Saved in:
Bibliographic Details
Main Authors: Dong, Xuanzhao, Zhu, Wenhui, Chen, Xiwen, Wang, Hao, Li, Xin, Xiong, Yujian, Cheng, Jiajun, Wang, Zhipeng, Tang, Shao, Dumitrascu, Oana, Wang, Yalin
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.03806
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913005332070400
author Dong, Xuanzhao
Zhu, Wenhui
Chen, Xiwen
Wang, Hao
Li, Xin
Xiong, Yujian
Cheng, Jiajun
Wang, Zhipeng
Tang, Shao
Dumitrascu, Oana
Wang, Yalin
author_facet Dong, Xuanzhao
Zhu, Wenhui
Chen, Xiwen
Wang, Hao
Li, Xin
Xiong, Yujian
Cheng, Jiajun
Wang, Zhipeng
Tang, Shao
Dumitrascu, Oana
Wang, Yalin
contents Over the past decade, generative models have demonstrated success in enhancing fundus images. However, the evaluation of these models remains a challenge. A benchmark for fundus image enhancement is needed for three main reasons:(1) Conventional denoising metrics such as PSNR and SSIM fail to capture clinically relevant features, such as lesion preservation and vessel morphology consistency, limiting their applicability in real-world settings; (2) There is a lack of unified evaluation protocols that address both paired and unpaired enhancement methods, particularly those guided by clinical expertise; and (3) An evaluation framework should provide actionable insights to guide future advancements in clinically aligned enhancement models. To address these gaps, we introduce EyeBench-V2, a benchmark designed to bridge the gap between enhancement model performance and clinical utility. Our work offers three key contributions:(1) Multi-dimensional clinical-alignment through downstream evaluations: Beyond standard enhancement metrics, we assess performance across clinically meaningful tasks including vessel segmentation, diabetic retinopathy (DR) grading, generalization to unseen noise patterns, and lesion segmentation. (2) Expert-guided evaluation design: We curate a novel dataset enabling fair comparisons between paired and unpaired enhancement methods, accompanied by a structured manual assessment protocol by medical experts, which evaluates clinically critical aspects such as lesion structure alterations, background color shifts, and the introduction of artificial structures. (3) Actionable insights: Our benchmark provides a rigorous, task-oriented analysis of existing generative models, equipping clinical researchers with the evidence needed to make informed decisions, while also identifying limitations in current methods to inform the design of next-generation enhancement models.
format Preprint
id arxiv_https___arxiv_org_abs_2604_03806
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Bridging Restoration and Diagnosis: A Comprehensive Benchmark for Retinal Fundus Enhancement
Dong, Xuanzhao
Zhu, Wenhui
Chen, Xiwen
Wang, Hao
Li, Xin
Xiong, Yujian
Cheng, Jiajun
Wang, Zhipeng
Tang, Shao
Dumitrascu, Oana
Wang, Yalin
Computer Vision and Pattern Recognition
Over the past decade, generative models have demonstrated success in enhancing fundus images. However, the evaluation of these models remains a challenge. A benchmark for fundus image enhancement is needed for three main reasons:(1) Conventional denoising metrics such as PSNR and SSIM fail to capture clinically relevant features, such as lesion preservation and vessel morphology consistency, limiting their applicability in real-world settings; (2) There is a lack of unified evaluation protocols that address both paired and unpaired enhancement methods, particularly those guided by clinical expertise; and (3) An evaluation framework should provide actionable insights to guide future advancements in clinically aligned enhancement models. To address these gaps, we introduce EyeBench-V2, a benchmark designed to bridge the gap between enhancement model performance and clinical utility. Our work offers three key contributions:(1) Multi-dimensional clinical-alignment through downstream evaluations: Beyond standard enhancement metrics, we assess performance across clinically meaningful tasks including vessel segmentation, diabetic retinopathy (DR) grading, generalization to unseen noise patterns, and lesion segmentation. (2) Expert-guided evaluation design: We curate a novel dataset enabling fair comparisons between paired and unpaired enhancement methods, accompanied by a structured manual assessment protocol by medical experts, which evaluates clinically critical aspects such as lesion structure alterations, background color shifts, and the introduction of artificial structures. (3) Actionable insights: Our benchmark provides a rigorous, task-oriented analysis of existing generative models, equipping clinical researchers with the evidence needed to make informed decisions, while also identifying limitations in current methods to inform the design of next-generation enhancement models.
title Bridging Restoration and Diagnosis: A Comprehensive Benchmark for Retinal Fundus Enhancement
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.03806