Seeing Through the Glare: A Multi-Source Benchmark and Ocular-Adaptive Pixel MeanFlow for Eyeglass Reflection Removal

Computer Science > Computer Vision and Pattern Recognition arXiv:2610.10703 (cs) [Submitted on 7 Oct 2026] Title: Seeing Through the Glare: A Multi-Source Benchmark and Ocular-Adaptive Pixel MeanFlow for Eyeglass Reflection Removal.

计算机科学 > 计算机视觉与模式识别 arXiv:2610.10703 (cs) [提交于 2026 年 10 月 7 日] 标题：透过眩光：用于眼镜反光去除的多源基准测试与眼部自适应像素均值流。

Abstract: Eyeglass reflection removal is important across smartphone imaging, video conferencing, and other face-centric visual applications. The task is challenging because reflections range from mild photometric contamination to severe ocular occlusion, requiring selective correction and plausible reconstruction without altering identity or natural appearance.

摘要：眼镜反光去除在智能手机成像、视频会议以及其他以人脸为中心的视觉应用中具有重要意义。这项任务极具挑战性，因为反光范围从轻微的光度污染到严重的眼部遮挡不等，需要进行选择性校正和合理的重建，且不能改变身份特征或自然外观。

Existing datasets cover limited reflection conditions, constraining generalization to complex real-world scenes and systematic evaluation. We introduce \textbf{OcuBench}, a multi-source benchmark comprising 10,280 controllable synthetic pairs, 732 real-input pseudo-pairs, and 458 independent real-world test images, supporting both paired evaluation and assessment beyond generated supervision.

现有的数据集涵盖的反光条件有限，限制了其在复杂现实场景中的泛化能力和系统性评估。我们引入了 \textbf{OcuBench}，这是一个多源基准测试，包含 10,280 对可控合成对、732 对真实输入伪对以及 458 张独立的现实世界测试图像，支持配对评估以及超越生成式监督的评估。

We further propose \textbf{OcuFlow}, an ocular-adaptive pixel MeanFlow (pMF) framework for efficient, detail-preserving restoration. It combines geometry-adaptive representation with one-step pMF to focus reconstruction on reflection-obscured ocular regions, together with native-resolution frequency-preserving synthesis to retain reliable observed details.

我们进一步提出了 \textbf{OcuFlow}，这是一个用于高效、保留细节修复的眼部自适应像素均值流 (pMF) 框架。它将几何自适应表示与一步式 pMF 相结合，将重建重点放在被反光遮挡的眼部区域，并辅以原生分辨率的频率保持合成，以保留可靠的观测细节。

Experiments across diverse reflection conditions demonstrate that OcuFlow achieves consistent advantages in reflection removal quality, ocular fidelity, and efficiency. In a blind user study, it receives $67.32%$ of selections, $6.2\times$ the next-best share. Both the code and dataset will be released.

在多种反光条件下的实验表明，OcuFlow 在反光去除质量、眼部保真度和效率方面均表现出持续的优势。在一项盲测用户研究中，它获得了 $67.32%$ 的选择率，是排名第二的方案的 $6.2$ 倍。代码和数据集都将对外发布。