透过眩光：用于眼镜反射去除的多源基准测试集与眼自适应像素均值流
Seeing Through the Glare: A Multi-Source Benchmark and Ocular-Adaptive Pixel MeanFlow for Eyeglass Reflection Removal
浏览论文内容
中文总结 AI 辅助
针对眼镜反射去除任务，提出多源基准OcuBench与眼自适应像素均值流框架OcuFlow，实验显示OcuFlow在反射去除质量等方面优势显著，盲选支持率达67.32%
中文摘要 AI 辅助
眼镜反射去除在智能手机成像、视频会议及其他以人脸为中心的视觉应用中至关重要。该任务颇具挑战性，因为反射程度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重建，同时不改变人物身份或自然外观。现有数据集涵盖的反射条件有限，限制了其对复杂真实场景的泛化能力和系统评估。我们推出OcuBench，这是一个多源基准测试集，包含10280对可控合成样本、732对真实输入伪样本以及458张独立真实世界测试图像，支持配对评估和超越生成式监督的评估。我们还提出OcuFlow，一种眼自适应像素均值流（pMF）框架，用于高效、保留细节的图像恢复。它将几何自适应表示与单步pMF相结合，聚焦于被反射遮挡的眼部区域的重建，同时采用原生分辨率、保留频率的合成以保留可靠的观测细节。在不同反射条件下的实验表明，OcuFlow在反射去除质量、眼部保真度和效率方面均取得持续优势。在盲用户研究中，它获得了67.32%的选择率，是次优选择份额的6.2倍。代码和数据集均将发布。
英文摘要
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. 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. 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. 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.
