发表机构
Saint Louis University; MOVEJ Analytics; U.S. Naval Research Laboratory（圣路易斯大学; MOVEJ分析公司; 美国海军研究实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出DensePol密集角度偏振数据集及确定性扩散框架，提升RGB到偏振预测和表面法线估计精度。
AI 中文摘要
偏振视觉正受到越来越多的关注，因为它提供了关于场景形状、材质和反射的物理线索，而这些线索难以仅从RGB图像中恢复。因此，近期工作探索了直接从常规RGB图像预测偏振信息的方法；然而，这些方法的保真度强烈依赖于用于训练的偏振监督。现有的大多数数据集依赖于具有四个空间交错分析器方向的焦平面分割（DoFP）相机，这提供了有限的角度冗余，并引入了插值和瞬时视场误差。我们引入了DensePol，一个基于分时（DoT）采集的高冗余RGB-偏振数据集，以$1^\circ$间隔捕获180个全分辨率分析器方向。DensePol包含2,018对配对的RGB-偏振图像，并保留了角度测量值和拟合残差。密集角度采样显著提高了偏振稳定性，将AoLP偏差从$13.36^\circ$降低到$2.21^\circ$。我们进一步引入了一个确定性的基于扩散的RGB到偏振框架，具有循环AoLP表示和局部DoLP细化器。实验表明，偏振预测和下游表面法线估计均得到改善。该数据集和代码将公开提供。
英文摘要
Polarimetric vision is gaining increasing attention because it provides physical cues about scene shape, material, and reflection that are difficult to recover from RGB alone. Recent work has therefore explored predicting polarization directly from conventional RGB images; however, the fidelity of these methods strongly depends on the polarization supervision used for training. Most existing datasets rely on Division-of-Focal-Plane (DoFP) cameras with four spatially interleaved analyzer orientations, which provide limited angular redundancy and introduce interpolation and instantaneous-field-of-view errors. We introduce DensePol, a high-redundancy RGB--polarization dataset based on Division-of-Time (DoT) acquisition, capturing 180 full-resolution analyzer orientations at $1^\circ$ intervals. DensePol contains 2,018 paired RGB--polarization images with the angular measurements and fitting residuals retained. Dense angular sampling substantially improves polarization stability, reducing AoLP deviation from $13.36^\circ$ to $2.21^\circ$. We further introduce a deterministic diffusion-based RGB-to-polarization framework with cyclic AoLP representation and a local DoLP refiner. Experiments demonstrate improved polarization prediction and downstream surface-normal estimation. The dataset and code will be publicly available.
