发表机构
UGE; ENPC; INFRES, Télécom Paris, IP Paris; MathMagic; Aptiv（法国国立高等工程技术大学（UGE）; 法国国立路桥学校（ENPC）; 巴黎理工学院电信学院（INFRES）、巴黎文理研究大学（IP Paris）; MathMagic公司; 安波福公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对现有OB基准的缺陷，构建含426万一致OB标签的RealOOB基准，评估多类模型后发现遮挡推理存在差距，该基准将助力低级视觉领域研究。
AI 中文摘要
遮挡边界（OBs）是对应于由遮挡导致的表面可见性不连续的像素级图像边界。通过精确的边界定位和遮挡方向，OBs编码了局部表面布局和深度顺序，为场景理解提供了几何驱动的中级线索。然而，像素级OB估计的进展受到碎片化监督的限制：现有基准通常存在覆盖范围有限、类别特定设计、缺少自遮挡注释或注释定义不一致的问题。与此同时，现代边缘检测器和单目深度估计器已成为强大的边界和几何预测器，但它们与定义一致的OBs的关系仍未得到充分探索。我们引入RealOOB，这是一个精心注释的真实世界基准，包含426万个定义一致、基于几何的OB标签，涵盖对象间和自遮挡边界，以及有效性感知的遮挡方向图，该图将监督限制在跨边界深度顺序可可靠测量的像素上。基于RealOOB，我们评估了40个OB估计器和边缘检测器，以及6个单目深度估计器。我们的评估揭示了遮挡推理方面的明显差距：现代边缘检测器在定位方面与OB方法表现相当，而方向预测对所有评估方法来说仍然具有挑战性。同时，即使是强大的深度估计器也常常无法在真实OB处表现出可测量的几何特征。我们认为RealOOB为OB估计领域提供了强大的参考基准，并为更广泛的低级视觉任务中的深度不连续性和几何保真度评估提供了真实世界的测试平台。数据集和代码将被发布。
英文摘要
Occlusion boundaries (OBs) are pixel-level image boundaries corresponding to surface visibility discontinuities caused by occlusion. Through precise boundary localisation and occlusion orientation, OBs encode local surface layout and depth ordering, providing geometry-driven mid-level cues for scene understanding. However, progress in pixel-level OB estimation has been limited by fragmented supervision: Existing benchmarks often suffer from limited coverage, category-specific designs, missing self-occlusion annotations, or inconsistent annotation definitions. Meanwhile, modern edge detectors and monocular depth estimators have become strong boundary and geometry predictors, yet their relationship to definition-consistent OBs remains underexplored. We introduce RealOOB, a carefully annotated real-world benchmark with 4.26M definition-consistent, geometry-grounded OB labels covering both inter-object and self-occlusion boundaries, together with validity-aware occlusion-orientation maps that restrict supervision to pixels whose cross-boundary depth ordering is reliably measurable. Based on RealOOB, we evaluate forty OB estimators and edge detectors alongside six monocular depth estimators. Our evaluation reveals a clear gap in occlusion reasoning: modern edge detectors perform competitively with OB methods in localisation, whereas orientation prediction remains challenging for all evaluated methods. Meanwhile, even strong depth estimators often fail to exhibit measurable geometry at true OBs. We believe RealOOB provides a strong reference benchmark for the OB estimation community and a real-world testbed for assessing depth discontinuities and geometry fidelity in broader low-level vision tasks. Dataset and code will be released.
Comments8 pages, 6 figures, 5 tables
