RealOOB: A Definition-Consistent Real-World Oriented Occlusion Boundary Benchmark

📄 arXiv: 2608.30820v1 📥 PDF

作者: Lintao Xu, Yinghao Wang, Chenchu Rong, Xuchong Qiu, Chaohui Wang

分类: cs.CV

发布日期: 2026-08-31

备注: 8 pages, 6 figures, 5 tables


💡 一句话要点

提出RealOOB基准以解决现有遮挡边界估计的不足

🎯 匹配领域: 支柱三:空间感知与语义 (Perception & Semantics)

关键词: 遮挡边界 深度估计 边缘检测 计算机视觉 场景理解 数据集 几何信息

📋 核心要点

  1. 现有的遮挡边界估计方法受限于监督信息的碎片化,导致性能不足。
  2. 本文提出RealOOB基准,提供426万条定义一致的遮挡边界标签,涵盖多种遮挡情况。
  3. 实验表明,现代边缘检测器在边界定位上表现良好,但方向预测仍然存在困难。

📝 摘要(中文)

遮挡边界(OBs)是对应于由于遮挡而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排序,为场景理解提供了几何驱动的中级线索。然而,现有的像素级OB估计进展有限,主要由于监督信息的碎片化。为此,本文提出了RealOOB,一个经过精心注释的真实世界基准,包含426万条定义一致、几何基础的OB标签,覆盖了物体间和自遮挡边界,并提供了有效的遮挡方向图。基于RealOOB,我们评估了四十种OB估计器和边缘检测器,结果显示现代边缘检测器在定位上表现良好,但方向预测仍然具有挑战性。

🔬 方法详解

问题定义:本文旨在解决现有遮挡边界估计方法在监督信息不足和标注不一致方面的痛点,导致的性能瓶颈。

核心思路:通过构建RealOOB基准,提供高质量的遮挡边界标签和遮挡方向图,从而为遮挡边界估计提供一致的监督信息。

技术框架:RealOOB基准包含数据收集、标注和验证三个主要阶段,确保标签的准确性和一致性,同时提供有效的遮挡方向信息。

关键创新:RealOOB的创新在于其定义一致性和几何基础的标签,解决了现有基准在覆盖范围和标注一致性方面的不足。

关键设计:在标签设计中,采用了有效的遮挡方向图,确保监督信息仅限于可可靠测量的像素,同时注重自遮挡和物体间遮挡的全面覆盖。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果显示,现代边缘检测器在遮挡边界定位上与传统OB方法表现相当,但在方向预测方面普遍存在困难。此外,强大的深度估计器在真实遮挡边界处的几何表现仍然不足,表明了该领域的进一步研究需求。

🎯 应用场景

该研究的潜在应用领域包括计算机视觉中的场景理解、自动驾驶、机器人导航等。通过提供高质量的遮挡边界数据,RealOOB可以帮助研究人员和工程师提升遮挡处理能力,从而在复杂环境中实现更高效的视觉感知和决策。未来,该基准可能推动低级视觉任务中的几何连续性和深度估计的研究进展。

📄 摘要(原文)

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.