RealOOB: A Definition-Consistent Real-World Oriented Occlusion Boundary Benchmark
2026-08-31 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors study occlusion boundaries, which are edges in images where one surface blocks another, showing depth changes. They created a new, large dataset called RealOOB with detailed and consistent labels for these boundaries in real-world images. By testing many edge and depth detection methods on this dataset, they found that while current methods can find the edges well, they struggle to correctly identify the direction of occlusion or depth order. The authors suggest their dataset will help improve and evaluate how well computer vision methods understand 3D geometry from images.
Occlusion boundariesSurface visibilityDepth orderingEdge detectionMonocular depth estimationBenchmark datasetOcclusion orientationGeometry cuesSelf-occlusionComputer vision
Authors
Lintao Xu, Yinghao Wang, Chenchu Rong, Xuchong Qiu, Chaohui Wang
Abstract
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.