Metraipolis › archive › dc_29a73ffa4e15
RealOOB: A Definition-Consistent Real-World Oriented Occlusion Boundary Benchmark — arXiv:2608.30820
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.30820
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T09:59:41.585Z
- SHA-256 of the archived text
c92b2a149b4a7b635d2be5b558e0efc6f654c19d95a0fc5388cb476d0a57e80a- Stable URL of this page
https://metraipolis.com/documento/dc_29a73ffa4e15
How to cite
RealOOB: A Definition-Consistent Real-World Oriented Occlusion Boundary Benchmark — arXiv:2608.30820 — arXiv (en), https://arxiv.org/abs/2608.30820 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_29a73ffa4e15 (Metraipolis archive dc_29a73ffa4e15, sha256 c92b2a149b4a7b635d2be5b558e0efc6f654c19d95a0fc5388cb476d0a57e80a)
BibTeX
@misc{dc29a73ffa4e15,
title = {RealOOB: A Definition-Consistent Real-World Oriented Occlusion Boundary Benchmark — arXiv:2608.30820},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.30820},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_29a73ffa4e15; sha256 c92b2a149b4a7b635d2be5b558e0efc6f654c19d95a0fc5388cb476d0a57e80a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30820. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.30820 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T09:28:48.189Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).