Metraipolis › archive › dc_480ba960dea1

Towards Generalizable 3D Anomaly Detection via Relational Inconsistency Modeling — arXiv:2609.35059

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35059
License (as archived)
CC0-1.0
Archived
2026-10-07T23:52:38.112Z
SHA-256 of the archived text
02efdea06951470edd1565bea636eba87741e2bd61dc52aaeb9a38ad4bbf3bd0
Stable URL of this page
https://metraipolis.com/documento/dc_480ba960dea1

How to cite

Towards Generalizable 3D Anomaly Detection via Relational Inconsistency Modeling — arXiv:2609.35059 — arXiv (en), https://arxiv.org/abs/2609.35059 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_480ba960dea1 (Metraipolis archive dc_480ba960dea1, sha256 02efdea06951470edd1565bea636eba87741e2bd61dc52aaeb9a38ad4bbf3bd0)
BibTeX
@misc{dc480ba960dea1,
  title = {Towards Generalizable 3D Anomaly Detection via Relational Inconsistency Modeling — arXiv:2609.35059},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35059},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_480ba960dea1; sha256 02efdea06951470edd1565bea636eba87741e2bd61dc52aaeb9a38ad4bbf3bd0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35059. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

3D anomaly detection (3DAD) aims to identify defective regions in point cloud data, serving as a critical component in industrial inspection systems. Existing methods are normality-centered -- learning the distribution of normal samples and treating deviations as anomalies -- without explicitly modeling what constitutes a defect. This leads to ambiguous decision boundaries with increased false positives and negatives, particularly in unified and cross-domain settings where diverse normal distributions further blur the boundaries. We propose a relational inconsistency modeling framework that characterizes defects as violations of geometric consistency among neighboring structures. Our approach learns category-agnostic defect cues through pseudo-anomalies designed as controlled relational violations, instantiated by two key modules: Edge-aware Graph Refinement (EGR) for encoding geometric relationships among local regions, and Cluster-Deviation Modeling (CDM) for identifying regions that are relationally incompatible within their structural peer group. Extensive experiments on Anomaly-ShapeNet and Real3D-AD demonstrate consistent improvements over prior state-of-the-art methods in both in-domain and cross-domain settings, validating the effectiveness of learning an explicit, relation-based defect criterion for 3D anomaly detection. Project page: this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.35059 — 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 2026-10-07T23:29:27.522Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).