Metraipolis › archive › dc_fb0ec00f7c61

GaugeDefect: Detecting Surface Anomalies by Curvature of Feature Transport — arXiv:2609.13282

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.13282
License (as archived): CC0-1.0
Archived: 2026-10-16T01:52:36.945Z
SHA-256 of the archived text: 17eaab02b3f375c0aae5341d6e6342ec919b16bb91101f1ea71f2d04861a0753
Stable URL of this page: https://metraipolis.com/documento/dc_fb0ec00f7c61

How to cite

GaugeDefect: Detecting Surface Anomalies by Curvature of Feature Transport — arXiv:2609.13282 — arXiv (en), https://arxiv.org/abs/2609.13282 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fb0ec00f7c61 (Metraipolis archive dc_fb0ec00f7c61, sha256 17eaab02b3f375c0aae5341d6e6342ec919b16bb91101f1ea71f2d04861a0753)

BibTeX

@misc{dcfb0ec00f7c61,
  title = {GaugeDefect: Detecting Surface Anomalies by Curvature of Feature Transport — arXiv:2609.13282},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.13282},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fb0ec00f7c61; sha256 17eaab02b3f375c0aae5341d6e6342ec919b16bb91101f1ea71f2d04861a0753},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13282. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Industrial anomaly localization has advanced rapidly with feature-based, reconstruction-based, and distillation-based methods. Most of these methods score a region by asking how unusual its local appearance or feature representation is with respect to normal training images. This is a strong and practical formulation. In this work, we study a complementary geometric cue for cases where an abnormal region may still contain locally plausible visual features. Thin scratches, small dents, and disrupted repeated patterns often do not make every local patch individually abnormal; instead, they disturb how nearby features vary and connect across the surface. We propose GaugeDefect, a geometric method for surface anomaly localization based on the curvature of feature transport. Given a feature lattice, we estimate a local feature frame at each node and compute orthogonal transports between neighboring frames. The accumulated transport around a small closed loop gives a holonomy matrix, whose deviation from identity measures feature-transport curvature. After calibration on normal training images, unusually large curvature indicates a local inconsistency in the feature field. The curvature here is not the physical curvature of the inspected object, but a representation-space measure of neighborhood inconsistency. This makes the method applicable to curved surfaces, textured materials, and non-planar industrial objects. Its main role is to improve localization of subtle surface disruptions, while often producing sharper responses near defect boundaries as a natural consequence of the curvature signal.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-15 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.13282 — 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 2026-10-16T01:25:23.494Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).