Metraipolis › archive › dc_7e2d82736e52

Subspace Representations for Synthetic-to-Real Transfer in 3-D Surface Inspection — arXiv:2611.02744

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.02744
License (as archived)
CC0-1.0
Archived
2026-11-03T11:25:25.982Z
SHA-256 of the archived text
bb9d5e1e4ca9f64d1f50e064c1f17571fd388c3d732b018ff1474e6384845d19
Stable URL of this page
https://metraipolis.com/documento/dc_7e2d82736e52

How to cite

Subspace Representations for Synthetic-to-Real Transfer in 3-D Surface Inspection — arXiv:2611.02744 — arXiv (en), https://arxiv.org/abs/2611.02744 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7e2d82736e52 (Metraipolis archive dc_7e2d82736e52, sha256 bb9d5e1e4ca9f64d1f50e064c1f17571fd388c3d732b018ff1474e6384845d19)
BibTeX
@misc{dc7e2d82736e52,
  title = {Subspace Representations for Synthetic-to-Real Transfer in 3-D Surface Inspection — arXiv:2611.02744},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02744},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7e2d82736e52; sha256 bb9d5e1e4ca9f64d1f50e064c1f17571fd388c3d732b018ff1474e6384845d19},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02744. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper studies what subspace representations contribute to synthetic-to-real transfer in 3-D surface inspection, where models learn from synthetic defects and the only real data before deployment are scans of good parts. We use three classical constructions as instruments: the nearest-subspace classifier, one-class template subspaces and the generalized difference subspace (GDS). On 1,197 MVTec 3D-AD scans without target annotation we find that every decision rule ranks real defects at a similar window AUC, that image-level detection stays at chance, and that no rule keeps its in-domain threshold. We show that the margin of a nearest-subspace rule moves by at most the part of the feature shift outside its class subspaces, and that this leakage, measured from unlabeled good scans, bounds the displacement observed on unseen scans. On 597 Real3D-AD objects, a one-class subspace of registered templates evaluated at every location on frozen features reaches point AUROC 0.957 on pre-registered scans and a category-mean object AUROC of 78 to 81 with no training on the benchmark. Our results suggest that a subspace helps under shift in proportion to the shift it spans, and that in reference-based inspection the reference and its registration matter more than the subspace.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.02744 — 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 2026-11-03T11:02:37.882Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).