Metraipolis › archive › dc_ff2bcda3bdaa

PADFormer: Pose-agnostic Anomaly Detection from Sparse View Images — arXiv:2608.04210

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.04210
License (as archived): CC0-1.0
Archived: 2026-10-31T11:47:47.808Z
SHA-256 of the archived text: a5ea19cb6bc184b7921ec870eea8f5c470e6db38410244896e3f057f2b796fb6
Stable URL of this page: https://metraipolis.com/documento/dc_ff2bcda3bdaa

How to cite

PADFormer: Pose-agnostic Anomaly Detection from Sparse View Images — arXiv:2608.04210 — arXiv (en), https://arxiv.org/abs/2608.04210 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff2bcda3bdaa (Metraipolis archive dc_ff2bcda3bdaa, sha256 a5ea19cb6bc184b7921ec870eea8f5c470e6db38410244896e3f057f2b796fb6)

BibTeX

@misc{dcff2bcda3bdaa,
  title = {PADFormer: Pose-agnostic Anomaly Detection from Sparse View Images — arXiv:2608.04210},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04210},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff2bcda3bdaa; sha256 a5ea19cb6bc184b7921ec870eea8f5c470e6db38410244896e3f057f2b796fb6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04210. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Pose-agnostic Anomaly Detection (PAD) remains challenging as anomalies can appear under arbitrary viewpoints, requiring methods to handle significant pose variations. Existing approaches rely on complex 3D reconstruction, which are computationally expensive and require extensive multi-view data. We propose PADFormer, a novel image-space approach that leverages Vision Transformer (ViT) to directly reconstruct anomaly-free versions of query images while preserving pose information. Our key insight is to adapt cross-view masked reconstruction for anomaly detection through training exclusively on normal data, combined with dynamic patch selection and spatial alignment mechanisms that enable effective learning from sparse reference views under significant pose variations. During inference, we perform multiple forward passes with different masking patterns to generate an ensemble of anomaly-free reconstructions, ensuring comprehensive coverage of the query image. Anomalies are detected by comparing these reconstructions with the query image. PADFormer achieves state-of-the-art results on the PAD benchmark while maintaining comparable performance on classic few-shot anomaly detection (FSAD) tasks, demonstrating superior efficiency and generalization without requiring 3D reconstruction.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-06 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.04210 — 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 2026-10-31T11:37:40.650Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).