Metraipolis › archive › dc_aa01040e40f2

Why 3D Reconstruction Breaks Down on Under-Ice AUV Video, and How to Predict It — arXiv:2610.19993

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.19993
License (as archived)
CC0-1.0
Archived
2026-10-15T21:56:49.148Z
SHA-256 of the archived text
2e1e84e6fa4185d580b495db896fd0ffbd3bc31b016198a6da301e49269a7489
Stable URL of this page
https://metraipolis.com/documento/dc_aa01040e40f2

How to cite

Why 3D Reconstruction Breaks Down on Under-Ice AUV Video, and How to Predict It — arXiv:2610.19993 — arXiv (en), https://arxiv.org/abs/2610.19993 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aa01040e40f2 (Metraipolis archive dc_aa01040e40f2, sha256 2e1e84e6fa4185d580b495db896fd0ffbd3bc31b016198a6da301e49269a7489)
BibTeX
@misc{dcaa01040e40f2,
  title = {Why 3D Reconstruction Breaks Down on Under-Ice AUV Video, and How to Predict It — arXiv:2610.19993},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19993},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aa01040e40f2; sha256 2e1e84e6fa4185d580b495db896fd0ffbd3bc31b016198a6da301e49269a7489},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19993. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reconstruction of 3D structures using under-ice AUV video footage has been inaccurate, although it is not certain whether this is due to shortcomings in the methods or an inherent deficiency of the capture system. We test four different models for reconstruction on the same Antarctic under-ice AUV video (Icefin, Kamb Ice Stream): classical feature matching SfM, differentiable photometric splatting, volumetric depth fusion, and a pose-free feed-forward foundation model. All four fail, each in a distinct way: near-total registration yielding almost no structure, geometrically broken output despite healthy photometric metrics, a persistent coverage artifact, and unstable cross-chunk scale. We show that all four are consistent with the same capture regime, a small camera-baseline-to-scene-depth ratio. Following our analysis, we propose a detection system that flags this type of failure in minutes, rather than hours of wasted compute.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2610.19993 — 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 2026-10-15T21:38:29.513Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).