Metraipolis › archive › dc_de8a473789a7

Learning Global Camera Poses from Noisy View-Graphs for Structure from Motion — arXiv:2609.09491

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.09491
License (as archived)
CC0-1.0
Archived
2026-10-16T10:57:09.712Z
SHA-256 of the archived text
952d5ea744e06a306abb9e2808696fdbf8d3aeadab28c0493ef4d75f1b850348
Stable URL of this page
https://metraipolis.com/documento/dc_de8a473789a7

How to cite

Learning Global Camera Poses from Noisy View-Graphs for Structure from Motion — arXiv:2609.09491 — arXiv (en), https://arxiv.org/abs/2609.09491 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_de8a473789a7 (Metraipolis archive dc_de8a473789a7, sha256 952d5ea744e06a306abb9e2808696fdbf8d3aeadab28c0493ef4d75f1b850348)
BibTeX
@misc{dcde8a473789a7,
  title = {Learning Global Camera Poses from Noisy View-Graphs for Structure from Motion — arXiv:2609.09491},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.09491},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_de8a473789a7; sha256 952d5ea744e06a306abb9e2808696fdbf8d3aeadab28c0493ef4d75f1b850348},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09491. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Camera pose estimation is a key step in 3D reconstruction and view-synthesis pipelines. We present a deep, global Structure-from-Motion framework based on learned view-graph aggregation. Our method employs a permutation-equivariant, edge-conditioned graph neural network that takes noisy pairwise relative poses as input and outputs globally consistent camera extrinsics. The network is trained without ground-truth supervision, relying solely on a relative-pose consistency objective. This is followed by 3D point triangulation and robust bundle adjustment. Our approach is efficient, scalable to more than a thousand images, and robust to graph density. We evaluate our method on MegaDepth, 1DSfM, Strecha, and BlendedMVS. These experiments demonstrate that our method achieves superior rotation and translation accuracy compared to deep track-centric methods while registering more images across many scenes, and competitive results compared to state-of-the-art classical pipelines, while being much faster.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-10 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.09491 — 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 2026-10-16T10:02:34.308Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).