Metraipolis › archive › dc_cf26f03255d4
Trainspotting: Learning Object-Centric 3D Reconstruction from Found Photos — arXiv:2611.06849
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.06849
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:30:14.264Z
- SHA-256 of the archived text
edb672640bcf8c9816578f8593f35fb46bb98eac7d032cd6a4299058c6a53dc6- Stable URL of this page
https://metraipolis.com/documento/dc_cf26f03255d4
How to cite
Trainspotting: Learning Object-Centric 3D Reconstruction from Found Photos — arXiv:2611.06849 — arXiv (en), https://arxiv.org/abs/2611.06849 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cf26f03255d4 (Metraipolis archive dc_cf26f03255d4, sha256 edb672640bcf8c9816578f8593f35fb46bb98eac7d032cd6a4299058c6a53dc6)
BibTeX
@misc{dccf26f03255d4,
title = {Trainspotting: Learning Object-Centric 3D Reconstruction from Found Photos — arXiv:2611.06849},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.06849},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cf26f03255d4; sha256 edb672640bcf8c9816578f8593f35fb46bb98eac7d032cd6a4299058c6a53dc6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06849. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
State-of-the-art feedforward reconstruction models perform poorly on in-the-wild object-centric photo collections. They are trained largely on single-session object captures whose images vary in viewpoint while the object and its environment remain nearly fixed. Public photo archives contain a different form of multi-view data. They hold found photos of the same object or design: photos taken independently by many people across years, environments, cameras, and sometimes physical units. In this work, we introduce Trainspotting, a dataset of 12,068 objects and 311,886 photos from Wikimedia Commons. We reconstruct each object to recover camera poses, multi-view stereo depth, and object masks. We categorize the objects into three regimes: objects fixed at one site, objects that move between sites, and designs shared by many physical units. Evaluating recent feedforward reconstruction models on Trainspotting shows that they fail most severely in the last two regimes. Fine-tuning VGGT-$\Omega$ on Trainspotting significantly improves camera pose, depth, and 3D geometry on held-out objects. We observe similar improvements on the independent NAVI in-the-wild benchmark, which contains photos of each object in different environments. Performance on conventional benchmarks remains largely unchanged. 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). Pagina del lavoro: https://arxiv.org/abs/2611.06849 — 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 2026-11-05T18:19:49.066Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).