Metraipolis › archive › dc_d5034243f15c

SceneBound: How Much Should a Streaming 3D Reconstruction Model Remember? — arXiv:2611.00756

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00756
License (as archived)
CC0-1.0
Archived
2026-11-03T11:40:45.697Z
SHA-256 of the archived text
865203e8ef4f8c8ae8138d2b20ea92c2d61669a57086248afd12a66f438c4e30
Stable URL of this page
https://metraipolis.com/documento/dc_d5034243f15c

How to cite

SceneBound: How Much Should a Streaming 3D Reconstruction Model Remember? — arXiv:2611.00756 — arXiv (en), https://arxiv.org/abs/2611.00756 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d5034243f15c (Metraipolis archive dc_d5034243f15c, sha256 865203e8ef4f8c8ae8138d2b20ea92c2d61669a57086248afd12a66f438c4e30)
BibTeX
@misc{dcd5034243f15c,
  title = {SceneBound: How Much Should a Streaming 3D Reconstruction Model Remember? — arXiv:2611.00756},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00756},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d5034243f15c; sha256 865203e8ef4f8c8ae8138d2b20ea92c2d61669a57086248afd12a66f438c4e30},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00756. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Streaming 3D reconstruction models keep past video frames in a recurrent state, fast weights from test-time training, or a key-value (KV) cache. Each written frame shifts the coordinate frame of later cameras or occupies GPU memory. Training-free rules decide what to write from a signal of the current frame. How much they write accounts for their mean accuracy: spending the update budget of a gate at uniformly spaced frames, with no signal, matches nine published gates, and the budget bounds the drift of the state wherever the writes fall. We propose SceneBound, a training-free rule that writes a frame only when its predicted camera pose lies at least a fixed radius from every stored keyframe. Its keyframe count stays within a constant factor of the covering number of the visited poses, the fewest views that keep a keyframe near every camera, so the count grows with the places visited and stays flat when the camera returns. In large scenes, SceneBound closes a submap once decoding its first frame again reveals drift. SceneBound uses one radius across four released models and three memory types. In the recurrent state of CUT3R and the KV cache of StreamVGGT, it achieves the lowest mean trajectory error among the published training-free rules we evaluate, in one pass and over nine passes of a scene, where its keyframes grow by 3% to 6%.

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/2611.00756 — 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 2026-11-03T11:06:37.444Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).