Metraipolis › archive › dc_33032df49faf

Remember, Revisit, Revise: Scaffold Memory for Long-Horizon 3D Geometry — arXiv:2610.19674

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.19674
License (as archived)
CC0-1.0
Archived
2026-10-15T21:56:24.356Z
SHA-256 of the archived text
b713f356bd39e6817f61c7060d8982ae08ffa384940ee63d4450f775b93fef3d
Stable URL of this page
https://metraipolis.com/documento/dc_33032df49faf

How to cite

Remember, Revisit, Revise: Scaffold Memory for Long-Horizon 3D Geometry — arXiv:2610.19674 — arXiv (en), https://arxiv.org/abs/2610.19674 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_33032df49faf (Metraipolis archive dc_33032df49faf, sha256 b713f356bd39e6817f61c7060d8982ae08ffa384940ee63d4450f775b93fef3d)
BibTeX
@misc{dc33032df49faf,
  title = {Remember, Revisit, Revise: Scaffold Memory for Long-Horizon 3D Geometry — arXiv:2610.19674},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19674},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_33032df49faf; sha256 b713f356bd39e6817f61c7060d8982ae08ffa384940ee63d4450f775b93fef3d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19674. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Geometry foundation models estimate camera poses and 3D scene structure from video sequences, but maintaining consistent reconstructions over long horizons remains challenging. Feed-forward models process long sequences as independent, fixed-length frame windows and align their predictions, causing pose and reconstruction errors to accumulate across windows. Streaming models retain information from past frames to inform future predictions, but cannot revise earlier estimates when later observations reveal errors. To address this, we introduce Scaffold MemOry for Revision (SMORE), a framework equipping frozen geometry foundation models with a revisable external memory for long-horizon inference. Inspired by hippocampal associative memory in biological brains, which links spatial context with sensory experience, SMORE associates where an observer is with what it observes, enabling past observations to be stored, retrieved, verified against new evidence, and revised when inconsistencies are detected. We evaluate SMORE with eight competitive geometry models on five datasets spanning camera pose estimation, multi-view depth estimation, 3D point-cloud reconstruction, simultaneous localization and mapping (SLAM), and novel view synthesis. Across all evaluated models, SMORE consistently improves long-sequence pose estimation, reduces multi-view depth error by up to 58%, reduces Chamfer distance for 3D point-cloud reconstruction by up to 43%, and achieves average trajectory error as low as 2.9 cm in long-horizon SLAM. By retaining corrected poses and observations, SMORE further improves the fidelity and spatial consistency of large-scale 3D scene reconstruction. These results establish revisable external memory as a flexible interface for extending pretrained geometry models beyond fixed-context prediction toward iterative, error-correcting inference over long visual sequences.

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/2610.19674 — 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 2026-10-15T21:38:29.488Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).