Metraipolis › archive › dc_c97cc282e9f5

Revisiting Local Context for Long-Horizon Streaming 3D Reconstruction — arXiv:2608.27529

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.27529
License (as archived)
CC0-1.0
Archived
2026-10-17T11:32:49.626Z
SHA-256 of the archived text
d7de59a0f642768d8f2a8f39dfa8704773ac87928d71bc2baf10065c56ab6339
Stable URL of this page
https://metraipolis.com/documento/dc_c97cc282e9f5

How to cite

Revisiting Local Context for Long-Horizon Streaming 3D Reconstruction — arXiv:2608.27529 — arXiv (en), https://arxiv.org/abs/2608.27529 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c97cc282e9f5 (Metraipolis archive dc_c97cc282e9f5, sha256 d7de59a0f642768d8f2a8f39dfa8704773ac87928d71bc2baf10065c56ab6339)
BibTeX
@misc{dcc97cc282e9f5,
  title = {Revisiting Local Context for Long-Horizon Streaming 3D Reconstruction — arXiv:2608.27529},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.27529},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c97cc282e9f5; sha256 d7de59a0f642768d8f2a8f39dfa8704773ac87928d71bc2baf10065c56ab6339},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27529. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Streaming 3D reconstruction from extremely long videos requires estimating camera motion and scene geometry online under bounded memory and computation. Early streaming models achieve causal, bounded-cost inference using finite context buffers or compact recurrent states, yet their estimates often deteriorate as sequences grow. Recent methods improve long-horizon stability by coupling short-range context with persistent or multi-level long-range memory. We pursue a different route: we keep the learned temporal state strictly local and formulate predictions whose targets remain independent of sequence length. We present ABot-Recon, a simple streaming model that caches KV features from only the preceding 11 frames. It predicts a point map in the current camera coordinate system together with an adjacent-frame relative pose. These predictions remain equivariant under changes of reference frame, and global poses and geometry are recovered through sequential composition. To reduce accumulated drift, a lightweight temporal refiner improves relative rotations using recent visual and motion context, while a composition-aware pose loss supervises multi-step pose composition. Extensive evaluations on challenging long-sequence benchmarks demonstrate the superior long-horizon performance of our local-context approach. On Oxford Spires, ABot-Recon achieves an ATE of 4.35 m and an RPE-R of $0.12^\circ$, reducing both errors by approximately 40\% relative to the best prior results.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-31 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.27529 — 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 2026-10-17T11:10:05.252Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).