Metraipolis › archive › dc_7cc54e22d3bc
MetricTrail: Revisiting the Power of Metric Depth and Local Optimization for Long-Sequence Streaming 3D Reconstruction — arXiv:2611.07555
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.07555
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-06T14:53:24.460Z
- SHA-256 of the archived text
5c3cfd92d3fd53c8818970c8fb24b7bde1cd4bd2cd5f74b008476f13d3ea39b6- Stable URL of this page
https://metraipolis.com/documento/dc_7cc54e22d3bc
How to cite
MetricTrail: Revisiting the Power of Metric Depth and Local Optimization for Long-Sequence Streaming 3D Reconstruction — arXiv:2611.07555 — arXiv (en), https://arxiv.org/abs/2611.07555 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7cc54e22d3bc (Metraipolis archive dc_7cc54e22d3bc, sha256 5c3cfd92d3fd53c8818970c8fb24b7bde1cd4bd2cd5f74b008476f13d3ea39b6)
BibTeX
@misc{dc7cc54e22d3bc,
title = {MetricTrail: Revisiting the Power of Metric Depth and Local Optimization for Long-Sequence Streaming 3D Reconstruction — arXiv:2611.07555},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.07555},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7cc54e22d3bc; sha256 5c3cfd92d3fd53c8818970c8fb24b7bde1cd4bd2cd5f74b008476f13d3ea39b6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07555. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We present MetricTrail, a streaming system for accurate camera motion estimation and dense reconstruction from long monocular videos. To keep inference efficient over long sequences, we revisit DPVO's sparse local estimator. We find that single-image metric depth substantially improves its trajectory accuracy, without retraining the correspondence network or enlarging the optimization window. Metric predictions initialize patch depths and remain as soft constraints during optimization. We further improve correspondence estimation through learned adapters that augment matching features and recurrent context with frozen DINOv3 representations. The correspondence estimator and adapters are trained on diverse short clips without additional long-sequence training. This modular design also allows the depth provider to be independently upgraded and supports supplied camera intrinsics and calibrated stereo observations without retraining. Under the reported RGB-only protocols, MetricTrail achieves the lowest average trajectory error among evaluated methods on KITTI, Oxford Spires, and VBR. Pairing the estimated poses with single-image depth predictions also produces strong dense reconstruction on indoor and outdoor benchmarks and coherent reconstructions of in-the-wild videos. With supplied intrinsics, the system processes KITTI-02 at 12.70 FPS with 3.21 GB peak GPU memory. 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/2611.07555 — 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 2026-11-06T14:25:42.611Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).