Metraipolis › archive › dc_d99570e1da38
RIDE: Relocalization-Informed Depth Estimation with 3D Gaussian Splatting — arXiv:2609.11079
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.11079
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T06:35:58.718Z
- SHA-256 of the archived text
f389940cc7ce0e5f851bad6628b609f80b4a8c2b674914e07e7f9ecceb73ed62- Stable URL of this page
https://metraipolis.com/documento/dc_d99570e1da38
How to cite
RIDE: Relocalization-Informed Depth Estimation with 3D Gaussian Splatting — arXiv:2609.11079 — arXiv (en), https://arxiv.org/abs/2609.11079 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d99570e1da38 (Metraipolis archive dc_d99570e1da38, sha256 f389940cc7ce0e5f851bad6628b609f80b4a8c2b674914e07e7f9ecceb73ed62)
BibTeX
@misc{dcd99570e1da38,
title = {RIDE: Relocalization-Informed Depth Estimation with 3D Gaussian Splatting — arXiv:2609.11079},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.11079},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d99570e1da38; sha256 f389940cc7ce0e5f851bad6628b609f80b4a8c2b674914e07e7f9ecceb73ed62},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11079. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Render--match--PnP relocalization establishes correspondences between query image pixels and 3D map points for camera pose recovery, but their potential to support dense depth estimation is often overlooked. To exploit this geometric information, we present RIDE, which estimates dense metric depth from a robot's RGB stream. Given a metrically scaled 3D Gaussian Splatting (3DGS) model, RIDE combines sparse metric depth observations derived from PnP-RANSAC inlier correspondences with the geometric prior of a pretrained video-depth model. To handle uneven and intermittent observations, it integrates global and local depth correction with temporal memory, supporting depth estimation through short observation gaps after metric scale initialization. Trained on public RGB-D videos, RIDE is evaluated on robot sequences without fine tuning. Experiments show improved depth accuracy and temporal consistency over scale-only calibration, demonstrating how localization geometry can support both pose recovery and dense robot perception. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-11 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.11079 — 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 2026-10-16T06:10:18.212Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).