Metraipolis › archive › dc_24ab74ecb78b
GS-CPE: Unified 6-Degree-of-Freedom Camera Pose Estimation via 3D Gaussian Splatting — arXiv:2608.10938
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.10938
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T06:30:33.018Z
- SHA-256 of the archived text
8f2689ff121e569349fd7b9f7a9feda26dc2e7f218353f41d7244eaf1b57045e- Stable URL of this page
https://metraipolis.com/documento/dc_24ab74ecb78b
How to cite
GS-CPE: Unified 6-Degree-of-Freedom Camera Pose Estimation via 3D Gaussian Splatting — arXiv:2608.10938 — arXiv (en), https://arxiv.org/abs/2608.10938 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_24ab74ecb78b (Metraipolis archive dc_24ab74ecb78b, sha256 8f2689ff121e569349fd7b9f7a9feda26dc2e7f218353f41d7244eaf1b57045e)
BibTeX
@misc{dc24ab74ecb78b,
title = {GS-CPE: Unified 6-Degree-of-Freedom Camera Pose Estimation via 3D Gaussian Splatting — arXiv:2608.10938},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.10938},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_24ab74ecb78b; sha256 8f2689ff121e569349fd7b9f7a9feda26dc2e7f218353f41d7244eaf1b57045e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10938. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Despite substantial progress in visual localization, from scene coordinate regression to direct camera pose regression, achieving both robust generalization and high accuracy remain challenging. This study introduces GS-CPE (Gaussian Splatting based Camera Pose Estimation), a coarse-to-fine framework for 6-DoF camera pose estimation that unifies geometry-based coarse pose estimation with robust 3D Gaussian Splatting (3DGS) warping based pose refinement. GS-CPE first estimates a coarse pose via retrieval-guided geometric pose estimation on a 3DGS scene representation, then refines it by minimizing a visibility aware masked RGB warping objective in a multi-scale optimization framework, with adaptive re-rendering. Extensive experiments on indoor and outdoor benchmarks including 7Scenes, Cambridge Landmarks, FAST-LIVO2 datasets, and a custom dataset demonstrate state-of-the-art performance, consistently outperforming in both accuracy and generalization. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-12 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.10938 — 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 2026-10-19T06:25:27.300Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).