Metraipolis › archive › dc_162db5be586b
GRIP: Gaussian Rendering as a Cross-Modal Bridge for Image-to-Point Cloud Registration — arXiv:2609.25966
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.25966
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T16:39:27.074Z
- SHA-256 of the archived text
58284a47b7c186b96cb9de3b5b2620f3ccdd60dab9485b3137531595b8b94cb3- Stable URL of this page
https://metraipolis.com/documento/dc_162db5be586b
How to cite
GRIP: Gaussian Rendering as a Cross-Modal Bridge for Image-to-Point Cloud Registration — arXiv:2609.25966 — arXiv (en), https://arxiv.org/abs/2609.25966 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_162db5be586b (Metraipolis archive dc_162db5be586b, sha256 58284a47b7c186b96cb9de3b5b2620f3ccdd60dab9485b3137531595b8b94cb3)
BibTeX
@misc{dc162db5be586b,
title = {GRIP: Gaussian Rendering as a Cross-Modal Bridge for Image-to-Point Cloud Registration — arXiv:2609.25966},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.25966},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_162db5be586b; sha256 58284a47b7c186b96cb9de3b5b2620f3ccdd60dab9485b3137531595b8b94cb3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25966. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
This paper introduces GRIP, a pose-conditioned refinement framework for pixel-to-point matching and 2D to 3D registration. Given an initial coarse pose estimate, GRIP addresses the structural mismatch between grid based image descriptors and unordered point cloud descriptors by softly rendering learned 3D point features onto the image grid through Gaussian feature splatting. The rendered point derived feature map is then fused with image features by a pixel aligned transformer, enabling visual semantic and geometric cues to interact in a shared 2D representation. The refined features are decoded and propagated to finer resolutions for dense correspondence estimation and final pose refinement. Experiments on RGB D Scenes V2 and 7 Scenes demonstrate state of the art inlier ratio and competitive registration recall, with stronger performance under stricter evaluation thresholds. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-23 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.25966 — 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 2026-10-08T15:56:18.165Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).