Metraipolis › archive › dc_61498bf5d207
NaCR: Visual Localization via NeRF-aided Camera Ray Regression — arXiv:2609.25907
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.25907
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T16:39:25.261Z
- SHA-256 of the archived text
dfb077d1b8ee6c91888c6a3c5c9118b1754b94e7ba2907ae16c63904eaa8d0c2- Stable URL of this page
https://metraipolis.com/documento/dc_61498bf5d207
How to cite
NaCR: Visual Localization via NeRF-aided Camera Ray Regression — arXiv:2609.25907 — arXiv (en), https://arxiv.org/abs/2609.25907 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_61498bf5d207 (Metraipolis archive dc_61498bf5d207, sha256 dfb077d1b8ee6c91888c6a3c5c9118b1754b94e7ba2907ae16c63904eaa8d0c2)
BibTeX
@misc{dc61498bf5d207,
title = {NaCR: Visual Localization via NeRF-aided Camera Ray Regression — arXiv:2609.25907},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.25907},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_61498bf5d207; sha256 dfb077d1b8ee6c91888c6a3c5c9118b1754b94e7ba2907ae16c63904eaa8d0c2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25907. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Visual localization (VL) is a fundamental technology for vision applications such as virtual reality. Recently, a novel VL paradigm, Camera Ray Regression (CRR), has emerged, which maps 2D image patches to 3D camera rays, but its accuracy is limited. To improve CRR accuracy, we notice a compelling duality: the inverse of this mapping is inherently performed by the novel view synthesis model, \ie, Neural Radiance Fields (NeRF). While NeRF renders image patches from camera rays via differentiable ray marching, CRR predicts the rays from image patches. Motivated by this complementary relationship, we propose NeRF-aided Camera Ray Regression (NaCR), a unified framework that seamlessly bridges NeRF and CRR at the ray level. First, NaCR incorporates three simple yet effective enhancements into the CRR baseline. Second, leveraging a pre-trained NeRF, NaCR augments the training data by synthesizing novel views tailored for efficient, patch-level consumption. Finally, exploiting the differentiability of NeRF, NaCR forms a closed-loop supervision pipeline where photometric rendering errors are back-propagated to optimize the predicted camera rays. To ensure stable convergence within the highly non-convex image space, we introduce a two-stage training curriculum. Extensive experiments across indoor and outdoor benchmarks demonstrate that NaCR achieves competitive accuracy. Comprehensive ablation studies validate the efficacy of each proposed component. 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/2609.25907 — 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 2026-10-08T15:56:18.159Z 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).