Metraipolis › archive › dc_1d45f1abe33b
AffineGS: Unlocking Accurate Geometry in 3DGS via Spatially Varying Affine Rectification — arXiv:2611.07709
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.07709
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-06T14:53:31.681Z
- SHA-256 of the archived text
4e3dc40b13cbe357b6dcfea9eb7e9a559a6c9d4a8548a78413777ba1aa28902d- Stable URL of this page
https://metraipolis.com/documento/dc_1d45f1abe33b
How to cite
AffineGS: Unlocking Accurate Geometry in 3DGS via Spatially Varying Affine Rectification — arXiv:2611.07709 — arXiv (en), https://arxiv.org/abs/2611.07709 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1d45f1abe33b (Metraipolis archive dc_1d45f1abe33b, sha256 4e3dc40b13cbe357b6dcfea9eb7e9a559a6c9d4a8548a78413777ba1aa28902d)
BibTeX
@misc{dc1d45f1abe33b,
title = {AffineGS: Unlocking Accurate Geometry in 3DGS via Spatially Varying Affine Rectification — arXiv:2611.07709},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.07709},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1d45f1abe33b; sha256 4e3dc40b13cbe357b6dcfea9eb7e9a559a6c9d4a8548a78413777ba1aa28902d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07709. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
3D Gaussian Splatting (3DGS) has become the leading approach for photorealistic novel view synthesis, yet its geometric accuracy lags behind its visual quality. Existing depth-guided methods attempt to resolve this by regularizing the optimization with monocular depth priors, typically using a single global scale-and-shift alignment. Crucially, we discover a fundamental flaw in this assumption: modern monocular depth networks systematically exhibit region-dependent, piecewise-linear distortions. This discovery invalidates standard global alignment strategies, which warp scene geometry by enforcing a single transform. To address this, we introduce a spatially varying affine rectification model that corrects monocular disparity into consistent metric depth using regionally smooth, edge-aware fields. We further derive a normal-aware regularizer that uses spatial gradients to couple the rectified disparity with 3DGS depth and normals. Across diverse experimental settings, our sensor-free method shows strong photometric quality of Gaussian Splatting while substantially improving geometric accuracy and outperforming state-of-the art geometry-focused methods. 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/2611.07709 — 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 2026-11-06T14:25:42.617Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).