Metraipolis › archive › dc_2dc478186e53

PCAsplat: Gaussian Splatting with Local PCA Regularization — arXiv:2610.11011

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.11011
License (as archived)
CC0-1.0
Archived
2026-10-09T06:30:13.362Z
SHA-256 of the archived text
35e47fab1846b8d81a12a461552fb53a7347d316f9357fdb9817084f44601326
Stable URL of this page
https://metraipolis.com/documento/dc_2dc478186e53

How to cite

PCAsplat: Gaussian Splatting with Local PCA Regularization — arXiv:2610.11011 — arXiv (en), https://arxiv.org/abs/2610.11011 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2dc478186e53 (Metraipolis archive dc_2dc478186e53, sha256 35e47fab1846b8d81a12a461552fb53a7347d316f9357fdb9817084f44601326)
BibTeX
@misc{dc2dc478186e53,
  title = {PCAsplat: Gaussian Splatting with Local PCA Regularization — arXiv:2610.11011},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.11011},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2dc478186e53; sha256 35e47fab1846b8d81a12a461552fb53a7347d316f9357fdb9817084f44601326},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11011. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Gaussian splatting has emerged as a flexible representation for 3D reconstruction from posed images. However, existing methods are optimized primarily using rasterization-based losses, which supervise a splat only when it contributes to sampled camera rays. Gaussians that are occluded or contribute little to the sampled view therefore receive weak or no geometric gradients and may drift away from the underlying surface, producing undesired floaters. We introduce PCAsplat, a geometry-aware regularization framework for Gaussian splatting based on differentiable local principal component analysis (PCA). Our PCA regularizer acts directly on neighborhoods of Gaussian centers and can therefore update Gaussians that do not contribute to the current training view. We regularize the PCA eigenvalues to encourage Gaussians to move to the underlying surface with isotropic tangent-plane coverage. We also align each Gaussian normal with the PCA-estimated neighborhood normal to enforce consistent orientation. Experiments on DTU, Tanks and Temples, and NeRF Synthetic show that the splats produced by PCAsplat better approximate samples of the reference surface while substantially reducing undesired floaters. These surface-aligned splats enable downstream geometry-processing tasks, including point cloud segmentation, and direct Poisson reconstruction. Additionally, PCAsplat remains competitive under conventional novel view synthesis and mesh extraction tasks. Code will be released.

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) ; Graphics (cs.GR).
Pagina del lavoro: https://arxiv.org/abs/2610.11011 — 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 2026-10-09T05:55:07.004Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).