Metraipolis › archive › dc_ab9e73cf1875

VS-Splat: Voxel-Selective feed-forward Gaussian Splatting for end-to-end 3D object reconstruction from sparse-views — arXiv:2609.12343

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.12343
License (as archived)
CC0-1.0
Archived
2026-10-16T03:57:32.942Z
SHA-256 of the archived text
65ce1556dec2cb4f5426b7c7e97baa2323df048dcc568b1a7ec5366ee8277b3d
Stable URL of this page
https://metraipolis.com/documento/dc_ab9e73cf1875

How to cite

VS-Splat: Voxel-Selective feed-forward Gaussian Splatting for end-to-end 3D object reconstruction from sparse-views — arXiv:2609.12343 — arXiv (en), https://arxiv.org/abs/2609.12343 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ab9e73cf1875 (Metraipolis archive dc_ab9e73cf1875, sha256 65ce1556dec2cb4f5426b7c7e97baa2323df048dcc568b1a7ec5366ee8277b3d)
BibTeX
@misc{dcab9e73cf1875,
  title = {VS-Splat: Voxel-Selective feed-forward Gaussian Splatting for end-to-end 3D object reconstruction from sparse-views — arXiv:2609.12343},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12343},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ab9e73cf1875; sha256 65ce1556dec2cb4f5426b7c7e97baa2323df048dcc568b1a7ec5366ee8277b3d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12343. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Feed-forward Gaussian splatting models have demonstrated remarkable effectiveness in reconstructing three-dimensional (3D) objects from a few two-dimensional (2D) images, even if they are unseen. As existing methods typically predict Gaussian primitives uniformly across the 3D space, most primitives are placed in non-object regions. This may hinder the representation of fine object details. This paper proposes a Voxel-Selective Gaussian Splatting model (VS-Splat), a new end-to-endfeed-forward Gaussian splatting framework that predicts many primitives only within selected voxels that are likely to belong to an object, without 3D structural supervision. To achieve this, we propose a new learnable voxel selection approach that identifies object-centric voxels only with 2D rendering supervision. Our sparse-view rendering experiments with three benchmark datasets show that proposed VS-Splat outperforms several state-of-the-art methods. We further demonstrate its effectiveness as a backbone for an existing densification method and show that anoptional extension improves its robustness to inaccurate camera pose estimates.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-14 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.12343 — 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 2026-10-16T03:44:26.236Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).