Metraipolis › archive › dc_c784433727bc

SplatAnything: Gaussian Spacing Normalization for Feed-forward 3DGS across Arbitrary Scenes — arXiv:2611.08264

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.08264
License (as archived)
CC0-1.0
Archived
2026-11-06T14:53:44.569Z
SHA-256 of the archived text
754defbd2fada6805f3500d788d5b1a556328eef98746deb33d4ef6986b2a192
Stable URL of this page
https://metraipolis.com/documento/dc_c784433727bc

How to cite

SplatAnything: Gaussian Spacing Normalization for Feed-forward 3DGS across Arbitrary Scenes — arXiv:2611.08264 — arXiv (en), https://arxiv.org/abs/2611.08264 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c784433727bc (Metraipolis archive dc_c784433727bc, sha256 754defbd2fada6805f3500d788d5b1a556328eef98746deb33d4ef6986b2a192)
BibTeX
@misc{dcc784433727bc,
  title = {SplatAnything: Gaussian Spacing Normalization for Feed-forward 3DGS across Arbitrary Scenes — arXiv:2611.08264},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08264},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c784433727bc; sha256 754defbd2fada6805f3500d788d5b1a556328eef98746deb33d4ef6986b2a192},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08264. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We identify a key limitation of existing feed-forward 3DGS methods: Gaussian attributes are typically predicted in a radial-distance-normalized space that canonicalizes a global radial statistic of the reconstructed geometry, while the spacing between neighboring Gaussian centers can still vary substantially across scene scales and camera configurations. This mismatch induces systematic shifts in Gaussian-scale targets, leading to ambiguous supervision. To address this, we propose SplatAnything with Gaussian Spacing Normalization (GSNorm), which canonicalizes a robust scene-level statistic of Gaussian spacing to provide a more consistent spatial reference for Gaussian prediction. To rigorously assess our method, we further establish a systematic benchmark spanning diverse datasets, input sparsity levels, and challenging extrapolated viewpoints. Extensive experiments demonstrate that SplatAnything achieves state-of-the-art performance, with particularly strong gains under substantial variations in scene scale and viewpoint.

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/2611.08264 — 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 2026-11-06T14:25:42.627Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).