Metraipolis › archive › dc_2cd581ed62da

What Builds the Scene? Luminance Dominates Geometry Formation in 3D Gaussian Splatting — arXiv:2610.00749

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.00749
License (as archived): CC0-1.0
Archived: 2026-10-06T19:11:35.035Z
SHA-256 of the archived text: 9c9946ac8aa8d6924cbc2e136bb69cd36dd8ed670f5c339bf405e115296e30bb
Stable URL of this page: https://metraipolis.com/documento/dc_2cd581ed62da

How to cite

What Builds the Scene? Luminance Dominates Geometry Formation in 3D Gaussian Splatting — arXiv:2610.00749 — arXiv (en), https://arxiv.org/abs/2610.00749 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2cd581ed62da (Metraipolis archive dc_2cd581ed62da, sha256 9c9946ac8aa8d6924cbc2e136bb69cd36dd8ed670f5c339bf405e115296e30bb)

BibTeX

@misc{dc2cd581ed62da,
  title = {What Builds the Scene? Luminance Dominates Geometry Formation in 3D Gaussian Splatting — arXiv:2610.00749},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.00749},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2cd581ed62da; sha256 9c9946ac8aa8d6924cbc2e136bb69cd36dd8ed670f5c339bf405e115296e30bb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00749. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Standard 3D Gaussian Splatting (3DGS) learns geometry and appearance jointly from RGB supervision, making it difficult to isolate how luminance and chroma contribute to the learned representation. We study this by training models under different channel supervision, freezing their non-appearance parameters (position, scale, rotation, and opacity), and re-estimating appearance with the same solver before comparing held-out reconstruction. Across eleven benchmark scenes with four independent runs each, geometry learned from luminance alone supports held-out reconstruction 0.085 dB below RGB-trained geometry on average. If chroma is deleted from a trained model, a sufficiently expressive solver can re-fit it on the frozen geometry to the original quality or slightly better. Higher-order spherical harmonics contribute much more reconstruction quality to luminance than to chroma, improving PSNR by 1.44 dB versus 0.19 dB on average, although on mirror-like surfaces hue does still change with viewpoint. The luminance advantage is even larger when geometry is being formed. Chroma-only supervision produces geometry 3.9-5.5 dB worse than luminance-only supervision after the same appearance solve; densification explains part of this gap. Overall, geometry formation in standard 3DGS is strongly luminance-dominated but not luminance-exclusive, and much of the chromatic appearance can be recovered after spatial support has formed.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-02 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Graphics (cs.GR).
Pagina del lavoro: https://arxiv.org/abs/2610.00749 — 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 2026-10-06T17:37:36.695Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).