Metraipolis › archive › dc_206e2bd90220
NRF-GS: Neural Residual Fields for Expressive and Compact Gaussian Splatting — arXiv:2609.37115
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.37115
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T18:40:57.218Z
- SHA-256 of the archived text
15697b62a3f4876d6684a9cdf14d8fa1efa11d92f270aeafd6fd27485fac63f8- Stable URL of this page
https://metraipolis.com/documento/dc_206e2bd90220
How to cite
NRF-GS: Neural Residual Fields for Expressive and Compact Gaussian Splatting — arXiv:2609.37115 — arXiv (en), https://arxiv.org/abs/2609.37115 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_206e2bd90220 (Metraipolis archive dc_206e2bd90220, sha256 15697b62a3f4876d6684a9cdf14d8fa1efa11d92f270aeafd6fd27485fac63f8)
BibTeX
@misc{dc206e2bd90220,
title = {NRF-GS: Neural Residual Fields for Expressive and Compact Gaussian Splatting — arXiv:2609.37115},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.37115},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_206e2bd90220; sha256 15697b62a3f4876d6684a9cdf14d8fa1efa11d92f270aeafd6fd27485fac63f8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37115. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We revisit the role of appearance modeling in 3D Gaussian Splatting (3DGS) and show that limited expressiveness in view-dependent reflectance is a key driver of representation redundancy. In standard 3DGS, low-order spherical harmonics (SH) are used, restricting the splats' ability to model high-frequency directional effects, which is typically compensated by increasing the number of splats. We propose \emph{NRF-GS: Neural Residual Fields for Gaussian Splatting}, a hybrid representation that replaces per-splat SH-bases with a shared neural residual field. Each Gaussian encodes a compact set of appearance features and a lambertian base color, while a lightweight \emph{global scene-level MLP} predicts view-dependent residuals conditioned on viewing direction, distance, and per-splat features. This formulation enhances directional reflectance modeling by combining diffuse per-splat reflectance representations with a shared global function for high-frequency details, enabling both higher expressiveness and parameter sharing across splats. Our key insight is that by accurately capturing high-frequency directional reflectance, especially in specular regions, the GS-representation becomes more expressive, reducing the need for geometrically redundant splats. As a result, NRF-GS achieves comparable or better rendering quality while reducing the number of Gaussians by up to 50\%, and produces visibly improved specular and high-frequency details.
Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Graphics (cs.GR).
Pagina del lavoro: https://arxiv.org/abs/2609.37115 — 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 2026-10-07T18:04:24.822Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).