Metraipolis › archive › dc_c620388ebdf2

3D Gaussian Splatting within Self-Learned Neural View-Dependent Color Fields — arXiv:2611.03114

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.03114
License (as archived): CC0-1.0
Archived: 2026-11-03T18:55:19.126Z
SHA-256 of the archived text: 0305a9a3a65d5cd4d114c430196aa9d2269975dbe6b99ac9284e27a2ef8d452f
Stable URL of this page: https://metraipolis.com/documento/dc_c620388ebdf2

How to cite

3D Gaussian Splatting within Self-Learned Neural View-Dependent Color Fields — arXiv:2611.03114 — arXiv (en), https://arxiv.org/abs/2611.03114 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c620388ebdf2 (Metraipolis archive dc_c620388ebdf2, sha256 0305a9a3a65d5cd4d114c430196aa9d2269975dbe6b99ac9284e27a2ef8d452f)

BibTeX

@misc{dcc620388ebdf2,
  title = {3D Gaussian Splatting within Self-Learned Neural View-Dependent Color Fields — arXiv:2611.03114},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03114},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c620388ebdf2; sha256 0305a9a3a65d5cd4d114c430196aa9d2269975dbe6b99ac9284e27a2ef8d452f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03114. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

3D Gaussian Splatting (3DGS) has become a vital tool in novel view synthesis. 3D Gaussian functions with attributes like color, opacity, and scale are stacked together to explicitly model a radiance field. However, discrete 3D Gaussians usually produce poor depth with few geometry details but lots of floaters, which hinders the effective modeling of smooth radiance fields. To address this issue, we propose to learn a radiance field within a continuous view-dependent color field parameterized by neural networks. With continuous constraints in color, the bias on low-frequency signals of neural networks can highly encourage the geometry modeling to contribute to high-frequency color variations on images, getting rid of solely relying on the color attribute itself. Moreover, we impose a constraint to improve the Lipschitz continuity of the neural color field, making large changes of each Gaussian's color also match with large changes of its position in terms of a ratio. To this end, we additionally introduce novel self-learning strategies to improve the learning of the neural view-dependent color field without any external knowledge or priors, aiming for better generalization on unseen scenes. Our numerical and visual comparisons on widely used benchmarks justify our idea and show better ability of high fidelity geometry recovery in 3DGS. Project page: this https URL .

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/2611.03114 — 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 2026-11-03T18:16:53.049Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).