Metraipolis › archive › dc_dd5cd3c9d44c
UGOD: Uncertainty-Guided Opacity and Dropout for Sparse-View 3D Gaussian Splatting — arXiv:2609.39089
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.39089
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T14:45:47.008Z
- SHA-256 of the archived text
c34eed9c52f200ee262589771a076a2fffd6885724dcd2bfcae0689869060cef- Stable URL of this page
https://metraipolis.com/documento/dc_dd5cd3c9d44c
How to cite
UGOD: Uncertainty-Guided Opacity and Dropout for Sparse-View 3D Gaussian Splatting — arXiv:2609.39089 — arXiv (en), https://arxiv.org/abs/2609.39089 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dd5cd3c9d44c (Metraipolis archive dc_dd5cd3c9d44c, sha256 c34eed9c52f200ee262589771a076a2fffd6885724dcd2bfcae0689869060cef)
BibTeX
@misc{dcdd5cd3c9d44c,
title = {UGOD: Uncertainty-Guided Opacity and Dropout for Sparse-View 3D Gaussian Splatting — arXiv:2609.39089},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.39089},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dd5cd3c9d44c; sha256 c34eed9c52f200ee262589771a076a2fffd6885724dcd2bfcae0689869060cef},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39089. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Sparse-view 3D Gaussian Splatting is prone to overfitting because limited observations leave many Gaussian primitives weakly constrained, yet their contributions are still accumulated through alpha blending. Without uncertainty estimation, the renderer cannot distinguish unreliable primitives from well-constrained ones, allowing their erroneous contributions to corrupt novel-view synthesis. We introduce UGOD, an uncertainty-guided framework that estimates a view-dependent uncertainty score for each Gaussian and uses it to regulate its rendering contribution. A lightweight uncertainty head conditioned on Gaussian attributes and viewing direction predicts this score, which then drives a differentiable opacity-modulation mechanism that attenuates high-uncertainty primitives before compositing. During training, a detached soft-dropout branch applies an uncertainty-controlled continuous keep mask to discourage the model from relying on poorly constrained Gaussians and thereby reduce overfitting. Crucially, detaching the uncertainty score prevents gradients from this stochastic regulariser from biasing or collapsing the uncertainty prediction. Experiments on Mip-NeRF~360 and LLFF show that UGOD improves sparse-view novel-view synthesis while producing more compact Gaussian representations than the compared methods. These results demonstrate that Gaussian uncertainty provides an effective rendering-time control for sparse-view reconstruction. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.39089 — 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 2026-10-07T14:19:00.664Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).