Metraipolis › archive › dc_fd174e25a031

NOVA-GS: Noise-Aware View-Consistent Gaussian Splatting for Low-Light Novel View Synthesis — arXiv:2609.12682

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.12682
License (as archived): CC0-1.0
Archived: 2026-10-16T03:57:42.577Z
SHA-256 of the archived text: 364075d7598ddceb295a8dffc48725653e2ed5f657ea3ea72b9c6065ecf79519
Stable URL of this page: https://metraipolis.com/documento/dc_fd174e25a031

How to cite

NOVA-GS: Noise-Aware View-Consistent Gaussian Splatting for Low-Light Novel View Synthesis — arXiv:2609.12682 — arXiv (en), https://arxiv.org/abs/2609.12682 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fd174e25a031 (Metraipolis archive dc_fd174e25a031, sha256 364075d7598ddceb295a8dffc48725653e2ed5f657ea3ea72b9c6065ecf79519)

BibTeX

@misc{dcfd174e25a031,
  title = {NOVA-GS: Noise-Aware View-Consistent Gaussian Splatting for Low-Light Novel View Synthesis — arXiv:2609.12682},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12682},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fd174e25a031; sha256 364075d7598ddceb295a8dffc48725653e2ed5f657ea3ea72b9c6065ecf79519},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12682. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reconstructing 3D scenes under real-world low-light conditions remains challenging due to severe sensor noise, low signal-to-noise ratios, and degraded photometric consistency, which destabilize geometry estimation and novel view synthesis. Existing approaches often rely on well-lit reference data for reliable Structure-from-Motion (SfM) initialization under degraded inputs or apply per-view enhancement methods that introduce cross-view inconsistencies. To address these limitations, we propose \textbf{NOVA-GS}, a unified noise-aware framework for low-light 3D Gaussian Splatting that subsumes enhancement, denoising, and geometry optimization within a single process. Our method leverages VGGT-based feed-forward estimation to obtain robust camera poses and geometry directly from degraded inputs, eliminating the need for SfM. Building on this initialization, NOVA-GS integrates three coupled components: a structure-aware enhancement module for exposure correction, a self-supervised denoising module with blind-spot masking for pseudo-supervision, and a consistency-driven Gaussian Splatting optimization enforcing cross-view geometric coherence. We further introduce a noise-guided spherical harmonic regularization to suppress view-dependent artifacts in noisy regions. Extensive experiments on diverse real-world low-light datasets demonstrate improved geometric fidelity, color consistency, and robustness without requiring paired supervision or well-lit references. this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-14 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.12682 — 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 2026-10-16T03:44:26.286Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).