发表机构
Indian Institute of Technology Madras（印度理工学院马德拉斯分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对低光3D重建中的噪声和视图不一致问题，提出NOVA-GS框架，集成增强、去噪和几何优化，无需SfM或参考数据，提升几何保真度和颜色一致性。
AI 中文摘要
在真实世界低光条件下重建3D场景仍具挑战性，原因在于严重的传感器噪声、低信噪比以及退化的光度一致性，这些因素破坏了几何估计和新视角合成的稳定性。现有方法通常依赖光照良好的参考数据，以便在退化输入下进行可靠的运动恢复结构（SfM）初始化，或采用逐视图增强方法，但这会引入跨视图不一致性。为解决这些局限，我们提出NOVA-GS，一个统一的噪声感知框架，用于低光3D高斯泼溅，将增强、去噪和几何优化整合于单一流程中。我们的方法利用基于VGGT的前馈估计，直接从退化输入中获取稳健的相机位姿和几何，无需SfM。基于此初始化，NOVA-GS集成了三个耦合组件：用于曝光校正的结构感知增强模块、具有盲点掩蔽的自监督去噪模块以生成伪监督，以及一致性驱动的高斯泼溅优化以强制跨视图几何一致性。我们进一步引入噪声引导的球谐正则化，以抑制噪声区域中与视图相关的伪影。在多种真实世界低光数据集上的大量实验表明，我们的方法在无需成对监督或光照良好参考的情况下，提高了几何保真度、颜色一致性和鲁棒性。
英文摘要
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. https://shaurya2524.github.io/nova-gs/
CommentsAccepted to the 3D4S Workshop at CVPR 2026; selected for the Best Paper Award
