用物理模型提升暗光下稀疏视角的3D重建质量
SplatBright: Generalizable Low-Light Scene Reconstruction from Sparse Views via Physically-Guided Gaussian Enhancement
- 分枝预测器稳定初始化3D高斯参数，解耦几何与外观
- 频率先验实现跨视角光照一致，还原纹理细节
- 自研暗光数据合成方法，泛化能力优于现有方法
稀疏视角下的暗光3D重建因曝光不平衡和色彩失真仍具挑战。现有方法存在视图不一致且需逐场景训练的问题。本文提出SplatBright，据我们所知是首个通用的3D高斯框架，可从稀疏sRGB输入中联合完成暗光增强与重建。核心思路是将物理引导的光照建模与几何-外观解耦结合，实现一致的暗光重建。具体地，采用双分支预测器提供稳定的3D高斯参数几何初始化；外观分支通过频率先验实现可控且跨视图一致的光照，再通过外观优化模块分离光照、材质和视角依赖特征以恢复精细纹理。为解决缺乏大规模几何一致配对数据的问题，利用基于物理的相机模型合成暗光视图用于训练。在公开及自采数据集上的大量实验表明，SplatBright在新视角合成、跨视图一致性以及未见暗光场景的泛化能力上均优于2D与3D方法。
原文摘要 · Abstract (English)
Low-light 3D reconstruction from sparse views remains challenging due to exposure imbalance and degraded color fidelity. While existing methods struggle with view inconsistency and require per-scene training, we propose SplatBright, which is, to our knowledge, the first generalizable 3D Gaussian framework for joint low-light enhancement and reconstruction from sparse sRGB inputs. Our key idea is to integrate physically guided illumination modeling with geometry-appearance decoupling for consistent low-light reconstruction. Specifically, we adopt a dual-branch predictor that provides stable geometric initialization of 3D Gaussian parameters. On the appearance side, illumination consistency leverages frequency priors to enable controllable and cross-view coherent lighting, while an appearance refinement module further separates illumination, material, and view-dependent cues to recover fine texture. To tackle the lack of large-scale geometrically consistent paired data, we synthesize dark views via a physics-based camera model for training. Extensive experiments on public and self-collected datasets demonstrate that SplatBright achieves superior novel view synthesis, cross-view consistency, and better generalization to unseen low-light scenes compared with both 2D and 3D methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。