GS²CI：基于大视觉模型先验的快照压缩成像鲁棒高斯溅射方法
GS$^{2}$CI: Robust Gaussian Splatting For Snapshot Compressive Imaging via Large Vision Model Priors
浏览论文内容
中文总结 AI 辅助
该研究针对快照压缩成像的三维重建难题，提出结合三维高斯溅射与大视觉模型先验的框架，引入专属致密化策略提升稳定性，在多基准实验中实现了最优整体性能。
中文摘要 AI 辅助
快照压缩成像（SCI）为高速视频采集提供了高效解决方案，在曝光时间内相机与场景发生相对运动时，通过将时间或空间信息压缩为单一二维测量值，还可实现多视图场景采集。尽管近期研究已探索将SCI用于三维场景重建，但现有方法因信息损失、视点多样性有限，以及联合优化三维表示与相机位姿的计算负担而面临重大挑战。本研究提出一种新颖框架，利用三维高斯溅射（3DGS）与大规模视觉基础模型（VFM）的强大先验，从单一SCI测量值重建高质量三维场景。我们的主要重建过程结合了测量衍生的三维VFM初始化与感知SCI的高斯优化；在粗阶段收敛后，辅助二维VFM会在合成视点提供伪视图监督，用于局部外观优化。为进一步解决3DGS优化期间因SCI监督模糊导致的不稳定性，我们引入了不透明度引导的分裂与增长调节（OSGR），这是一种SCI专属的致密化策略，通过局部不透明度统计增强分裂候选，通过平均不透明度调节抑制损失补偿性不透明度膨胀，并通过明确的候选比例与高斯数量约束限制表示增长。在多个基准上开展的大量实验表明，我们的方法实现了最强的整体性能，兼具领先的重建质量、对视点变化的鲁棒性以及有竞争力的计算效率。
英文摘要
Snapshot Compressive Imaging (SCI) offers an efficient solution for high-speed video acquisition and, under exposure-time camera--scene relative motion, multi-view scene capture by compressing temporal or spatial information into a single 2D measurement. While recent studies have explored SCI for 3D scene reconstruction, existing methods struggle with significant challenges due to information loss, limited viewpoint diversity, and the computational burden of jointly optimizing 3D representations and camera poses. In this work, we propose a novel framework that reconstructs high-quality 3D scenes from a single SCI measurement by leveraging 3D Gaussian Splatting (3DGS) and the powerful priors of large-scale vision foundation models (VFMs). Our primary reconstruction combines measurement-derived 3D VFM initialization with SCI-aware Gaussian optimization. After coarse-stage convergence, an auxiliary 2D VFM provides pseudo-view supervision at synthesized viewpoints for local appearance refinement. To further address the instability caused by ambiguous SCI supervision during 3DGS optimization, we introduce Opacity-Guided Splitting and Growth Regulation (OSGR), an SCI-specific densification strategy that augments split candidates using local opacity statistics, discourages loss-compensating opacity inflation through mean-opacity regulation, and bounds representation growth with explicit candidate-ratio and Gaussian-count constraints. Extensive experiments across multiple benchmarks demonstrate that our method achieves the strongest overall performance, combining leading reconstruction quality and robustness to viewpoint variation with competitive computational efficiency.
发表机构
- Westlake University（西湖大学）
机构由 AI 辅助整理，请以论文原文为准。
