SplineGS：面向单目视频实时动态3D高斯的鲁棒运动自适应样条
SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from Monocular Video
AI总结：
提出SplineGS框架，通过运动自适应样条与控制点剪枝方法及联合优化策略，实现无需COLMAP的单目视频动态3D高斯高质量重建与数千倍加速渲染。
摘要：
由于场景动态性以及缺乏多视图线索，从野外单目视频中合成新视图具有挑战性。为解决此问题，我们提出了SplineGS，这是一个无需COLMAP的动态3D高斯泼溅（3DGS）框架，用于从单目视频进行高质量重建和快速渲染。其核心是一种新颖的运动自适应样条（MAS）方法，该方法使用具有少量控制点的三次Hermite样条来表示连续的动态3D高斯轨迹。对于MAS，我们引入了运动自适应控制点剪枝（MACP）方法，以建模每个动态3D高斯在不同运动下的变形，在保持动态建模完整性的同时逐步剪枝控制点。此外，我们提出了一种用于相机参数估计和3D高斯属性的联合优化策略，利用光度一致性和几何一致性。这消除了对Structure-from-Motion预处理的需求，并增强了SplineGS在真实世界条件下的鲁棒性。实验表明，SplineGS在单目视频动态场景的新视图合成质量上显著优于现有最先进方法，实现了数千倍的渲染速度提升。
英文摘要：
Synthesizing novel views from in-the-wild monocular videos is challenging due to scene dynamics and the lack of multi-view cues. To address this, we propose SplineGS, a COLMAP-free dynamic 3D Gaussian Splatting (3DGS) framework for high-quality reconstruction and fast rendering from monocular videos. At its core is a novel Motion-Adaptive Spline (MAS) method, which represents continuous dynamic 3D Gaussian trajectories using cubic Hermite splines with a small number of control points. For MAS, we introduce a Motion-Adaptive Control points Pruning (MACP) method to model the deformation of each dynamic 3D Gaussian across varying motions, progressively pruning control points while maintaining dynamic modeling integrity. Additionally, we present a joint optimization strategy for camera parameter estimation and 3D Gaussian attributes, leveraging photometric and geometric consistency. This eliminates the need for Structure-from-Motion preprocessing and enhances SplineGS's robustness in real-world conditions. Experiments show that SplineGS significantly outperforms state-of-the-art methods in novel view synthesis quality for dynamic scenes from monocular videos, achieving thousands times faster rendering speed.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
