3R-GS: Best Practice in Optimizing Camera Poses Along with 3DGS

CV 3DGS VSER
2025年04月05日
3D Gaussian Splatting (3DGS) 以其高效性和高质量彻底改变了神经渲染领域,但与许多新颖的视图合成方法一样,它严重依赖于来自运动结构(SfM)系统的精确相机姿态。尽管最近的 SfM 流程取得了令人印象深刻的进展,但在如何进一步同时提升其在挑战性条件(例如无纹理场景)下的鲁棒性能以及相机参数估计的精度方面,仍然存在疑问。我们提出了 3R-GS,这是一种结合了大规模重建先验 MASt3R-SfM 的 3D Gaussian Splatting 框架,能够联合优化 3D 高斯分布和相机参数。我们注意到,简单地进行联合 3D 高斯分布和相机优化会面临两个挑战:对 SfM 初始化质量的敏感性,以及全局优化能力有限,从而导致次优的重建结果。我们的 3R-GS 通过引入优化实践克服了这些问题,即使在相机注册不完善的情况下也能实现鲁棒的场景重建。大量实验表明,3R-GS 在保持计算效率的同时,能够提供高质量的新视图合成和精确的相机姿态估计。项目页面:https://zsh523.github.io/3R-GS/
3D Gaussian Splatting (3DGS) has revolutionized neural rendering with its efficiency and quality, but like many novel view synthesis methods, it heavily depends on accurate camera poses from Structure-from-Motion (SfM) systems. Although recent SfM pipelines have made impressive progress, questions remain about how to further improve both their robust performance in challenging conditions (e.g., textureless scenes) and the precision of camera parameter estimation simultaneously. We present 3R-GS, a 3D Gaussian Splatting framework that bridges this gap by jointly optimizing 3D Gaussians and camera parameters from large reconstruction priors MASt3R-SfM. We note that naively performing joint 3D Gaussian and camera optimization faces two challenges: the sensitivity to the quality of SfM initialization, and its limited capacity for global optimization, leading to suboptimal reconstruction results. Our 3R-GS, overcomes these issues by incorporating optimized practices, enabling robust scene reconstruction even with imperfect camera registration. Extensive experiments demonstrate that 3R-GS delivers high-quality novel view synthesis and precise camera pose estimation while remaining computationally efficient. Project page: https://zsh523.github.io/3R-GS/
许愿