面向360度视频的无位姿全景高斯泼溅与一致深度先验
Pose-Free Omnidirectional Gaussian Splatting for 360-Degree Videos with Consistent Depth Priors
把相机位姿估计从 SfM 中解放出来，直接利用高斯内部深度先验建立 2D-3D 对应来恢复全景相机位姿，并用单目深度内点筛选驱动高斯致密化；对做无位姿/稀疏视角 3DGS 与全景新视角合成的人可直接复用该位姿求解与致密化策略。
原文依据 recovers poses by establishing consistent 2D-3D correspondences between the reconstructed Gaussians and the unposed images using Gaussians' internal depth priors
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于全景图的全向3D高斯泼溅是三维场景表示的一项关键技术，现有方法通常依赖缓慢的SfM来提供相机位姿与稀疏点先验。本文提出一种无位姿的全向3DGS方法PFGS360，可从无位姿的全向视频中重建3D高斯。为获得准确的相机位姿估计，我们首先构建一个球面一致性感知的位姿估计模块，该模块利用高斯内部的深度先验，在重建的高斯与无位姿图像之间建立一致的2D-3D对应关系来恢复位姿。此外，为提升新视角合成的保真度，我们引入深度内点感知的致密化模块，借助一致的单目深度先验提取深度内点与高斯外点，从而实现高效的高斯致密化并获得照片级真实感的新视角合成。实验表明，在真实世界与合成的360度视频上，本方法显著优于现有的无位姿与有位姿3DGS方法。代码见 https://github.com/zcq15/PFGS360。
英文原文摘要 1133 字符
Omnidirectional 3D Gaussian Splatting with panoramas is a key technique for 3D scene representation, and existing methods typically rely on slow SfM to provide camera poses and sparse points priors. In this work, we propose a pose-free omnidirectional 3DGS method, named PFGS360, that reconstructs 3D Gaussians from unposed omnidirectional videos. To achieve accurate camera pose estimation, we first construct a spherical consistency-aware pose estimation module, which recovers poses by establishing consistent 2D-3D correspondences between the reconstructed Gaussians and the unposed images using Gaussians' internal depth priors. Besides, to enhance the fidelity of novel view synthesis, we introduce a depth-inlier-aware densification module to extract depth inliers and Gaussian outliers with consistent monocular depth priors, enabling efficient Gaussian densification and achieving photorealistic novel view synthesis. The experiments show significant outperformance over existing pose-free and pose-aware 3DGS methods on both real-world and synthetic 360-degree videos. Code is available at https://github.com/zcq15/PFGS360.