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.

翻译：全景三维高斯泼溅是三维场景表示的关键技术，现有方法通常依赖缓慢的SfM（运动恢复结构）来提供相机位姿和稀疏点先验。本文提出一种无位姿的全景三维高斯泼溅方法PFGS360，可从无位姿的全向视频中重建三维高斯体。为精确估计相机位姿，我们首先构建球面一致性感知的位姿估计模块，通过利用高斯体内部深度先验，在重建的高斯体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，为增强新视角合成的逼真度，我们引入深度内点感知的致密化模块，利用一致的单目深度先验提取深度内点与高斯离群点，实现高效的高斯致密化和照片级真实感的新视角合成。实验表明，该方法在真实场景和合成360度视频上均显著优于现有无位姿和基于位姿的三维高斯泼溅方法。代码开源地址：https://github.com/zcq15/PFGS360