无姿态全景方向高斯溅射用于具有一致深度先验的360度视频
Pose-Free Omnidirectional Gaussian Splatting for 360-Degree Videos with Consistent Depth Priors
AI总结：
本文提出PFGS360方法，通过无姿态全景视频重建3D高斯，利用一致性深度先验估计姿态并提升视图合成保真度。
摘要：
全景方向3D高斯溅射是3D场景表示的关键技术，现有方法通常依赖慢速SfM提供相机姿态和稀疏点先验。本文提出无姿态全景方向3DGS方法PFGS360，从无姿态全景视频中重建3D高斯。为实现准确姿态估计，首先构建一个球形一致性感知的姿态估计模块，通过重建高斯与无姿态图像之间的一致2D-3D对应关系，利用高斯内部深度先验恢复姿态。此外，为增强视图合成保真度，引入深度内点感知的密集化模块，提取深度内点和高斯异常点，利用一致单目深度先验实现高效高斯密集化，达到逼真视图合成。实验显示PFGS360在真实和合成360度视频上显著优于现有无姿态和有姿态3DGS方法。代码可在https://github.com/zcq15/PFGS360获取。
英文摘要：
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.
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。
