无需COLMAP，通过姿态共正则化实现复杂运动下的高精度3D高斯点云重建。
PCR-GS: COLMAP-Free 3D Gaussian Splatting via Pose Co-Regularizations
- 利用相邻视角的DINO特征对齐进行语义重投影正则化
- 通过小波高频差异优化相机旋转矩阵，提升姿态估计精度
- 适合相机大幅移动或旋转的复杂场景重建，如动态拍摄视频
无COLMAP的3D高斯点云（3D-GS）近年来因能从无姿态图像或视频中重建高质量3D场景而受到广泛关注。然而，在具有复杂相机轨迹（如相邻视角间剧烈旋转与平移）的场景中，其相机姿态估计常出现退化，并导致联合优化过程陷入局部极小值。本文提出PCR-GS，一种创新的无COLMAP 3D-GS方法，通过相机姿态共正则化实现更优的3D场景建模与姿态估计。该方法从两个角度实现正则化：一是特征重投影正则化，从相邻视角提取鲁棒的DINO特征并对其语义信息对齐以约束姿态；二是基于小波的频率正则化，利用高频细节差异优化相机旋转矩阵。在多个真实场景上的大量实验表明，所提方法在相机轨迹剧烈变化时仍能实现优异的无姿态3D-GS建模效果。
原文摘要 · Abstract (English)
COLMAP-free 3D Gaussian Splatting (3D-GS) has recently attracted increasing attention due to its remarkable performance in reconstructing high-quality 3D scenes from unposed images or videos. However, it often struggles to handle scenes with complex camera trajectories as featured by drastic rotation and translation across adjacent camera views, leading to degraded estimation of camera poses and further local minima in joint optimization of camera poses and 3D-GS. We propose PCR-GS, an innovative COLMAP-free 3DGS technique that achieves superior 3D scene modeling and camera pose estimation via camera pose co-regularization. PCR-GS achieves regularization from two perspectives. The first is feature reprojection regularization which extracts view-robust DINO features from adjacent camera views and aligns their semantic information for camera pose regularization. The second is wavelet-based frequency regularization which exploits discrepancy in high-frequency details to further optimize the rotation matrix in camera poses. Extensive experiments over multiple real-world scenes show that the proposed PCR-GS achieves superior pose-free 3D-GS scene modeling under dramatic changes of camera trajectories.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。