基于概率 Procrustes 映射的无位姿 3DGS 重建
Unposed 3DGS Reconstruction with Probabilistic Procrustes Mapping
AI总结：
针对大规模户外无位姿图像的 3DGS 重建难题，本文提出结合预训练 MVS 先验、概率 Procrustes 全局对齐及位姿—场景联合优化的框架，并在 Waymo、KITTI 上达到新 SOTA。
摘要：
3D Gaussian Splatting（3DGS）已成为三维表示的核心技术。其效果在很大程度上依赖精确的相机位姿和准确的点云初始化，而这些通常来自预训练的 Multi-View Stereo（MVS）模型。然而，在利用数百张户外图像进行无位姿重建的任务中，现有 MVS 模型可能受到内存限制，并随着输入图像数量增加而损失精度。为解决这一局限，我们提出一种新颖的无位姿 3DGS 重建框架，将预训练 MVS 先验与概率 Procrustes 映射策略相结合。该方法将输入图像划分为若干子集，把子地图映射到全局空间，并利用 3DGS 联合优化几何与位姿。技术上，我们将数千万个点云的映射表述为概率 Procrustes 问题，并求解闭式对齐。通过采用概率耦合以及用于拒绝不确定对应关系的软垃圾桶机制，我们的方法可在数分钟内对数百张图像中的点云和位姿进行全局对齐。此外，我们提出一个面向 3DGS 与相机位姿的联合优化框架。该框架从具备置信度感知的锚点构建 Gaussian，并将 3DGS 可微渲染与解析 Jacobian 相结合，以联合精化场景和位姿，从而实现准确的重建与位姿估计。在 Waymo 和 KITTI 数据集上的实验表明，我们的方法能够从无位姿图像序列中实现准确重建，为无位姿 3DGS 重建设立了新的最先进水平。
英文摘要：
3D Gaussian Splatting (3DGS) has emerged as a core technique for 3D representation. Its effectiveness largely depends on precise camera poses and accurate point cloud initialization, which are often derived from pretrained Multi-View Stereo (MVS) models. However, in unposed reconstruction task from hundreds of outdoor images, existing MVS models may struggle with memory limits and lose accuracy as the number of input images grows. To address this limitation, we propose a novel unposed 3DGS reconstruction framework that integrates pretrained MVS priors with the probabilistic Procrustes mapping strategy. The method partitions input images into subsets, maps submaps into a global space, and jointly optimizes geometry and poses with 3DGS. Technically, we formulate the mapping of tens of millions of point clouds as a probabilistic Procrustes problem and solve a closed-form alignment. By employing probabilistic coupling along with a soft dustbin mechanism to reject uncertain correspondences, our method globally aligns point clouds and poses within minutes across hundreds of images. Moreover, we propose a joint optimization framework for 3DGS and camera poses. It constructs Gaussians from confidence-aware anchor points and integrates 3DGS differentiable rendering with an analytical Jacobian to jointly refine scene and poses, enabling accurate reconstruction and pose estimation. Experiments on Waymo and KITTI datasets show that our method achieves accurate reconstruction from unposed image sequences, setting a new state of the art for unposed 3DGS reconstruction.
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。
