无需SfM即可从粗略图像和噪声点云重建3D场景，速度快质量高。
A Constrained Optimization Approach for Gaussian Splatting from Coarsely-posed Images and Noisy Lidar Point Clouds
- 分步优化相机位姿与场景几何，降低对精确初始值的依赖。
- 在自建数据集和两个公开基准上优于现有方法，重建精度显著提升。
- 适合缺乏精确标定设备的实时3D重建场景，如自动驾驶采集。
3D高斯泼溅（3DGS）是一种强大的三维重建技术，但通常需要准确的相机位姿和高质量点云进行初始化。传统方法依赖于结构光恢复（SfM）算法，但SfM耗时长，限制了3DGS在真实场景和大规模重建中的应用。本文提出一种无需SfM支持的联合相机位姿估计与3D重建的约束优化方法。核心思想是将相机位姿分解为相机到设备中心、设备中心到世界坐标系的两阶段优化。为此，我们设计了针对不同参数组敏感性的优化约束，并限制各参数搜索空间。同时，由于直接从噪声点云中学习场景几何，我们引入几何约束以提升重建质量。实验表明，该方法在自建数据集及两个公开基准上显著优于现有（多模态）3DGS基线方法及基于COLMAP补充的方法。
原文摘要 · Abstract (English)
3D Gaussian Splatting (3DGS) is a powerful reconstruction technique, but it needs to be initialized from accurate camera poses and high-fidelity point clouds. Typically, the initialization is taken from Structure-from-Motion (SfM) algorithms; however, SfM is time-consuming and restricts the application of 3DGS in real-world scenarios and large-scale scene reconstruction. We introduce a constrained optimization method for simultaneous camera pose estimation and 3D reconstruction that does not require SfM support. Core to our approach is decomposing a camera pose into a sequence of camera-to-(device-)center and (device-)center-to-world optimizations. To facilitate, we propose two optimization constraints conditioned to the sensitivity of each parameter group and restricts each parameter's search space. In addition, as we learn the scene geometry directly from the noisy point clouds, we propose geometric constraints to improve the reconstruction quality. Experiments demonstrate that the proposed method significantly outperforms the existing (multi-modal) 3DGS baseline and methods supplemented by COLMAP on both our collected dataset and two public benchmarks.
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。