无需COLMAP，用多模态数据实现水下珊瑚礁的高效3D重建
ReefMapGS: Enabling Large-Scale Underwater Reconstruction by Closing the Loop Between Multimodal SLAM and Gaussian Splatting
- 融合声学/惯性/压力/视觉数据，通过位姿图优化估计相机位姿
- 在700米航线上实现比传统方法更精确的全局轨迹估计
- 增量式重建，逐步扩展场景，适合无人潜航器实时应用
3D Gaussian Splatting是一种强大的视觉表征方法，能高效生成高质量的3D场景重建，但其依赖于准确的相机位姿，而这些通常来自计算量大的结构光运动（structure-from-motion）过程，不适用于野外机器人应用。然而，在此类场景中，声学、惯性、压力和视觉等多模态传感器数据可用，适合基于位姿图优化的SLAM方法，可估计车辆轨迹并提供不确定性信息。我们提出一种基于3DGS的增量重建框架ReefMapGS，从高置信度区域构建初始模型，并逐步扩展以涵盖整个场景。通过交替进行新图像观测的局部跟踪与底层3DGS场景的优化，不断精化位姿，并将其反馈至位姿图中进行全局轨迹优化。实验表明，该方法可在无COLMAP的情况下完成两个具有复杂几何结构的水下珊瑚礁区域的3D重建，并在长达700米的航行轨迹上实现更精确的自主水下航行器（AUV）全局位姿估计。
原文摘要 · Abstract (English)
3D Gaussian Splatting is a powerful visual representation, providing high-quality and efficient 3D scene reconstruction, but it is crucially dependent on accurate camera poses typically obtained from computationally intensive processes like structure-from-motion that are unsuitable for field robot applications. However, in these domains, multimodal sensor data from acoustic, inertial, pressure, and visual sensors are available and suitable for pose-graph optimization-based SLAM methods that can estimate the vehicle's trajectory and thus our needed camera poses while providing uncertainty. We propose a 3DGS-based incremental reconstruction framework, ReefMapGS, that builds an initial model from a high certainty region and progressively expands to incorporate the whole scene. We reconstruct the scene incrementally by interleaving local tracking of new image observations with optimization of the underlying 3DGS scene. These refined poses are integrated back into the pose-graph to globally optimize the whole trajectory. We show COLMAP-free 3D reconstruction of two underwater reef sites with complex geometry as well as more accurate global pose estimation of our AUV over survey trajectories spanning up to 700 m.
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。