解决多人协作重建3D场景时点云对齐难题
ColabSfM: Collaborative Structure-from-Motion by Point Cloud Registration
- 构建合成相机轨迹生成部分重建点云，用于训练点云配准模型
- 提出RefineRoITr模型，在现有方法上实现显著性能提升
- 首个支持分布式SfM重建协同的可扩展注册方案，适合多设备协作场景
结构从运动（SfM）是从图像中估计三维结构和相机位姿的任务。我们定义协同SfM（ColabSfM）为共享分布式的SfM重建结果。共享地图需要估计一个联合参考坐标系，通常称为配准。然而，目前缺乏可扩展的配准方法和训练数据集来注册SfM重建结果。本文通过提出针对SfM重建的点云配准可扩展任务来解决此挑战。我们发现，当前配准方法在现有数据集上训练后无法成功注册SfM点云。为此，我们提出一种SfM配准数据集生成流程，利用每个场景的合成相机轨迹生成部分重建点云。最后，我们在最先进配准方法RoITr之上提出一个简单但有效的神经精炼器，命名为RefineRoITr，取得了显著改进。大量实验评估表明，所提出的流程和模型实现了真正的ColabSfM。代码已开源：https://github.com/EricssonResearch/ColabSfM
原文摘要 · Abstract (English)
Structure-from-Motion (SfM) is the task of estimating 3D structure and camera poses from images. We define Collaborative SfM (ColabSfM) as sharing distributed SfM reconstructions. Sharing maps requires estimating a joint reference frame, which is typically referred to as registration. However, there is a lack of scalable methods and training datasets for registering SfM reconstructions. In this paper, we tackle this challenge by proposing the scalable task of point cloud registration for SfM reconstructions. We find that current registration methods cannot register SfM point clouds when trained on existing datasets. To this end, we propose a SfM registration dataset generation pipeline, leveraging partial reconstructions from synthetically generated camera trajectories for each scene. Finally, we propose a simple but impactful neural refiner on top of the SotA registration method RoITr that yields significant improvements, which we call RefineRoITr. Our extensive experimental evaluation shows that our proposed pipeline and model enables ColabSfM. Code is available at https://github.com/EricssonResearch/ColabSfM
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。