ColabSfM: Collaborative Structure-from-Motion by Point Cloud Registration

Figure 1 . Our proposed registration paradigm for collaborative SfM reconstructions (ColabSfM). Given two input SfM reconstructions P, Q of the same scene, the task is to estimate the relative similarity transform (s, R, t) between them. Our first contribution is to address this as a point cloud registration problem, using only 3D SfM tracks. For this, we do not rely on the visual descriptors, but on the 3D coordinates of the points P, Q, their normals N, M and, optionally, but not necessarily, features X, Y. To make point cloud registration methods perform well on this task, we propose as our second contribution a scalable pipeline to construct synthetic training datasets for SfM registration. Finally, we propose an improved version of RoITr [64] as registration method f θ .