Itai Lang and Asaf Manor: Learned Sampling of Point Clouds

Join Zoom Meeting
https://zoom.us/j/6043600514?pwd=VTFuU2VSTTNhTE1RRFJTZjhZNTN1Zz09

Meeting ID: 604 360 0514
Password: 703769

There is a growing number of tasks that work directly on point clouds. As the size of the point cloud grows, so do the computational demands of these tasks. A possible solution is to sample the point cloud first. Classic sampling approaches, such as farthest point sampling (FPS), do not consider the downstream task. We introduce a novel differentiable relaxation for point cloud sampling that approximates sampled points as a mixture of points in the primary input cloud. Our approximation scheme leads to consistently good results on classification and geometry reconstruction applications. We also show that the proposed sampling method can be used as a front to a point cloud registration network. This is a challenging task since sampling must be consistent across two different point clouds for a shared downstream task. In all cases, our approach outperforms existing sampling alternatives.

The talk will cover two papers:

1. "Learning to Sample", http://openaccess.thecvf.com/content_CVPR_2019/html/Dovrat_Learning_to_Sample_CVPR_2019_paper.html (CVPR 2019)
2. "SampleNet: Differentiable Point Cloud Sampling", https://arxiv.org/abs/1912.03663 (accepted to CVPR 2020)