SampleNet | Differentiable Point Cloud Sampling | Image Editing library

SampleNet is a Python library typically used in Media, Image Editing, Deep Learning applications. SampleNet has no bugs, it has no vulnerabilities and it has low support. However SampleNet build file is not available and it has a Non-SPDX License. You can download it from GitHub.

This work is based on our arXiv tech report. Please read it for more information. You are also welcome to watch the oral talk from CVPR 2020. 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. A recent work showed that learning a task-specific sampling can improve results significantly. However, the proposed technique did not deal with the non-differentiability of the sampling operation and offered a workaround instead. We introduce a novel differentiable relaxation for point cloud sampling. Our approach employs a soft projection operation that approximates sampled points as a mixture of points in the primary input cloud. The approximation is controlled by a temperature parameter and converges to regular sampling when the temperature goes to zero. During training, we use a projection loss that encourages the temperature to drop, thereby driving every sample point to be close to one of the input points. This approximation scheme leads to consistently good results on various applications such as classification, retrieval, and geometric reconstruction. We also show that the proposed sampling network 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. In all cases, our method works better than existing non-learned and learned sampling alternatives.