LTA-PCS: Learnable Task-Agnostic Point Cloud Sampling

Recently, many approaches directly operate on point clouds for different tasks. These approaches become more computation and storage demanding when point cloud size is large. To reduce the required computation and storage, one possible solution is to sample the point cloud. In this paper, we propose the first Learnable Task-Agnostic Point Cloud Sampling (LTA-PCS) framework. Existing taskagnostic point cloud sampling strategy (e.g., FPS) does not consider semantic information of point clouds, causing degraded performance on downstream tasks. While learningbased point cloud sampling methods consider semantic information, they are task-specific and require task-oriented ground-truth annotations. So they cannot generalize well on different downstream tasks. Our LTA-PCS achieves task-agnostic point cloud sampling without requiring taskoriented labels, in which both the geometric and semantic information of points is considered in sampling. Extensive experiments on multiple downstream tasks demonstrate the effectiveness of our LTA-PCS.