LTA-PCS: Learnable Task-Agnostic Point Cloud Sampling
Jiaheng Liu, Jianhao Li, Kaisiyuan Wang, Hongcheng Guo, Jian Yang, Junran Peng, Ke Xu, Xianglong Liu
Abstract
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 task-agnostic point cloud sampling strategy (e.g. FPS) does not consider semantic information of point clouds causing degraded performance on downstream tasks. While learning-based 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 task-oriented 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.
BibTeX
@inproceedings{cvpr2024_ltapcslearnablet,
title = {LTA-PCS: Learnable Task-Agnostic Point Cloud Sampling},
author = {Jiaheng Liu and Jianhao Li and Kaisiyuan Wang and Hongcheng Guo and Jian Yang and Junran Peng and Ke Xu and Xianglong Liu and Jinyang Guo},
booktitle = {CVPR 2024},
year = {2024}
}