Dense Supervision Propagation for Weakly Supervised Semantic Segmentation on 3D Point Clouds

arXiv:2107.11267v3 Announce Type: replace
Abstract: Semantic segmentation on 3D point clouds is an important task for 3D scene understanding. While dense labeling on 3D data is expensive and time-consuming, only a few works address weakly supervised semantic point cloud segmentation methods to relieve the labeling cost by learning from simpler and cheaper labels. Meanwhile, there are still huge performance gaps between existing weakly supervised methods and state-of-the-art fully supervised methods. In this paper, we train a semantic point cloud segmentation …

abstract arxiv cloud cost cs.cv data labeling propagation segmentation semantic supervision type understanding