Instance segmentation is an important task for scene understanding. Compared to the fully-developed 2D, 3D instance segmentation for point clouds have much room to improve. In this paper, we present PointGroup, a new end-to-end bottom-up architecture, specifically focused on better grouping the points by exploring the void space between objects. We design a two-branch network to extract point features and predict semantic labels and offsets, for shifting each point towards its respective instance centroid. A clustering component is followed to utilize both the original and offset-shifted point coordinate sets, taking advantage of their complementary strength. Further, we formulate the ScoreNet to evaluate the candidate instances, followed by the Non-Maximum Suppression (NMS) to remove duplicates. We conduct extensive experiments on two challenging datasets, ScanNet v2 and S3DIS, on which our method achieves the highest performance, 63.6% and 64.0%, compared to 54.9% and 54.4% achieved by former best solutions in terms of mAP with IoU threshold 0.5.
@article{arxiv.2004.01658,
title = {PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation},
author = {Li Jiang and Hengshuang Zhao and Shaoshuai Shi and Shu Liu and Chi-Wing Fu and Jiaya Jia},
journal= {arXiv preprint arXiv:2004.01658},
year = {2020}
}