In this paper we propose a new framework for point cloud instance segmentation. Our framework has two steps: an embedding step and a clustering step. In the embedding step, our main contribution is to propose a probabilistic embedding space for point cloud embedding. Specifically, each point is represented as a tri-variate normal distribution. In the clustering step, we propose a novel loss function, which benefits both the semantic segmentation and the clustering. Our experimental results show important improvements to the SOTA, i.e., 3.1% increased average per-category mAP on the PartNet dataset.
@article{arxiv.1912.00145,
title = {Point Cloud Instance Segmentation using Probabilistic Embeddings},
author = {Biao Zhang and Peter Wonka},
journal= {arXiv preprint arXiv:1912.00145},
year = {2021}
}
Comments
Accepted by CVPR 2021. Project: http://1zb.github.io/publication/prob-embed/