Point Cloud Instance Segmentation Using Probabilistic Embeddings

Biao Zhang, Peter Wonka; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 8883-8892

Abstract


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.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2021_CVPR, author = {Zhang, Biao and Wonka, Peter}, title = {Point Cloud Instance Segmentation Using Probabilistic Embeddings}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2021}, pages = {8883-8892} }