Point Cloud Instance Segmentation Using Probabilistic Embeddings

CVPR 2021 pp. 8883-8892

doi:10.1109/CVPR46437.2021.00877 /cvpr/2021/zhang2021cvpr-point/

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.

PDF CVPR Semantic Scholar

Cite

Text

Zhang and Wonka. "Point Cloud Instance Segmentation Using Probabilistic Embeddings." Conference on Computer Vision and Pattern Recognition, 2021. doi:10.1109/CVPR46437.2021.00877

Markdown

[Zhang and Wonka. "Point Cloud Instance Segmentation Using Probabilistic Embeddings." Conference on Computer Vision and Pattern Recognition, 2021.](https://mlanthology.org/cvpr/2021/zhang2021cvpr-point/) doi:10.1109/CVPR46437.2021.00877

BibTeX

@inproceedings{zhang2021cvpr-point,
  title     = {{Point Cloud Instance Segmentation Using Probabilistic Embeddings}},
  author    = {Zhang, Biao and Wonka, Peter},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2021},
  pages     = {8883-8892},
  doi       = {10.1109/CVPR46437.2021.00877},
  url       = {https://mlanthology.org/cvpr/2021/zhang2021cvpr-point/}
}