ML Anthology

GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud

Li Yi, Wang Zhao, He Wang, Minhyuk Sung, Leonidas J. Guibas
CVPR 2019
doi:10.1109/CVPR.2019.00407 /cvpr/2019/yi2019cvpr-gspn/

Abstract

We introduce a novel 3D object proposal approach named Generative Shape Proposal Network (GSPN) for instance segmentation in point cloud data. Instead of treating object proposal as a direct bounding box regression problem, we take an analysis-by-synthesis strategy and generate proposals by reconstructing shapes from noisy observations in a scene. We incorporate GSPN into a novel 3D instance segmentation framework named Region-based PointNet (R-PointNet) which allows flexible proposal refinement and instance segmentation generation. We achieve state-of-the-art performance on several 3D instance segmentation tasks. The success of GSPN largely comes from its emphasis on geometric understandings during object proposal, greatly reducing proposals with low objectness.

PDF CVPR Semantic Scholar

Cite

Text

Yi et al. "GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019. doi:10.1109/CVPR.2019.00407

Markdown

[Yi et al. "GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.](https://mlanthology.org/cvpr/2019/yi2019cvpr-gspn/) doi:10.1109/CVPR.2019.00407

BibTeX

@inproceedings{yi2019cvpr-gspn,
  title     = {{GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud}},
  author    = {Yi, Li and Zhao, Wang and Wang, He and Sung, Minhyuk and Guibas, Leonidas J.},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2019},
  doi       = {10.1109/CVPR.2019.00407},
  url       = {https://mlanthology.org/cvpr/2019/yi2019cvpr-gspn/}
}