ML Anthology

3D Point Capsule Networks

Yongheng Zhao, Tolga Birdal, Haowen Deng, Federico Tombari
CVPR 2019
doi:10.1109/CVPR.2019.00110 /cvpr/2019/zhao2019cvpr-3d/

Abstract

In this paper, we propose 3D point-capsule networks, an auto-encoder designed to process sparse 3D point clouds while preserving spatial arrangements of the input data. 3D capsule networks arise as a direct consequence of our unified formulation of the common 3D auto-encoders. The dynamic routing scheme and the peculiar 2D latent space deployed by our capsule networks bring in improvements for several common point cloud-related tasks, such as object classification, object reconstruction and part segmentation as substantiated by our extensive evaluations. Moreover, it enables new applications such as part interpolation and replacement.

PDF CVPR Semantic Scholar

Cite

Text

Zhao et al. "3D Point Capsule Networks." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019. doi:10.1109/CVPR.2019.00110

Markdown

[Zhao et al. "3D Point Capsule Networks." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.](https://mlanthology.org/cvpr/2019/zhao2019cvpr-3d/) doi:10.1109/CVPR.2019.00110

BibTeX

@inproceedings{zhao2019cvpr-3d,
  title     = {{3D Point Capsule Networks}},
  author    = {Zhao, Yongheng and Birdal, Tolga and Deng, Haowen and Tombari, Federico},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2019},
  doi       = {10.1109/CVPR.2019.00110},
  url       = {https://mlanthology.org/cvpr/2019/zhao2019cvpr-3d/}
}