ML Anthology

Deep Parametric Continuous Convolutional Neural Networks

Shenlong Wang, Simon Suo, Wei-Chiu Ma, Andrei Pokrovsky, Raquel Urtasun
CVPR 2018
doi:10.1109/CVPR.2018.00274 /cvpr/2018/wang2018cvpr-deep/

Abstract

Standard convolutional neural networks assume a grid structured input is available and exploit discrete convolutions as their fundamental building blocks. This limits their applicability to many real-world applications. In this paper we propose Parametric Continuous Convolution, a new learnable operator that operates over non-grid structured data. The key idea is to exploit parameterized kernel functions that span the full continuous vector space. This generalization allows us to learn over arbitrary data structures as long as their support relationship is computable. Our experiments show significant improvement over the state-of-the-art in point cloud segmentation of indoor and outdoor scenes, and lidar motion estimation of driving scenes.

PDF CVPR Semantic Scholar

Cite

Text

Wang et al. "Deep Parametric Continuous Convolutional Neural Networks." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018. doi:10.1109/CVPR.2018.00274

Markdown

[Wang et al. "Deep Parametric Continuous Convolutional Neural Networks." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.](https://mlanthology.org/cvpr/2018/wang2018cvpr-deep/) doi:10.1109/CVPR.2018.00274

BibTeX

@inproceedings{wang2018cvpr-deep,
  title     = {{Deep Parametric Continuous Convolutional Neural Networks}},
  author    = {Wang, Shenlong and Suo, Simon and Ma, Wei-Chiu and Pokrovsky, Andrei and Urtasun, Raquel},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2018},
  doi       = {10.1109/CVPR.2018.00274},
  url       = {https://mlanthology.org/cvpr/2018/wang2018cvpr-deep/}
}