Dilated Point Convolutions:
On the Receptive Field Size of Point Convolutions on 3D Point Clouds

Francis Engelmann     Theodora Kontogianni     Bastian Leibe    

RWTH Aachen University, Computer Vision Group

International Conference on Robotics and Automation (ICRA), 2020.




In this work, we propose Dilated Point Convolutions (DPC). In a thorough ablation study, we show that the receptive field size is directly related to the performance of 3D point cloud processing tasks, including semantic segmentation and object classification. Point convolutions are widely used to efficiently process 3D data representations such as point clouds or graphs. However, we observe that the receptive field size of recent point convolutional networks is inherently limited. Our dilated point convolutions alleviate this issue, they significantly increase the receptive field size of point convolutions. Importantly, our dilation mechanism can easily be integrated into most existing point convolutional networks. To evaluate the resulting network architectures, we visualize the receptive field and report competitive scores on popular point cloud benchmarks.

News

Video

Publication

Paper International Conference on Robotics and Automation (ICRA), 2020.
Poster ScanNet workshop at Conference on Computer Vision and Pattern Recognition (CVPR Workshop), 2019.

BibTeX

@inproceedings{Engelmann20ICRA,
  author = {Engelmann, Francis and  Kontogianni, Theodora and Leibe, Bastian},
  title = {{Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds}},
  booktitle = {{International Conference on Robotics and Automation (ICRA)}},
  year = {2020}
}