DPDist: Comparing Point Clouds Using Deep Point Cloud Distance
Abstract
We introduce a new deep learning method for point cloud comparison. Our approach, named Deep Point Cloud Distance (DPDist), measures the distance between the points in one cloud and the estimated surface from which the other point cloud is sampled. The surface is estimated locally and efficiently using the 3D modified Fisher vector representation. The local representation reduces the complexity of the surface, enabling efficient and effective learning, which generalizes well between object categories. We test the proposed distance in challenging tasks, such as similar object comparison and registration, and show that it provides significant improvements over commonly used distances such as Chamfer distance, Earth mover's distance, and others.
Cite
Text
Urbach et al. "DPDist: Comparing Point Clouds Using Deep Point Cloud Distance." Proceedings of the European Conference on Computer Vision (ECCV), 2020. doi:10.1007/978-3-030-58621-8_32Markdown
[Urbach et al. "DPDist: Comparing Point Clouds Using Deep Point Cloud Distance." Proceedings of the European Conference on Computer Vision (ECCV), 2020.](https://mlanthology.org/eccv/2020/urbach2020eccv-dpdist/) doi:10.1007/978-3-030-58621-8_32BibTeX
@inproceedings{urbach2020eccv-dpdist,
title = {{DPDist: Comparing Point Clouds Using Deep Point Cloud Distance}},
author = {Urbach, Dahlia and Ben-Shabat, Yizhak and Lindenbaum, Michael},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2020},
doi = {10.1007/978-3-030-58621-8_32},
url = {https://mlanthology.org/eccv/2020/urbach2020eccv-dpdist/}
}