ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds

Gopal Sharma, Difan Liu, Subhransu Maji, Evangelos Kalogerakis, Siddhartha Chaudhuri, Radomír Měch

ECCV 2020

doi:10.1007/978-3-030-58571-6_16 /eccv/2020/sharma2020eccv-parsenet/

Abstract

We propose a novel, end-to-end trainable, deep network called ParSeNet that decomposes a 3D point cloud into parametric surface patches, including B-spline patches as well as basic geometric primitives. ParSeNet is trained on a large-scale dataset of man-made 3D shapes and captures high-level semantic priors for shape decomposition. It handles a much richer class of primitives than prior work, and allows us to represent surfaces with higher fidelity. It also produces repeatable and robust parametrizations of a surface compared to purely geometric approaches. We present extensive experiments to validate our approach against analytical and learning-based alternatives. Our source code is publicly available at: https://hippogriff.github.io/parsenet.

PDF ECCV Semantic Scholar

Cite

Text

Sharma et al. "ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds." Proceedings of the European Conference on Computer Vision (ECCV), 2020. doi:10.1007/978-3-030-58571-6_16

Markdown

[Sharma et al. "ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds." Proceedings of the European Conference on Computer Vision (ECCV), 2020.](https://mlanthology.org/eccv/2020/sharma2020eccv-parsenet/) doi:10.1007/978-3-030-58571-6_16

BibTeX

@inproceedings{sharma2020eccv-parsenet,
  title     = {{ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds}},
  author    = {Sharma, Gopal and Liu, Difan and Maji, Subhransu and Kalogerakis, Evangelos and Chaudhuri, Siddhartha and Měch, Radomír},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2020},
  doi       = {10.1007/978-3-030-58571-6_16},
  url       = {https://mlanthology.org/eccv/2020/sharma2020eccv-parsenet/}
}