KPConv: Flexible and Deformable Convolution for Point Clouds
Hugues Thomas, Charles R. Qi, Jean-Emmanuel Deschaud, Beatriz Marcotegui, François Goulette, Leonidas J. Guibas · ICCV 2019 · 2019
- Status
- To read
- Topics
- backbones
- Feeds
- First paper · height sampling
What they did
Introduces kernel point convolution, with weights placed at kernel points in Euclidean space, and a deformable variant that moves the kernel points to fit local geometry.
My note
No note yet.
Code
- Repository
- HuguesTHOMAS/KPConv-PyTorch
- Framework
- PyTorch
- Licence
- MIT
- My status
- Not tried
BibTeX
@inproceedings{thomas2019-kpconv,
title = {{KPConv: Flexible and Deformable Convolution for Point Clouds}},
author = {Hugues Thomas and Charles R. Qi and Jean-Emmanuel Deschaud and Beatriz Marcotegui and François Goulette and Leonidas J. Guibas},
booktitle = {ICCV 2019},
year = {2019},
eprint = {1904.08889},
archivePrefix = {arXiv}
}