@article{DBLP:journals/corr/abs-1811-07782,
author = {Shiyi Lan and
Ruichi Yu and
Gang Yu and
Larry S. Davis},
title = {Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNN},
journal = {CoRR},
volume = {abs/1811.07782},
year = {2018},
url = {http://arxiv.org/abs/1811.07782},
archivePrefix = {arXiv},
eprint = {1811.07782},
timestamp = {Mon, 26 Nov 2018 12:52:45 +0100},
biburl = {https://dblp.org/rec/bib/journals/corr/abs-1811-07782},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
We re-implemented the Geo-CNN following Frustum PointNets.
Follow the instruction of installing Frustum PointNets and thus compile Geo-Conv operator located at models/tf_ops/geoconv.
Use scripts/command_train_geocnn_v1.sh and command_test_geocnn_v1.sh to train/test Geo-CNN.
- Combine GeoCNN and PointNet++
- GeoCNN on other 3D datasets (ModelNet40, ScanNet)
- Well-trained parameters
- This implementation is slightly different from the original version on a private deep learning architure.