Source Code Author: Vinit Sarode
- Cuda 10
- pytorch==1.3.0
- transforms3d==0.3.1
- h5py==2.9.0
Path for dataset: Link
- Download 'train_data' folder from above link for iterative PCRNet.
- Download 'car_data' folder from above link for PCRNet.
python train.py
python train.py --iterations 1 --dataset pcr_single
@InProceedings{vsarode2019pcrnet,
author = {Sarode, Vinit and Li, Xueqian and Goforth, Hunter and Aoki, Yasuhiro and Arun Srivatsan, Rangaprasad and Lucey, Simon and Choset, Howie},
title = {PCRNet: Point Cloud Registration Network using PointNet Encoding},
month = {Aug},
year = {2019}
}
This code builds upon the code provided in Deep Closest Point DCP. We thanks the authors of the paper for sharing their code.