PV-RAFT
This repository contains the PyTorch implementation for paper "PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point Clouds" (CVPR 2021)[arXiv]
Installation
Prerequisites
- Python 3.8
- PyTorch 1.8
- torch-scatter
- CUDA 10.2
- RTX 2080 Ti
- tqdm, tensorboard, scipy, imageio, png
conda create -n pvraft python=3.8
conda activate pvraft
conda install pytorch torchvision torchaudio cudatoolkit=10.2 -c pytorch
conda install tqdm tensorboard scipy imageio
pip install pypng
pip install torch-scatter -f https://pytorch-geometric.com/whl/torch-1.8.0+cu102.htmlUsage
Data Preparation
We follow HPLFlowNet to prepare FlyingThings3D and KITTI datasets. Please refer to repo. Make sure the project structure look like this:
PV-RAFT/
data/
FlyingThings3D_subset_processed_35m/
kitti_processed/
data_preprocess/
datasets/
experiments/
model/
modules/
tools/After downloading datasets, we need to preprocess them.
FlyingThings3D Dataset
python process_flyingthings3d_subset.py --raw_data_path=path_src/FlyingThings3D_subset --save_path=path_dst/FlyingThings3D_subset_processed_35m --only_save_near_ptsYou should replace raw_data_path and save_path with your own setting.
KITTI Dataset
python process_kitti.py --raw_data_path=path_src/kitti --save_path=path_dst/kitti_processed --calib_path=calib_folder_pathYou should replace raw_data_path, save_path and calib_path with your own setting.
Train
python train.py --exp_path=pv_raft --batch_size=2 --gpus=0,1 --num_epochs=20 --max_points=8192 --iters=8 --root=./where exp_path is the experiment folder name and root is the project root path. These 20 epochs take about 53 hours on two RTX 2080 Ti.
If you want to train the refine model, please add --refine and specify --weights parameter as the directory name of the pre-trained model. For example,
python train.py --refine --exp_path=pv_raft_refine --batch_size=2 --gpus=0,1 --num_epochs=10 --max_points=8192 --iters=32 --root=./ --weights=./experiments/pv_raft/checkpoints/best_checkpoint.paramsThese 10 epochs take about 38 hours on two RTX 2080 Ti.
Test
python test.py --dataset=KITTI --exp_path=pv_raft --gpus=1 --max_points=8192 --iters=8 --root=./ --weights=./experiments/pv_raft/checkpoints/best_checkpoint.paramswhere dataset should be chosen from FT3D/KITTI, and weights is the absolute path of checkpoint file.
If you want to test the refine model, please add --refine. For example,
python test.py --refine --dataset=KITTI --exp_path=pv_raft_refine --gpus=1 --max_points=8192 --iters=32 --root=./ --weights=./experiments/pv_raft_refine/checkpoints/best_checkpoint.paramsReproduce results
You can download the checkpoint of refined model here.
Acknowledgement
Our code is based on FLOT. We also refer to RAFT and HPLFlowNet.
Citation
If you find our work useful in your research, please consider citing:
@inproceedings{wei2020pv,
title={{PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point Clouds}},
author={Wei, Yi and Wang, Ziyi and Rao, Yongming and Lu, Jiwen and Zhou, Jie},
booktitle={CVPR},
year={2021}
}
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent