Accurate and Efficient Stereo Matching via Attention Concatenation Volume
Gangwei Xu, Yun Wang, Junda Cheng, Jinhui Tang, Xin Yang
Paper
Fast-ACVNet.
Demo on KITTI raw data
A demo result on our RTX 3090 (Ubuntu 20.04).
How to use
Environment
- Python 3.8
- Pytorch 1.10
Install
Create a virtual environment and activate it.
conda create -n fast_acv python=3.8
conda activate fast_acv
Dependencies
conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch -c nvidia
pip install opencv-python
pip install scikit-image
pip install tensorboard
pip install matplotlib
pip install tqdm
pip install timm==0.5.4
Data Preparation
Download Scene Flow Datasets, KITTI 2012, KITTI 2015
Train
Use the following command to train Fast-ACVNet+ or Fast-ACVNet on Scene Flow
Firstly, train attention weights generation network for 24 epochs,
python main_sceneflow.py --attention_weights_only True --logdir ./checkpoints/sceneflow/attention
Secondly, train complete network for another 24 epochs,
python main_sceneflow.py --loadckpt ./checkpoints/sceneflow/attention/checkpoint_000023.ckpt --logdir ./checkpoints/sceneflow/complete
Use the following command to train Fast-ACVNet+ or Fast-ACVNet on KITTI (using pretrained model on Scene Flow),
python main_kitti.py --loadckpt ./checkpoints/sceneflow/complete/checkpoint_000023.ckpt --logdir ./checkpoints/kitti
Submitted to KITTI benchmarks
python save_disp.py
Evaluation on Scene Flow and KITTI
Method | Scene Flow (EPE) |
KITTI 2012 (3-all) |
KITTI 2015 (D1-all) |
Runtime (ms) |
---|---|---|---|---|
Fast-ACVNet+ | 0.59 | 1.85 % | 2.01 % | 45 |
HITNet | - | 1.89 % | 1.98 % | 54 |
CoEx | 0.69 | 1.93 % | 2.13 % | 33 |
BGNet+ | - | 2.03 % | 2.19 % | 35 |
AANet | 0.87 | 2.42 % | 2.55 % | 62 |
DeepPrunerFast | 0.97 | - | 2.59 % | 50 |
Our Fast-ACVNet+ achieves comparable accuracy with HITNet on KITTI 2012 and KITTI 2015
Pretrained Model
Qualitative results on Scene Flow.
Qualitative results on KITTI.
Generalization performance on the Middlebury 2014 dataset. All the comparison methods are only trained on Scene Flow without data augmentation.
Citation
If you find this project helpful in your research, welcome to cite the paper.
@article{xu2022accurate,
title={Accurate and Efficient Stereo Matching via Attention Concatenation Volume},
author={Xu, Gangwei and Wang, Yun and Cheng, Junda and Tang, Jinhui and Yang, Xin},
journal={arXiv preprint arXiv:2209.12699},
year={2022}
}
Acknowledgements
Thanks to Antyanta Bangunharcana for opening source of his excellent work Correlate-and-Excite. Thanks to Xiaoyang Guo for opening source of his excellent work GwcNet.