Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
张佳预 318009e717 | 1 year ago | |
---|---|---|
datasets | 1 year ago | |
filenames | 1 year ago | |
imgs | 1 year ago | |
models | 1 year ago | |
utils | 1 year ago | |
LICENSE | 1 year ago | |
README.md | 1 year ago | |
main.py | 1 year ago | |
main_kitti.py | 1 year ago | |
save_disp_sceneflow.py | 1 year ago | |
test_sceneflow.py | 1 year ago |
Our significant extension version of ACV, named Fast-ACV, is available at Paper, Code
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
This is the implementation of the paper: Attention Concatenation Volume for Accurate and Efficient Stereo Matching, CVPR 2022, Gangwei Xu, Junda Cheng, Peng Guo, Xin Yang
An informative and concise cost volume representation is vital for stereo matching of high accuracy and efficiency. In this paper, we present a novel cost volume construction method which generates attention weights from correlation clues to suppress redundant information and enhance matching-related information in the concatenation volume. To generate reliable attention weights, we propose multi-level adaptive patch matching to improve the distinctiveness of the matching cost at different disparities even for textureless regions.
conda create -n acvnet python=3.8
conda activate acvnet
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
Download Scene Flow Datasets, KITTI 2012, KITTI 2015
Use the following command to train ACVNet on Scene Flow
Firstly, train attention weights generation network for 64 epochs,
python main.py --attention_weights_only True
Secondly, freeze attention weights generation network parameters, train the remaining network for another 64 epochs,
python main.py --freeze_attention_weights True
Finally, train the complete network for 64 epochs,
python main.py
Use the following command to train ACVNet on KITTI (using pretrained model on Scene Flow)
python main_kitti.py
python test_sceneflow.py
Method | D1-bg (All) | D1-fg (All) | D1-all (All) | Runtime (s) |
---|---|---|---|---|
ACVNet | 1.37 % | 3.07 % | 1.65 % | 0.20 |
LEAStereo | 1.40 % | 2.91 % | 1.65 % | 0.30 |
GwcNet | 1.74 % | 3.93 % | 2.11 % | 0.32 |
PSMNet | 1.86 % | 4.62 % | 2.32 % | 0.41 |
If you find this project helpful in your research, welcome to cite the paper.
@inproceedings{xu2022attention,
title={Attention Concatenation Volume for Accurate and Efficient Stereo Matching},
author={Xu, Gangwei and Cheng, Junda and Guo, Peng and Yang, Xin},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={12981--12990},
year={2022}
}
Thanks to Xiaoyang Guo for opening source of his excellent work GwcNet. Our work is inspired by this work and part of codes are migrated from GwcNet.
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》