Skip to content

SOS IROS 2018 GOOGLE; StereoNet ECCV2018 GOOGLE; ActiveStereoNet ECCV2018 Oral GOOGLE; HITNET CVPR2021 GOOGLE;PLUME Uber ATG

License

Notifications You must be signed in to change notification settings

meteorshowers/X-StereoLab

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

X-StereoLab is an open source stereo matching and stereo 3D object detection toolbox based on PyTorch.

News: We released the codebase v0.0.0.

  • matching and detection model result.
  • GOOGLE HITNET model pytorch model will be released.

Requirements

All the codes are tested in the following environment:

  • Ubuntu 16.04
  • Python 3.7
  • PyTorch 1.1.0 or 1.2.0 or 1.3.0
  • Torchvision 0.2.2 or 0.4.1

Installation

(1) Clone this repository.

git clone [email protected]:meteorshowers/X-StereoLab.git && cd X-StereoLab

(2) Setup Python environment.

conda activate -n xstereolab
pip install -r requirements.txt --user

## conda deactivate xstereolab

Data Preparation

(1) Please download the KITTI dataset.

ln -s /path/to/KITTI_DATA_PATH ./data/kitti/
ln -s /path/to/OUTPUT_PATH ./outputs/

Multi-GPU Training

The training scripts support multi-processing distributed training, which is much faster than the typical PyTorch DataParallel interface.

python3 tools/train_net_disp.py --cfg ./configs/config_xxx.py --savemodel ./outputs/MODEL_NAME -btrain 4 -d 0-3 --multiprocessing-distributed

The training models, configuration and logs will be saved in the model folder.

To load some pretrained model, you can run

python3 tools/train_net_disp.py --cfg xxx/config.py --loadmodel ./outputs/MODEL_NAMEx --start_epoch xxx --savemodel ./outputs/MODEL_NAME -btrain 4 -d 0-3 --multiprocessing-distributed

If you want to continue training from some epochs, just set the cfg, loadmodel and start_epoch to the respective model path.

Besides, you can start a tensorboard session by

tensorboard --logdir=./outputs/MODEL_NAME/tensorboard --port=6666

and visualize your training process by accessing https://localhost:6666 on your browser.

Inference and Evaluation

on working ...

stereo matching Performance and Model Zoo

</tbody>
Methods Epochs Train Mem (GB/Img) Test Mem (GB/Img) EPE D1-all Models
HITNET (kitti) 4200 2.43% GoogleDrive
HITNET (sceneflow) 200 0.65 GoogleDrive
stereonet (sceneflow) 20 1.10 GoogleDrive
ActiveStereoNet 10 GoogleDrive
SOS

stereo 3D detection Performance and Model Zoo

PLUME: Efficient 3D Object Detection from Stereo Images

Methods Epochs Train Mem (GB/Img) Test Mem (GB/Img) 3D BEV AP (Ours small plume) 3D BEV AP (Paper small plume)
PLUME 72.9 / 62.5 / 56.9 74.4 / 61.7 / 55.8

Video Demo

We provide a video demo for showing the result of X-StereoLab. Here we show the predicted disparity map of activastereonet.

TODO List

  • Multiprocessing GPU training
  • TensorboardX
  • Reduce training GPU memory usage
  • eval and test code
  • Result visualization
  • Still in progress

Citations

If you find our work useful in your research, please consider citing:

@misc{XStereoLab2021,
    title={{X-StereoLab} stereo matching and stereo 3D object detection toolbox},
    author={X-StereoLab Contributors},
    howpublished = {\url{https://github.com/meteorshowers/X-StereoLab}},
    year={2021}
}
* refercence[2] 
@article{tankovich2020hitnet,
  title={HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching},
  author={Tankovich, Vladimir and H{\"a}ne, Christian and Fanello, Sean and Zhang, Yinda and Izadi, Shahram and Bouaziz, Sofien},
  journal={arXiv preprint arXiv:2007.12140},
  year={2020}
}

* refercence[3] 
@inproceedings{tankovich2018sos,
  title={Sos: Stereo matching in o (1) with slanted support windows},
  author={Tankovich, Vladimir and Schoenberg, Michael and Fanello, Sean Ryan and Kowdle, Adarsh and Rhemann, Christoph and Dzitsiuk, Maksym and Schmidt, Mirko and Valentin, Julien and Izadi, Shahram},
  booktitle={2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  pages={6782--6789},
  year={2018},
  organization={IEEE}
}

Others contributors

pic
vtankovich

GOOGLE

pic
Yan Wang

Waymo

Acknowledgment

License

The code is released under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public License for NonCommercial use only. Any commercial use should get formal permission first.

Contact

If you have any questions or suggestions about this repo, please feel free to contact me ([email protected]). Wechat:

pic
XUANYILI

About

SOS IROS 2018 GOOGLE; StereoNet ECCV2018 GOOGLE; ActiveStereoNet ECCV2018 Oral GOOGLE; HITNET CVPR2021 GOOGLE;PLUME Uber ATG

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published