This repository contains the code for our MICCAI 2022 paper Deep Laparoscopic Stereo Matching with Transformers
[arXiv]
- Python 3.8.*
- CUDA 10.0
- PyTorch
- TorchVision
Create a virtual environment and activate it.
conda create -n hybristereo python=3.8
conda activate hybristereoThe code has been tested with PyTorch 1.6 and Cuda 10.2.
conda install pytorch=1.6.0 torchvision=0.7.0 cudatoolkit=10.2 -c pytorch
conda install matplotlib path.py tqdm
conda install tensorboard tensorboardX
conda install scipy scikit-image opencvInstall Nvidia Apex
Follow the instructions here. Apex is required for mixed precision training. Please do not use pip install apex - this will not install the correct package.
To evaluate/train our network, you will need to download the required datasets.
You can evaluate a trained model using prediction.sh for each dataset, that would help you generate *.png or *.pfm images correspoding to different datasets.
sh predict_scared.sh
sh predict_davinci.shUse the file 'main_all.m' in eval folder to evaluate your model. Download our pre-trained model via this link: snapshot.
If you find this code useful, please consider to cite our work.
@inproceedings{cheng2022laparoscopic,
title={Deep Laparoscopic Stereo Matching with Transformers},
author={Cheng, Xuelian and Zhong, Yiran and Harandi, Mehrtash and Drummond, Tom and Wang, Zhiyong and Ge, Zongyuan},
booktitle={MICCAI},
year={2022}
}
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent