This is the official implementation of the MATR model proposed in the paper (MATR: Multimodal Medical Image Fusion via Multiscale Adaptive Transformer) with Pytorch.
- CUDA 11.4
- conda 4.10.1
- Python 3.8.12
- PyTorch 1.9.1
- timm 0.4.12
- tqdm
- glob
- pandas
Dealing with RGB input: Refer to DPCN-Fusion.
Dataset is here.
The code for evaluation metrics is here.
If this work is helpful to you, please cite it as:
@ARTICLE{Tang_2022_MATR,
author={Tang, Wei and He, Fazhi and Liu, Yu and Duan, Yansong},
journal={IEEE Transactions on Image Processing},
title={MATR: Multimodal Medical Image Fusion via Multiscale Adaptive Transformer},
year={2022},
volume={31},
number={},
pages={5134-5149},
doi={10.1109/TIP.2022.3193288}}
If you have any questions, feel free to contact me ([email protected]).