Skip to content

Latest commit

 

History

History
62 lines (39 loc) · 1.69 KB

README.md

File metadata and controls

62 lines (39 loc) · 1.69 KB

DePF

This is the code of the paper titled as "DePF: A Novel Fusion Approach based on Decomposition Pooling for Infrared and Visible Images".

The article is accepted by IEEE Transactions on Instrumentation and Measurement.

Framework

framework

Decomposition Pooling

compare_msrs

Environment

  • Python 3.9.13
  • torch 1.12.1
  • torchvision 0.13.1
  • tqdm 4.64.1

To Train

We train our network using MS-COCO 2014(T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollar, and C. L. Zitnick. Microsoft coco: Common objects in context. In ECCV, 2014. 3-5.)

You can run the following prompt:

python train_auto_encoder.py

To Test

Put your image pairs in the "test_images" directory and run the following prompt:

python test.py

Acknowledgement

  • Our code of training is based on the DenseFuse.
  • For calculating the image quality assessments, please refer to this Metric.

Contact Informaiton

If you have any questions, please contact me at [email protected].

Citation

If this work is helpful to you, please cite it as (BibTeX):

@article{li2023depf,
  title={DePF: A Novel Fusion Approach based on Decomposition Pooling for Infrared and Visible Images},
  author={Li, Hui and Xiao, Yongbiao and Cheng, Chunyang and Shen, Zhongwei and Song, Xiaoning},
  journal={IEEE Transactions on Instrumentation and Measurement},
  year={2023},
  publisher={IEEE}
}