Giter VIP home page Giter VIP logo

datfuse's Introduction

DATFuse: Infrared and Visible Image Fusion via Dual Attention Transformer (IEEE TCSVT 2023)

This is the official implementation of the DATFuse model proposed in the paper (DATFuse: Infrared and Visible Image Fusion via Dual Attention Transformer) with Pytorch.

Comparison with SOTA methods

Fusion results on TNO dataset

Image text

Fusion results on RoadScene dataset

Image text

Ablation study on network structure

Image text

Ablation study on the number of TRMs

Image text

Ablation study on the second DARM

Image text

Impact of weight parameters in the loss function

Impact of weight parameter α on fusion performance with λ and γ fixed as 100 and 10, respectively.

Image text

Impact of weight parameter λ on fusion performance with α and γ fixed as 1 and 10, respectively.

Image text

Impact of weight parameter γ on fusion performance with α and λ fixed as 1 and 100, respectively.

Image text

Computational efficiency comparisons

Average running time for generating a fused image (Unit: seconds)

Method TNO Dataset RoadScene Dataset
MDLatLRR 26.0727 11.7310
AUIF 0.1119 0.0726
DenseFuse 0.5663 0.3190
FusionGAN 2.6796 1.1442
GANMcC 5.6752 2.3813
RFN_Nest 2.3096 0.9423
CSF 10.3311 5.5395
MFEIF 0.0793 0.0494
PPTFusion 1.4150 0.8656
SwinFuse 3.2687 1.6478
DATFuse 0.0257 0.0141

Cite the paper

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

@ARTICLE{Tang_2023_DATFuse,
  author={Tang, Wei and He, Fazhi and Liu, Yu and Duan, Yansong and Si, Tongzhen},
  journal={IEEE Transactions on Circuits and Systems for Video Technology}, 
  title={DATFuse: Infrared and Visible Image Fusion via Dual Attention Transformer}, 
  year={2023},
  volume={},
  number={},
  pages={1-15},
  doi={10.1109/TCSVT.2023.3234340}}

If you have any questions, feel free to contact me ([email protected]).

datfuse's People

Contributors

tthinking avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.