✨ We sincerely thank the reviewers, AC and AC triplet of this paper, for their responsibility, dedication, professionalism, and recognition. Meanwhile, we would like to express our gratitude to all the reviewers and ACs. Together, you have created a favorable academic environment, which will enable us to go further.
🌟 Official implementation of the ICCV 2025 paper:
The Source Image is the Best Attention for Infrared and Visible Image Fusion
Song Wang, Xie Han, Liqun Kuang*, Boying Wang, Zhongyu Chen, Zherui Qiao, Fan Yang, Xiaoxia Liu, Bingyu Zhang, Zhixun Wang
School of Computer Science and Technology, North University of China, Taiyuan 030051, China
cuda=11.2
python=3.8.18
imageio==2.32.0
numpy==1.24.4
opencv-python==4.8.1.78
pillow==10.0.1
timm==0.9.10
torch==1.10.0+cu111
torchaudio==0.10.0+cu111
torchvision==0.11.0+cu111
einops==0.7.0
tqdm==4.66.1
kornia==0.7.0MSRS_test | M3FD_Fusion | TNO_baidu | TNO_google
@InProceedings{Wang_2025_ICCV,
author = {Wang, Song and Han, Xie and Kuang, Liqun and Wang, Boying and Chen, Zhongyu and Qiao, Zherui and Yang, Fan and Liu, Xiaoxia and Zhang, Bingyu and Wang, Zhixun},
title = {The Source Image is the Best Attention for Infrared and Visible Image Fusion},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2025},
pages = {13513-13522}
}