Towards Extremely Fast Infrared and Visible Image Fusion via Distillation to Learnable Look-Up Tables

conda create -n lutfuse python=3.8
conda activate lutfuse

conda install pytorch==2.0.0 torchvision==0.15.0 pytorch-cuda=11.8 -c pytorch -c nvidia
pip install -r requirements.txt

You should list your dataset as followed rule:

|dataset
  |train
    |Infrared
    |Visible
    |Fuse_ref
  |test
    |Infrared
    |Visible
    |Fuse_ref

We provide our pretrained checkpoints directly in this repository for convenience.
You can find them under ./ckpts.

• Fusion LUT weights: ckpts/fine_tuned_lut.npy
• Context generator weights: ckpts/generator_context.pth

CUDA_VISIBLE_DEVICES=0 python test_lut.py

CUDA_VISIBLE_DEVICES=0 python fine_tune_lut.py

If you find our work or dataset useful for your research, please cite our paper.

@inproceedings{yi2025LUT-Fuse,
  title={LUT-Fuse: Towards Extremely Fast Infrared and Visible Image Fusion via Distillation to Learnable Look-Up Tables},
  author={Yi, Xunpeng and Zhang, Yibing and Xiang, Xinyu and Yan, Qinglong and Xu, Han and Ma, Jiayi},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  year={2025}
}

If you have any questions, please send an email to zhangyibing@whu.edu.cn