Neural Characteristic Function Learning for Conditional Image Generation (ICCV 2023)

This code is for the implementation of CCF-GAN proposed in the paper "Neural Characteristic Function Learning for Conditional Image Generation" that has been accepted in ICCV 2023.

[pdf] [supp] [poster]

Requirements

For BigGAN platform:

• Python 3.7
• PyTorch
• pip install -r requirements_biggan.txt

For StudioGAN platform:

• Python 3.7
• PyTorch (at least 1.7)
• pip install -r requirements_studiogan.txt

Citation

CCF-GAN implementation is heavily based on BigGAN and StudioGAN. If you use this code, please cite

@InProceedings{Li_2023_ICCV,
    author    = {Li, Shengxi and Zhang, Jialu and Li, Yifei and Xu, Mai and Deng, Xin and Li, Li},
    title     = {Neural Characteristic Function Learning for Conditional Image Generation},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2023},
    pages     = {7204-7214}
}