FDL-pytorch 1.0

Frequency Distribution Loss (FDL) for misalignment data

Frequency Distribution Loss (FDL) for misaligned data

The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

Zhangkai Ni, Juncheng Wu, Zian Wang, Wenhan Yang, Hanli Wang, Lin Ma

This repository provides the official PyTorch implementation for the paper “Misalignment-Robust Frequency Distribution Loss for Image Transformation”, CVPR-2024. Paper

About FDL

A novel Frequency Distribution Loss (FDL) for image transformation models trained with misaligned data, opening up new avenues for addressing the broad issue of misalignment in image transformation tasks.

Quick Start

Installation:

pip install fdl-pytorch

Requirements:

• Python>=3.6
• Pytorch>=1.0

Usage:

from FDL_pytorch import FDL_loss
fdl_loss = FDL_loss()
# X: (N,C,H,W) 
# Y: (N,C,H,W) 
loss_value = fdl_loss(X, Y)
loss_value.backward()

Citation

If you find our work useful, please cite it as

@article{ni2024misalignment,
  title={Misalignment-Robust Frequency Distribution Loss for Image Transformation},
  author={Ni, Zhangkai and Wu, Juncheng and Wang, Zian and Yang, Wenhan and Wang, Hanli and Ma, Lin},
  journal={arXiv preprint arXiv:2402.18192},
  year={2024}
}

Contact

Thanks for your attention! If you have any suggestion or question, feel free to leave a message here or contact Dr. Zhangkai Ni ([e-mail]).

License

MIT License