ColorFM: An Optimization-to-Learning Framework for Color Transfer via Flow Matching

Yuhang He¹, Kai Zhang^1,†, Xiaoming Li¹, Du Chen², Jian Yang¹

¹Nanjing University, China    ²VIVO BlueImage Lab, China
^†Corresponding author

ECCV 2026

ColorFM image color transfer (left) and video color transfer (right).

🚀 Explore more application results: Image Color Transfer  |  Video Color Transfer

---

Table of Contents

• ColorFM: An Optimization-to-Learning Framework for Color Transfer via Flow Matching
  • Overview
  • Online Demos
  • Image Color Transfer
  • Video Color Transfer
  • Method
  • Quantitative Results
  • Installation
  • Testing/Training
  • Acknowledgements
  • Citation
  • License

Overview

ColorFM is an optimization-to-learning framework for accurate and semantically consistent color transfer. It connects instance-specific optimization with efficient feed-forward inference through two complementary variants: ColorFM-O and ColorFM-L.

Online Demos

Method	Type	Demo
ColorFM-O	Optimization-based	Try online
ColorFM-L	Learning-based	Try online

Image Color Transfer

Video Color Transfer

Method

ColorFM formulates color transfer as transporting pixel distributions along velocity fields via Flow Matching. ColorFM-O optimizes an instance-specific velocity field with semantic guidance, while ColorFM-L learns from the generated pairs to provide efficient feed-forward inference.

Overview of the ColorFM-O and ColorFM-L frameworks.

Quantitative Results

The following table compares ColorFM with existing color transfer methods in terms of similarity, Lipschitz constant, and inference time. All results are evaluated at an image resolution of 512 x 512.

Installation

Create an environment and install the dependencies from the repository root:

conda create -n ColorFM python=3.10 -y
conda activate ColorFM
pip install torch torchvision
pip install -r requirements.txt

Install the PyTorch build that matches your CUDA version when GPU acceleration is required. xFormers can optionally accelerate ColorFM-L on supported CUDA environments.

Download the pretrained ColorFM-L checkpoint from Hugging Face and place it under the repository-level checkpoints folder. ColorFM-O does not require a pretrained checkpoint.

Testing/Training

Guide	Description
Testing	Run the ColorFM-O and ColorFM-L image or video WebUIs.
Training	Generate ColorFM-O training pairs, train ColorFM-L, and run evaluation.

Acknowledgements

This project builds upon the open-source implementations of DINOv2 by Meta AI.

Citation

If you find this work useful, please cite:

@inproceedings{he2026colorfm,
    title={ColorFM: An Optimization-to-Learning Framework for Color Transfer via Flow Matching},
    author={He, Yuhang and Zhang, Kai and Li, Xiaoming and Chen, Du and Yang, Jian},
    booktitle={European Conference on Computer Vision},
    year={2026}
}

License

This project is released under the Apache License 2.0.