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: An Optimization-to-Learning Framework for Color Transfer via Flow Matching
  • Overview
  • Online Demos
  • Method
  • Quantitative Results
  • Image Color Transfer
  • Video Color Transfer
  • Citation

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

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.

Image Color Transfer

Video Color Transfer

Citation

If you find this work useful, please cite:

@misc{he2026ColorFM,
      title={ColorFM: An Optimization-to-Learning Framework for Color Transfer via Flow Matching}, 
      author={Yuhang He and Kai Zhang and Xiaoming Li and Du Chen and Jian Yang},
      year={2026},
      eprint={2607.07119},
      url={https://arxiv.org/abs/2607.07119}, 
}