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

2026-07-08

AI Summary

Existing color transfer methods are often limited by inaccurate global mappings, semantic misalignment, and visual artifacts. This work proposes ColorFM, a novel framework that formulates color transfer as a flow-matching-based pixel distribution transport process. It constructs a velocity field through hierarchical color coupling guided by semantic priors and integrates online optimization with offline feedforward inference. Notably, the method innovatively leverages optimization trajectories to generate high-quality pseudo-supervised data for training an efficient feedforward network. Extensive experiments demonstrate that ColorFM surpasses state-of-the-art approaches in visual quality, structural fidelity, and semantic consistency, achieving both high accuracy and computational efficiency.

Abstract

Color transfer aims to align the color distribution of a source image with that of a reference image while preserving structural and semantic consistency. However, existing methods often suffer from inaccurate global mapping, semantic misalignment, and visual artifacts. To address these issues, we propose ColorFM, an optimization-to-learning framework. ColorFM connects online optimization to offline inference by reformulating color transfer as the transport of pixel distributions along velocity fields via Flow Matching. Specifically, we introduce ColorFM-O, an instance-specific optimization scheme that fits the velocity field through hierarchical color coupling guided by semantic priors. By numerically integrating the induced flow trajectories, ColorFM-O produces precise and semantically consistent color transfer results, while generating high-quality paired data as pseudo-supervision. Building upon this, we design ColorFM-L, an efficient feed-forward model trained on the generated pairs. Through implicit state modeling, ColorFM-L extracts deep semantic features to predict flow parameters for bidirectional linearized transport, ensuring accurate color transfer. Extensive experiments demonstrate that ColorFM-L outperforms state-of-the-art methods in visual quality, structural fidelity, and semantic consistency, successfully combining the accuracy of optimization with the speed of feed-forward inference.

Problem

• color transfer
• semantic alignment
• visual artifacts
• global mapping
• structural consistency

Innovation

• Flow Matching
• Color Transfer
• Optimization-to-Learning
• Semantic Consistency
• Velocity Field