Search papers, labs, and topics across Lattice.
This paper introduces ColorFM, an innovative optimization-to-learning framework for color transfer that addresses common pitfalls in existing methods, such as inaccurate global mapping and visual artifacts. By reformulating the problem as the transport of pixel distributions along velocity fields through Flow Matching, the authors present ColorFM-O, which utilizes instance-specific optimization guided by semantic priors to achieve precise color transfer. The subsequent ColorFM-L model leverages high-quality paired data generated by ColorFM-O to efficiently predict flow parameters, resulting in superior visual quality and semantic consistency compared to state-of-the-art approaches.
ColorFM achieves a breakthrough in color transfer by seamlessly integrating optimization with learning, delivering unmatched visual quality and semantic fidelity.
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.
