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

• URL: http://arxiv.org/abs/2607.07119v1
• Date: Wed, 08 Jul 2026 08:01:15 GMT
• Title: ColorFM: An Optimization-to-Learning Framework for Color Transfer via Flow Matching
• Abstract summary: We propose ColorFM, an optimization-to-learning framework for color transfer.<n> ColorFM connects online optimization to offline inference by reformulating color transfer as the transport of pixel distributions.<n>We show that ColorFM-L outperforms state-of-the-art methods in visual quality, structural fidelity, and semantic consistency.
• Score: 38.73819453939708
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Retrieval-Augmented Generation-Based Color Restoration for Low-Light Image Enhancement [0.0]
  We recast color restoration as an independent sub-problem, realizing it as a general-purpose post-processing module built on retrieval-augmented generation (RAG)<n>The design has three components: (i) a dual-index FAISS retriever built on intermediate VGG19 features, capturing textural and structural similarity through global mean and variance statistics; (ii) GlobalSPHistAdaIN, which reduces the reference spatial-preserving color histogram to a global color vector and modulates network features via adaptive instance normalization; and (iii) a residual formulation that predicts a color correction over the front-end output.
  arXiv  Detail & Related papers  (2026-08-08T16:12:12Z)
• FreeInpaint: Tuning-free Prompt Alignment and Visual Rationality Enhancement in Image Inpainting [98.04041133839088]
  Text-guided image inpainting endeavors to generate new content within specified regions of images using textual prompts from users.<n>We introduce FreeInpaint, a plug-and-play tuning-free approach that directly optimize the diffusion latents on the fly during inference to improve the faithfulness of the generated images.
  arXiv  Detail & Related papers  (2025-12-24T11:06:26Z)
• Edit2Perceive: Image Editing Diffusion Models Are Strong Dense Perceivers [55.15722080205737]
  Edit2Perceive is a unified diffusion framework that adapts editing models for depth, normal, and matting.<n>Our single-step deterministic inference yields up to faster runtime while training on relatively small datasets.
  arXiv  Detail & Related papers  (2025-11-24T01:13:51Z)
• Improving Progressive Generation with Decomposable Flow Matching [50.63174319509629]
  Decomposable Flow Matching (DFM) is a simple and effective framework for the progressive generation of visual media.<n>On Imagenet-1k 512px, DFM achieves 35.2% improvements in FDD scores over the base architecture and 26.4% over the best-performing baseline.
  arXiv  Detail & Related papers  (2025-06-24T17:58:02Z)
• Color Transfer with Modulated Flows [41.94295877935867]
  Modulated Flows is a novel approach for color transfer between images based on rectified flows.<n>Our technique is based on optimal transport and executes color transfer as an invertible transformation within the RGB color space.<n>The presented method is capable of processing 4K images and achieves the state-of-the-art performance in terms of content and style similarity.
  arXiv  Detail & Related papers  (2025-03-24T18:39:54Z)
• Leveraging Semantic Attribute Binding for Free-Lunch Color Control in Diffusion Models [53.73253164099701]
  We introduce ColorWave, a training-free approach that achieves exact RGB-level color control in diffusion models without fine-tuning.<n>We demonstrate that ColorWave establishes a new paradigm for structured, color-consistent diffusion-based image synthesis.
  arXiv  Detail & Related papers  (2025-03-12T21:49:52Z)
• LTCF-Net: A Transformer-Enhanced Dual-Channel Fourier Framework for Low-Light Image Restoration [1.049712834719005]
  We introduce LTCF-Net, a novel network architecture designed for enhancing low-light images. Our approach utilizes two color spaces - LAB and YUV - to efficiently separate and process color information. Our model incorporates the Transformer architecture to comprehensively understand image content.
  arXiv  Detail & Related papers  (2024-11-24T07:21:17Z)
• Consistency Flow Matching: Defining Straight Flows with Velocity Consistency [97.28511135503176]
  We introduce Consistency Flow Matching (Consistency-FM), a novel FM method that explicitly enforces self-consistency in the velocity field. Preliminary experiments demonstrate that our Consistency-FM significantly improves training efficiency by converging 4.4x faster than consistency models.
  arXiv  Detail & Related papers  (2024-07-02T16:15:37Z)
• Wavelet Transform-assisted Adaptive Generative Modeling for Colorization [15.814591440291652]
  This study presents a novel scheme that exploiting the score-based generative model in wavelet domain to address the issue. By taking advantage of the multi-scale and multi-channel representation via wavelet transform, the proposed model learns the priors from stacked wavelet coefficient components. Experiments demonstrated remarkable improvements of the proposed model on colorization quality, particularly on colorization robustness and diversity.
  arXiv  Detail & Related papers  (2021-07-09T07:12:39Z)
• Example-based Color Transfer with Gaussian Mixture Modeling [16.880968031370767]
  We model color transfer under a probability framework and cast it as a parameter estimation problem. We employ the Expectation-Maximization (EM) algorithm (E-step and M-step) for optimization. Our method is able to generate continuous color transfer results with increasing EM iterations.
  arXiv  Detail & Related papers  (2020-08-31T14:07:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.