# Color Transfer with Modulated Flows

arXiv: https://arxiv.org/abs/2503.19062 · HTML: https://mlsanity.com/paper/2503.19062/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 17 of its 35 references that are in the map.
- First posted on arXiv 24 Mar 2025.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 17 of 17)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [Universal Style Transfer via Feature Transforms](https://mlsanity.com/paper/1705.08086/) (2017)
- [Deep Photo Style Transfer](https://mlsanity.com/paper/1703.07511/) (2017)
- [Photorealistic Style Transfer via Wavelet Transforms](https://mlsanity.com/paper/1903.09760/) (2019)
- [A Closed-form Solution to Photorealistic Image Stylization](https://mlsanity.com/paper/1802.06474/) (2018)
- [DepthFM: Fast Monocular Depth Estimation with Flow Matching](https://mlsanity.com/paper/2403.13788/) (2024)
- [Domain-Aware Universal Style Transfer](https://mlsanity.com/paper/2108.04441/) (2021)
- [Ultrafast Photorealistic Style Transfer via Neural Architecture Search](https://mlsanity.com/paper/1912.02398/) (2019)
- [PIRM Challenge on Perceptual Image Enhancement on Smartphones: Report](https://mlsanity.com/paper/1810.01641/) (2018)
- [Neural Preset for Color Style Transfer](https://mlsanity.com/paper/2303.13511/) (2023)
- [PhotoWCT2: Compact Autoencoder for Photorealistic Style Transfer Resulting from Blockwise Training and Skip Connections of High-Frequency Residuals](https://mlsanity.com/paper/2110.11995/) (2021)
- [Deep Preset: Blending and Retouching Photos with Color Style Transfer](https://mlsanity.com/paper/2007.10701/) (2020)
- [Optimal Image Transport on Sparse Dictionaries](https://mlsanity.com/paper/2311.01984/) (2023)

## Built on by (most cited first, 7 of 7)

- [Personalized Image Filter: Mastering Your Photographic Style](https://mlsanity.com/paper/2510.16791/) (2025)
- [AceTone: Bridging Words and Colors for Conditional Image Grading](https://mlsanity.com/paper/2604.00530/) (2026)
- [Towards In-Context Tone Style Transfer with A Large-Scale Triplet Dataset](https://mlsanity.com/paper/2604.16114/) (2026)
- [ReSWD: ReSTIR'd, not shaken. Combining Reservoir Sampling and Sliced Wasserstein Distance for Variance Reduction](https://mlsanity.com/paper/2510.01061/) (2025)
- [Histogram-constrained Image Generation](https://mlsanity.com/paper/2606.31683/) (2026)
- [ColorFM: An Optimization-to-Learning Framework for Color Transfer via Flow Matching](https://mlsanity.com/paper/2607.07119/) (2026)
- [Simple, Safe, and Overlooked: Reclaiming Sustainable Domain Generalization with Statistical Color Matching](https://mlsanity.com/paper/2608.18915/) (2026)

## Abstract (arXiv)

In this work, we introduce Modulated Flows (ModFlows), a novel approach for color transfer between images based on rectified flows. The primary goal of the color transfer is to adjust the colors of a target image to match the color distribution of a reference image. Our technique is based on optimal transport and executes color transfer as an invertible transformation within the RGB color space. The ModFlows utilizes the bijective property of flows, enabling us to introduce a common intermediate color distribution and build a dataset of rectified flows. We train an encoder on this dataset to predict the weights of a rectified model for new images. After training on a set of optimal transport plans, our approach can generate plans for new pairs of distributions without additional fine-tuning. We additionally show that the trained encoder provides an image embedding, associated only with its color style. The presented method is capable of processing 4K images and achieves the state-of-the-art performance in terms of content and style similarity. Our source code is available at https://github.com/maria-larchenko/modflows