ColorFLUX：一种用于老照片上色的结构-颜色解耦框架
ColorFLUX: A Structure-Color Decoupling Framework for Old Photo Colorization
将结构保持与颜色恢复解耦，并利用视觉语义提示替代文本提示来消除老照片的颜色偏差，为图像上色和可控生成提供了可复用的条件控制思路。
原文依据 we propose a novel old photo colorization framework based on the generative diffusion model FLUX
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论老照片保存着珍贵的历史记忆，因此其修复和上色非常必要。现有修复模型可以解决一些退化问题，如去噪和划痕去除，但往往难以实现准确的上色。这一局限源于老照片特有的退化，如亮度褪色和色调改变，这些退化与现代照片分布不同，在上色过程中造成显著的域间差距。本文提出了一种基于生成扩散模型FLUX的新型老照片上色框架。我们的方法引入结构-颜色解耦策略，将结构保持与颜色恢复分离，在保持结构一致性的同时实现老照片的准确上色。我们进一步通过渐进式直接偏好优化（Pro-DPO）策略增强模型，该策略使模型能够通过颜色增强中从粗到细的过渡学习细微的颜色偏好。此外，我们通过引入视觉语义提示来解决基于文本提示的局限性，该提示直接从老照片中提取细粒度语义信息，有助于消除老照片中固有的颜色偏差。在合成和真实数据集上的实验结果表明，我们的方法优于现有的最优上色方法，包括闭源商业模型，能够产生高质量且生动的上色效果。
英文原文摘要 1508 字符
Old photos preserve invaluable historical memories, making their restoration and colorization highly desirable. While existing restoration models can address some degradation issues like denoising and scratch removal, they often struggle with accurate colorization.This limitation arises from the unique degradation inherent in old photos, such as faded brightness and altered color hues, which are different from modern photo distributions, creating a substantial domain gap during colorization. In this paper, we propose a novel old photo colorization framework based on the generative diffusion model FLUX. Our approach introduces a structure-color decoupling strategy that separates structure preservation from color restoration, enabling accurate colorization of old photos while maintaining structural consistency. We further enhance the model with a progressive Direct Preference Optimization (Pro-DPO) strategy, which allows the model to learn subtle color preferences through coarse-to-fine transitions in color augmentation. Additionally, we address the limitations of text-based prompts by introducing visual semantic prompts, which extract fine-grained semantic information directly from old photos, helping to eliminate the color bias inherent in old photos. Experimental results on both synthetic and real datasets demonstrate that our approach outperforms existing state-of-the-art colorization methods, including closed-source commercial models, producing high-quality and vivid colorization.