重新着色所关注的：通过令牌级扩散实现区域感知的着色编辑
Recolour What Matters: Region-Aware Colour Editing via Token-Level Diffusion
AI总结：
本文提出ColourCrafter框架，通过令牌级融合RGB颜色和图像令牌，在潜在空间中实现区域感知的着色生成，提升细粒度着色编辑的准确性和可控性。
摘要：
颜色是图像生成中最具感知显著性但最难以控制的属性之一。尽管最近的扩散模型可以根据用户指令修改物体颜色，但其结果往往偏离预期色调，尤其是对于细粒度和局部编辑。早期基于文本的方法依赖于离散的语言描述，无法准确表示连续的色度变化。为克服这一限制，我们提出了ColourCrafter，一个统一的扩散框架，将颜色编辑从全局色调转移转变为结构化、区域感知的生成过程。与传统颜色驱动方法不同，ColourCrafter在潜在空间中对RGB颜色令牌和图像令牌进行令牌级融合，选择性地将颜色信息传播到语义相关区域，同时保持结构保真度。一个感知Lab空间损失进一步通过解耦亮度和色度，并约束编辑在遮蔽区域内，提升像素级精度。此外，我们构建了ColourfulSet，一个大规模的高质量图像对数据集，具有连续且多样的颜色变化。广泛实验表明，ColourCrafter在细粒度着色编辑中实现了最先进的颜色准确性、可控性和感知保真度。我们的项目可在https://yangyuqi317.github.io/ColourCrafter.github.io/上获得。
英文摘要：
Colour is one of the most perceptually salient yet least controllable attributes in image generation. Although recent diffusion models can modify object colours from user instructions, their results often deviate from the intended hue, especially for fine-grained and local edits. Early text-driven methods rely on discrete language descriptions that cannot accurately represent continuous chromatic variations. To overcome this limitation, we propose ColourCrafter, a unified diffusion framework that transforms colour editing from global tone transfer into a structured, region-aware generation process. Unlike traditional colour driven methods, ColourCrafter performs token-level fusion of RGB colour tokens and image tokens in latent space, selectively propagating colour information to semantically relevant regions while preserving structural fidelity. A perceptual Lab-space Loss further enhances pixel-level precision by decoupling luminance and chrominance and constraining edits within masked areas. Additionally, we build ColourfulSet, a largescale dataset of high-quality image pairs with continuous and diverse colour variations. Extensive experiments demonstrate that ColourCrafter achieves state-of-the-art colour accuracy, controllability and perceptual fidelity in fine-grained colour editing. Our project is available at https://yangyuqi317.github.io/ColourCrafter.github.io/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
