ColorEdit：基于扩散模型的无训练图像引导颜色编辑
ColorEdit: Training-free Image-Guided Color editing with diffusion model
AI总结：
本文提出了一种无需训练的图像引导颜色编辑方法ColorEdit，通过交叉注意力层的值矩阵对齐实现对象级颜色修改，并构建了首个颜色编辑基准COLORBENCH，在合成与真实图像上均优于现有方法。
摘要：
文本到图像（T2I）扩散模型凭借其令人印象深刻的生成能力，已被应用于图像编辑任务，展现出卓越的效能。然而，由于注意力泄漏以及对象的交叉注意力图与来自文本提示的新颜色属性之间的冲突，文本引导的图像编辑方法可能无法改变对象的颜色，导致生成图像与文本提示之间出现不一致。在本文中，我们对文本引导图像合成的过程以及不同交叉注意力块所学到的语义信息进行了深入分析。我们观察到，对象的视觉表示在去噪过程的早期阶段于扩散模型的上块中被确定，并且可以通过交叉注意力层中的值矩阵对齐来实现颜色调整。基于我们的发现，我们提出了一种简单、稳定且有效的图像引导方法，无需任何额外的微调或训练即可修改对象的颜色。最后，我们提出了一个名为 COLORBENCH 的基准数据集，这是首个用于评估颜色变化方法性能的基准。大量实验验证了我们的方法在对象级颜色编辑中的有效性，并在合成图像和真实图像上均超越了流行的文本引导图像编辑方法的性能。
英文摘要：
Text-to-image (T2I) diffusion models, with their impressive generative capabilities, have been adopted for image editing tasks, demonstrating remarkable efficacy. However, due to attention leakage and collision between the cross-attention map of the object and the new color attribute from the text prompt, text-guided image editing methods may fail to change the color of an object, resulting in a misalignment between the resulting image and the text prompt. In this paper, we conduct an in-depth analysis on the process of text-guided image synthesizing and what semantic information different cross-attention blocks have learned. We observe that the visual representation of an object is determined in the up-block of the diffusion model in the early stage of the denoising process, and color adjustment can be achieved through value matrices alignment in the cross-attention layer. Based on our findings, we propose a straightforward, yet stable, and effective image-guided method to modify the color of an object without requiring any additional fine-tuning or training. Lastly, we present a benchmark dataset called COLORBENCH, the first benchmark to evaluate the performance of color change methods. Extensive experiments validate the effectiveness of our method in object-level color editing and surpass the performance of popular text-guided image editing approaches in both synthesized and real images.
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。
