arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.04489cs.CVcs.AI
收藏

SINE:基于文本到图像扩散模型的单图像编辑

SINE: SINgle Image Editing with Text-to-Image Diffusion Models

Rutgers University(罗格斯大学);Snap Inc.(Snap公司)

Zhixing Zhang, Ligong Han, Arnab Ghosh, Dimitris Metaxas, Jian Ren

AI总结:

提出SINE方法,通过模型引导和补丁微调,解决单图像编辑中的过拟合与信息泄漏问题,实现风格改变、内容添加和对象操作。

摘要:

近期关于扩散模型的研究工作已经展示了强大的条件图像生成能力,例如文本引导的图像合成。这一成功激发了许多尝试使用大规模预训练扩散模型来解决一个具有挑战性的问题——真实图像编辑。该领域的工作学习一个独特的文本标记,对应于包含同一对象的多个图像。然而,在许多情况下,只有一张图像可用,例如《戴珍珠耳环的少女》这幅画。使用现有的方法对预训练扩散模型进行单图像微调会导致严重的过拟合问题。预训练扩散模型的信息泄漏使得编辑无法在保持与给定图像相同内容的同时,创建由语言引导所描述的新特征。这项工作旨在解决单图像编辑的问题。我们提出了一种基于分类器无关引导的新型模型引导,使得从单图像训练的模型中获得的知识可以被蒸馏到预训练扩散模型中,即使只有一张给定图像也能实现内容创作。此外,我们提出了一种基于补丁的微调方法,可以有效帮助模型生成任意分辨率的图像。我们进行了大量实验来验证我们方法的设计选择,并展示了有前景的编辑能力,包括改变风格、添加内容和对象操作。代码可在 https://github.com/zhang-zx/SINE.git 上获取,供研究使用。

英文摘要:

Recent works on diffusion models have demonstrated a strong capability for conditioning image generation, e.g., text-guided image synthesis. Such success inspires many efforts trying to use large-scale pre-trained diffusion models for tackling a challenging problem--real image editing. Works conducted in this area learn a unique textual token corresponding to several images containing the same object. However, under many circumstances, only one image is available, such as the painting of the Girl with a Pearl Earring. Using existing works on fine-tuning the pre-trained diffusion models with a single image causes severe overfitting issues. The information leakage from the pre-trained diffusion models makes editing can not keep the same content as the given image while creating new features depicted by the language guidance. This work aims to address the problem of single-image editing. We propose a novel model-based guidance built upon the classifier-free guidance so that the knowledge from the model trained on a single image can be distilled into the pre-trained diffusion model, enabling content creation even with one given image. Additionally, we propose a patch-based fine-tuning that can effectively help the model generate images of arbitrary resolution. We provide extensive experiments to validate the design choices of our approach and show promising editing capabilities, including changing style, content addition, and object manipulation. The code is available for research purposes at https://github.com/zhang-zx/SINE.git .

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。

↑