基于感知相似性引导与文本引导优化的引导扩散模型真实图像编辑
Perceptual Similarity guidance and text guidance optimization for Editing Real Images using Guided Diffusion Models
AI总结:
针对扩散模型图像编辑时修改图与源图差异大的问题,提出结合文本引导优化与感知相似性引导的双引导方法,实现编辑区域真实且未编辑区域高保真的图像编辑效果。
摘要:
使用扩散模型进行图像编辑时,修改后的图像有时会与源图像差异极大。为解决该问题,我们采用双引导方法,在未改动区域保持对原图的高保真度。首先,我们运用文本引导优化,借助文本嵌入引导隐空间与无分类器引导。其次,我们使用感知相似性引导,在反向过程中通过Tweedie公式利用后验采样优化隐向量。该方法既能保证编辑元素的真实渲染,又能保留原始图像未编辑的部分。
英文摘要:
When using a diffusion model for image editing, there are times when the modified image can differ greatly from the source. To address this, we apply a dual-guidance approach to maintain high fidelity to the original in areas that are not altered. First, we employ text-guided optimization, using text embeddings to direct latent space and classifier-free guidance. Second, we use perceptual similarity guidance, optimizing latent vectors with posterior sampling via Tweedie formula during the reverse process. This method ensures the realistic rendering of both the edited elements and the preservation of the unedited parts of the original image.
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。