cs.AI updates on arXiv.org 07月03日
There and Back Again: On the relation between Noise and Image Inversions in Diffusion Models
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文分析了DDIM逆变换在图像生成中的表现,提出以正向扩散过程替代部分逆变换步骤,提高生成图像质量。

arXiv:2410.23530v3 Announce Type: replace-cross Abstract: Diffusion Models achieve state-of-the-art performance in generating new samples but lack a low-dimensional latent space that encodes the data into meaningful features. Inversion-based methods address this by reversing the denoising trajectory, mapping each image back to its approximated starting noise. In this work, we thoroughly analyze this procedure and focus on the relation between the initial Gaussian noise, the generated samples, and their corresponding latent encodings obtained through the DDIM inversion. First, we show that latents exhibit structural patterns in the form of less diverse noise predicted for smooth image regions. As a consequence of this divergence, we present that the space of image inversions is notably less manipulative than the original Gaussian noise. Next, we explain the origin of the phenomenon, demonstrating that, during the first inversion steps, the noise prediction error is much more significant for the plain areas than for the rest of the image. As a surprisingly simple solution, we propose to replace the first DDIM Inversion steps with a forward diffusion process, which successfully decorrelates latent encodings, leading to higher quality editions and interpolations. The code is available at https://github.com/luk-st/taba.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

DDIM 图像生成 逆变换 扩散模型 数据特征
相关文章