DIFFNAT: Improving Diffusion Image Quality Using Natural Image Statistics.
CoRR(2023)
摘要
Diffusion models have advanced generative AI significantly in terms of
editing and creating naturalistic images. However, efficiently improving
generated image quality is still of paramount interest. In this context, we
propose a generic "naturalness" preserving loss function, viz., kurtosis
concentration (KC) loss, which can be readily applied to any standard diffusion
model pipeline to elevate the image quality. Our motivation stems from the
projected kurtosis concentration property of natural images, which states that
natural images have nearly constant kurtosis values across different band-pass
versions of the image. To retain the "naturalness" of the generated images, we
enforce reducing the gap between the highest and lowest kurtosis values across
the band-pass versions (e.g., Discrete Wavelet Transform (DWT)) of images. Note
that our approach does not require any additional guidance like classifier or
classifier-free guidance to improve the image quality. We validate the proposed
approach for three diverse tasks, viz., (1) personalized few-shot finetuning
using text guidance, (2) unconditional image generation, and (3) image
super-resolution. Integrating the proposed KC loss has improved the perceptual
quality across all these tasks in terms of both FID, MUSIQ score, and user
evaluation.
更多查看译文
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要