Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

关于模型振幅保持能力 #69

Open
xiaojiebangbang opened this issue Dec 13, 2023 · 4 comments
Open

关于模型振幅保持能力 #69

xiaojiebangbang opened this issue Dec 13, 2023 · 4 comments

Comments

@xiaojiebangbang
Copy link

作者您好,我想用latentRefusion做信号去噪,但是发现结果的细节恢复能力很好,但是幅度保持能力较差,各个频率的信号都有衰减,您对这个模型了解更加深入,请问应该是什么原因导致这样的结果呢?期待您的回复!

@Algolzw
Copy link
Owner

Algolzw commented Dec 13, 2023

你好,latent-refusion本身确实会降低图像生成的性能(我猜测unet和refusion是分开训的,并不能保证refusion生成的latent正好是unet的latent因此会有一定误差)。如果你想做信号去高斯噪声的话可能尝试denoising-ode,这个模型是专门用于高斯降噪的。

@xiaojiebangbang
Copy link
Author

xiaojiebangbang commented Dec 13, 2023 via email

@Algolzw
Copy link
Owner

Algolzw commented Dec 13, 2023

目前只能是高斯噪声= =,想去除任意噪声还是用IR-SDE或者Refusion吧。

@xiaojiebangbang
Copy link
Author

xiaojiebangbang commented Dec 13, 2023 via email

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants