arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.05557cs.LGcs.CVstat.ML
收藏

模糊扩散模型

Blurring Diffusion Models

Google Research(谷歌研究院);Amsterdam(阿姆斯特丹)

Emiel Hoogeboom, Tim Salimans

AI总结:

本文证明模糊化等价于非各向同性噪声的高斯扩散,弥合了逆热耗散与去噪扩散的差距,并提出兼具两者优点的模糊扩散模型。

摘要:

最近,Rissanen等人(2022)提出了一种基于热耗散(即模糊化)的新型扩散过程用于生成建模,作为各向同性高斯扩散的替代方案。在此,我们证明模糊化可以等价地通过具有非各向同性噪声的高斯扩散过程来定义。通过建立这一联系,我们弥合了逆热耗散与去噪扩散之间的差距,并阐明了这种建模选择所产生的归纳偏置。最后,我们提出了一类广义扩散模型,它兼具标准高斯去噪扩散和逆热耗散两者的优点,我们称之为模糊扩散模型(Blurring Diffusion Models)。

英文摘要:

Recently, Rissanen et al., (2022) have presented a new type of diffusion process for generative modeling based on heat dissipation, or blurring, as an alternative to isotropic Gaussian diffusion. Here, we show that blurring can equivalently be defined through a Gaussian diffusion process with non-isotropic noise. In making this connection, we bridge the gap between inverse heat dissipation and denoising diffusion, and we shed light on the inductive bias that results from this modeling choice. Finally, we propose a generalized class of diffusion models that offers the best of both standard Gaussian denoising diffusion and inverse heat dissipation, which we call Blurring Diffusion Models.

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。

↑