Skip to yearly menu bar Skip to main content


In-Person Poster presentation / poster accept

Blurring Diffusion Models

Emiel Hoogeboom · Tim Salimans

MH1-2-3-4 #75

Keywords: [ diffusion ] [ blurring ] [ generative model ] [ Generative models ]


Abstract:

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.

Chat is not available.