Blurring Diffusion Models
This work provides a theoretical bridge for generative modeling researchers, but it is incremental as it builds on existing diffusion methods.
The paper tackles the problem of connecting blurring-based diffusion processes to Gaussian diffusion by showing their equivalence through non-isotropic noise, and proposes Blurring Diffusion Models that combine the strengths of both approaches.
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.