论文标题
模糊扩散模型
Blurring Diffusion Models
论文作者
论文摘要
最近，Rissanen等人（2022年）提出了一种基于热量耗散或模糊的生成建模的新型扩散过程，作为各向同性高斯扩散的替代方法。在这里，我们表明，通过具有非异型噪声的高斯扩散过程可以等效地定义模糊。在建立这一联系时，我们弥合了反热量耗散和降解扩散之间的缝隙，并阐明了由于这种建模选择而导致的电感偏差。最后，我们提出了一类普遍的扩散模型，该模型既可以提供标准高斯脱氧扩散和逆热散热的最佳，我们称之为模糊的扩散模型。
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.
