flâneur — a map of the web's best reading

Diffusion is spectral autoregression – Sander Dieleman

sander.ai · 5,617 words · saved by 12 readers

A deep dive into spectral analysis of diffusion models of images, revealing how they implicitly perform a form of autoregression in the frequency domain.

A bit of signal processing swiftly reveals that diffusion models and autoregressive models aren’t all that different: diffusion models of images perform approximate autoregression in the frequency domain! This blog post is also available as a Python notebook in Google Colab , with the code used to produce all the plots and animations. Last year, I wrote a blog post describing various different perspectives on diffusion . The idea was to highlight a number of connections between diffusion models and other classes of models and concepts. In recent months, I have given a few talks where I discuss

Explore this link on the map →

saved by

related reading