Skip to yearly menu bar Skip to main content


Invited Talk
in
Workshop: Text, camera, action! Frontiers in controllable video generation

Sander Dieleman - Wading through the noise: an intuitive look at diffusion models

Sander Dieleman

[ ]
Sat 27 Jul 5:30 a.m. PDT — 6:10 a.m. PDT

Abstract:

Diffusion models come in many shapes and forms, and research papers tend to describe this class of models in a variety of different ways, which can be confusing. In this talk, we'll look at the intuition behind diffusion models, and why they work so well for audiovisual generative modelling in particular, with a focus on video generation.

Chat is not available.