Demystifying noise: The role of randomness in generative AI
Loading...
Date
2025
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
This tutorial offers a thorough exploration of the role of randomness in generative AI, leveraging foundational knowledge from statistical physics, stochastic differential equations, and computer graphics. By connecting these disciplines, the tutorial aims to provide participants with a deep understanding of how noise impacts generative modeling and introduce state-of-the-art techniques and applications of noise in AI. First, we revisit the mathematical concepts essential for understanding diffusion and the integral role of noise in diffusion-based generative modeling. In the second part of the tutorial, we introduce the various types of noises studied within the computer graphics community and present their impact on rendering, texture synthesis and content creation. In the last part, we will look at how different noise correlations and noise schedulers impact the expressive power of image and video generation models. By the end of the tutorial, participants will gain an in-depth understanding of the mathematical constructs for diffusion models and how noise correlations can play an important role in enhancing the diversity and expressiveness of these models. The audience will also learn to code these noises developed in the graphics literature and their impact on generative modeling. The tutorial is aimed for students, researchers and practitioners, with our panel members bringing insights from the industry. All the materials related to the tutorial will be available on diffusion-noise.mpi-inf.mpg.de.
Description
CCS Concepts: Computing methodologies → Machine learning approaches; Rendering
@inproceedings{10.2312:egt.20251004,
booktitle = {Eurographics 2025 - Tutorials},
editor = {Mantiuk, Rafal and Hildebrandt, Klaus},
title = {{Demystifying noise: The role of randomness in generative AI}},
author = {Singh, Gurprit and Huang, Xingchang and Vandersanden, Jente and Oztireli, Cengiz and Mitra, Niloy},
year = {2025},
publisher = {The Eurographics Association},
ISSN = {1017-4656},
ISBN = {978-3-03868-267-7},
DOI = {10.2312/egt.20251004}
}