Demystifying noise: The role of randomness in generative AI

Simple item page
dc.contributor.authorSingh, Gurpriten_US
dc.contributor.authorHuang, Xingchangen_US
dc.contributor.authorVandersanden, Jenteen_US
dc.contributor.authorOztireli, Cengizen_US
dc.contributor.authorMitra, Niloyen_US
dc.contributor.editorMantiuk, Rafalen_US
dc.contributor.editorHildebrandt, Klausen_US
dc.date.accessioned2025-05-09T08:59:02Z
dc.date.available2025-05-09T08:59:02Z
dc.date.issued2025
dc.description.abstractThis 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.en_US
dc.description.sectionheadersTutorials
dc.description.seriesinformationEurographics 2025 - Tutorials
dc.identifier.doi10.2312/egt.20251004
dc.identifier.isbn978-3-03868-267-7
dc.identifier.issn1017-4656
dc.identifier.pages5 pages
dc.identifier.urihttps://doi.org/10.2312/egt.20251004
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/egt20251004
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Machine learning approaches; Rendering
dc.subjectComputing methodologies → Machine learning approaches
dc.subjectRendering
dc.titleDemystifying noise: The role of randomness in generative AIen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
egt20251004.pdf
Size:
5.31 MB
Format:
Adobe Portable Document Format
Download
Collections
EG 2025 - Tutorials