Generating 3D Models with Diffusion - Computerphile
Summary
This video from Computerphile explains the technical details of how 2D diffusion models can be adapted to generate 3D models, particularly when 3D datasets are limited. It is highly valuable for students and educators seeking to deepen their understanding of advanced generative AI and machine learning concepts.
Description
When the 3D dataset is too small to create models of frogs on stilts we have to think of a different way - Lewis Stuart is based at the University of Nottingham and explains how you can use 2D diffusion to create 3D models. Computerphile is supported by Jane Street. Learn more about them (and exciting career opportunities) at: https://jane-st.co/computerphile This video was filmed and edited by Sean Riley. Computerphile is a sister project to Brady Haran's Numberphile. More at https://www.bradyharanblog.com
