Presentation

<
Towards AI-Driven 3D Creation at the Speed of Thought
SessionML in Production
DescriptionHow can generative AI seamlessly integrate into professional 3D workflows? This talk explores how vision-language models (VLMs) can automate tedious editing tasks, generate structured 3D scenes, and perform object placement while preserving editability. I’ll discuss key findings, open challenges, and future applications across industries like robotics, game design, and VFX.
Contributor
Ian Huang
Stanford University
Event Type
Talk
TimeThursday, 14 August 20252:44pm - 3:06pm PDT
LocationWest Building, Rooms 109-110
Session TimeThursday, 14 August 20252:00pm - 3:30pm PDT
LocationWest Building, Rooms 109-110
Interest Areas
Arts & Design
New Technologies
Research & Education
Recordings
Livestreamed
Recorded
Keywords
Artificial Intelligence/Machine Learning
Generative AI
Geometry
Pipeline Tools and Work
Next PresentationNext PresentationTowards automated corrections in video-driven animation transfer
Similar Presentations
Demystifying Noise: Role of Randomness in Generative AI
Hands-On Class: Implementing SOTA Generative AI Pipelines in Your 3D Application
Hands-On Class: Introduction To Generative Machine Learning