Close

Presentation

CALM: Conditional Adversarial Latent Models for Directable Virtual Characters
DescriptionConditional Adversarial Latent Models (CALM) is a method for learning latent generative models for physical character animation. CALM learns a semantic representation for motion, allowing control over the generated motions and style-conditioning for higher-level training. Once trained, the character is controlled using intuitive controls akin to those in video games.
Event Type
Technical Paper
TimeWednesday, 9 August 202311:29am - 11:39am PDT
LocationPetree Hall C
Interest Areas
Research & Education
Recordings
Livestreamed
Recorded
Keywords
Animation/Simulation
Artificial Intelligence/Machine Learning
Registration Categories
FC
FCS
V
VS
EFC