AIGA!nimation

Generative & Controllable
Character Animation

A collection of our research projects on learning generative priors for controllable, real-time character and hand motion.

SCA 2026

Prior-First, Condition-Second

Scalable and controllable hand motion completion. A prior-first framework that generates coherent, kinematically consistent hand motion from body motion in real time.

View project

SIGGRAPH 2024

Taming Diffusion Probabilistic Models for Character Control

A diffusion-based framework for real-time, responsive character control that produces high-quality and diverse character animations.

View project