PRIMARY SOURCE
NaP-Control: Navigating Diffusion Prior for Versatile and Fast Character Control
4 months, 1 week ago
Read source
NaP-Control uses reinforcement learning to steer a diffusion policy’s latent noise, aiming for whole-body character control that is both fast and robust. The approach skips iterative test-time guidance, which can cut inference cost while keeping motion natural. For teams building physics-based animation, that could mean more responsive control without sacrificing fidelity.
With your permission, GameDev.net uses analytics cookies to understand how people use the platform. You can accept analytics or continue with necessary cookies only. Learn more