Kavli Affiliate: David Muller | Summary:Motion Diffusion Models (MDMs) can generate diverse and visually appealing human motion; yet, the resulting trajectories frequently violate physical constraints, limiting their downstream use in simulation and control. We present PhysibleMDM, a framework that promotes physical feasibility of MDM output by optimizing at inference time the diffusion noise without retraining […]
Continue.. PhysibleMDM: Enforcing Inference-Time Physical Feasibility Constraints on Motion Diffusion Models via Noise Optimization