MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model

arXiv:2404.19759v1 Announce Type: new
Abstract: This work introduces MotionLCM, extending controllable motion generation to a real-time level. Existing methods for spatial control in text-conditioned motion generation suffer from significant runtime inefficiency. To address this issue, we first propose the motion latent consistency model (MotionLCM) for motion generation, building upon the latent diffusion model (MLD). By employing one-step (or few-step) inference, we further improve the runtime efficiency of the motion latent diffusion model for motion generation. To ensure effective controllability, we …

abstract arxiv building consistency model control cs.cv issue real-time spatial text type via work