Seamless Human Motion Composition with Blended Positional Encodings

arXiv:2402.15509v1 Announce Type: new
Abstract: Conditional human motion generation is an important topic with many applications in virtual reality, gaming, and robotics. While prior works have focused on generating motion guided by text, music, or scenes, these typically result in isolated motions confined to short durations. Instead, we address the generation of long, continuous sequences guided by a series of varying textual descriptions. In this context, we introduce FlowMDM, the first diffusion-based model that generates seamless Human Motion Compositions (HMC) …

abstract applications arxiv cs.cv gaming human music prior reality robotics text type virtual virtual reality