MotionChain: Conversational Motion Controllers via Multimodal Prompts

arXiv:2404.01700v2 Announce Type: replace
Abstract: Recent advancements in language models have demonstrated their adeptness in conducting multi-turn dialogues and retaining conversational context. However, this proficiency remains largely unexplored in other multimodal generative models, particularly in human motion models. By integrating multi-turn conversations in controlling continuous virtual human movements, generative human motion models can achieve an intuitive and step-by-step process of human task execution for humanoid robotics, game agents, or other embodied systems. In this work, we present MotionChain, a conversational …

abstract arxiv context continuous conversational conversations cs.cv generative generative models however human language language models movements multimodal prompts type via virtual virtual human