InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction

arXiv:2403.19652v1 Announce Type: new
Abstract: Text-conditioned human motion generation has experienced significant advancements with diffusion models trained on extensive motion capture data and corresponding textual annotations. However, extending such success to 3D dynamic human-object interaction (HOI) generation faces notable challenges, primarily due to the lack of large-scale interaction data and comprehensive descriptions that align with these interactions. This paper takes the initiative and showcases the potential of generating human-object interactions without direct training on text-interaction pair data. Our key insight …

abstract annotations arxiv challenges cs.ai cs.cv data diffusion diffusion models dynamic however human motion capture object scale success text text to 3d textual type zero-shot