in2IN: Leveraging individual Information to Generate Human INteractions

arXiv:2404.09988v1 Announce Type: new
Abstract: Generating human-human motion interactions conditioned on textual descriptions is a very useful application in many areas such as robotics, gaming, animation, and the metaverse. Alongside this utility also comes a great difficulty in modeling the highly dimensional inter-personal dynamics. In addition, properly capturing the intra-personal diversity of interactions has a lot of challenges. Current methods generate interactions with limited diversity of intra-person dynamics due to the limitations of the available datasets and conditioning strategies. For …

abstract animation application arxiv cs.cv diversity dynamics gaming generate human human interactions information interactions metaverse modeling robotics textual the metaverse type utility