
Automated spatial composition of 3D human motions using GPT-guided synthetic data improves generation quality.


coremsg

spatial-composition-of-3d-human-motions-for-simultaneous-action-generation


Spatial Composition of 3D Human Motions for Simultaneous Action Generation



ReMoS presents a novel approach for generating realistic 3D reactive motions in two-person interactions, enhancing animation pipelines.



ReMoS: 3D Motion-Conditioned Reaction Synthesis for Two-Person Interactions
