We introduced in2IN to generate more realistic human interactions leveraging individual information. And we also introduce DualMDM a model compostion technique that allows to combien interactions models with individual priors to increase the diversity and controllability.
In this thesis, we introduce a novel Diffusion Model incorporating a Transformer-based architecture. This model is conditioned using textual descriptions of both the motion interactions and the individual motions within these interactions. By focusing on the individual components of the interaction, our method achieves more precise conditioning in the generation of these specific motions. Concurrently, the textual descriptions of the overall interaction enable our model to effectively capture the interplay between individual motions.