in2IN: Leveraging individual Information to Generate Human INteractions
This work addresses a challenging task in robotics, gaming, and animation by improving motion generation diversity and control, though it is incremental as it builds on existing datasets and methods.
The paper tackles the problem of generating diverse and coherent human-human motion interactions from text by introducing in2IN, a diffusion model conditioned on both overall and individual action descriptions, which achieves state-of-the-art performance on the InterHuman dataset, and DualMDM, a technique that enhances intra-personal diversity while maintaining inter-personal coherence.
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 this, we introduce in2IN, a novel diffusion model for human-human motion generation which is conditioned not only on the textual description of the overall interaction but also on the individual descriptions of the actions performed by each person involved in the interaction. To train this model, we use a large language model to extend the InterHuman dataset with individual descriptions. As a result, in2IN achieves state-of-the-art performance in the InterHuman dataset. Furthermore, in order to increase the intra-personal diversity on the existing interaction datasets, we propose DualMDM, a model composition technique that combines the motions generated with in2IN and the motions generated by a single-person motion prior pre-trained on HumanML3D. As a result, DualMDM generates motions with higher individual diversity and improves control over the intra-person dynamics while maintaining inter-personal coherence.