in2IN icon indicating copy to clipboard operation
in2IN copied to clipboard

Published 20 hours ago • verified publisher icon pabloruizponce
→

Metadata

[CVPRW 2024] Official Implementation of "in2IN: Leveraging individual Information to Generate Human INteractions".

in2IN:Leveraging individual Information to Generate Human INteractions

Project arXiv


🔎 About

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.

📌 News

  • [2024-04-16] Our paper is available on arXiv
  • [2024-04-06] in2IN is now accepted at CVPR 2024 Workshop HuMoGen!

📝 TODO List

  • [ ] Release code
  • [ ] Release model weights
  • [ ] Release individual descriptions from InterHuman dataset.
  • [ ] Release visualization code.

📚 Citation

If you find our work helpful, please cite:

@misc{ponce2024in2in,
      title={in2IN: Leveraging individual Information to Generate Human INteractions}, 
      author={Pablo Ruiz Ponce and German Barquero and Cristina Palmero and Sergio Escalera and Jose Garcia-Rodriguez},
      year={2024},
      eprint={2404.09988},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

← Metadata

41
Stars
1
Forks
Watchers

Owner

verified publisher icon pabloruizponce

Metadata

[CVPRW 2024] Official Implementation of "in2IN: Leveraging individual Information to Generate Human INteractions".

Back