Generating realistic character animations is of great importance in computer graphics and related domains. Existing approaches for this application involve a significant amount of human interaction. In this paper, we introduce a system that maps a natural language description to an animation of a humanoid skeleton. Our system is a sequence-to-sequence model that is pretrained with an autoencoder objective and then trained end-to-end.

PDF

In Proceedings of the Visually Grounded Interaction and Language Workshop at NeurIPS 2018, December 2018.

@inproceedings{lin:vigil18, title={Generating Animated Videos of Human Activities from Natural Language Descriptions}, author={Angela S. Lin and Lemeng Wu and Rodolfo Corona , Kevin Tai , Qixing Huang , Raymond J. Mooney}, booktitle={Proceedings of the Visually Grounded Interaction and Language Workshop at NeurIPS 2018}, month={December}, url="http://www.cs.utexas.edu/users/ai-labpub-view.php?PubID=127730", year={2018} }

Poster