Lune

CVPR2024

WANDR: Intention-guided Human Motion Generation

Markos Diomataris, Nikos Athanasiou, Omid Taheri, Xi Wang, Otmar Hilliges, Michael J. Black

DOIarXiv出版方

摘要

a conditional Variational Auto-Encoder (c-VAE), which we train using the AMASS and CIRCLE datasets. We evaluate our method extensively and demonstrate its ability to generate natural and long-term motions that reach 3D goals and generalize to unseen goal locations. Our models and code are available for research purposes at wandr.is.tue.mpg.de.