Perceiving Systems Conference Paper 2024

WANDR: Intention-guided Human Motion Generation

Thumb xxl wandr youtube thumbnail.001 copy

Synthesizing natural human motions that enable a 3D human avatar to walk and reach for arbitrary goals in 3D space remains an unsolved problem with many applications. Existing methods (data-driven or using reinforcement learning) are limited in terms of generalization and motion naturalness.A primary obstacle is the scarcity of training data that combines locomotion with goal reaching. To address this, we introduce WANDR, a data-driven model that takes an avatar's initial pose and a goal's 3D position and generates natural human motions that place the end effector (wrist) on the goal location. To solve this, we introduce novel \textit{intention} features that drive rich goal-oriented movement. \textit{Intention} guides the agent to the goal, and interactively adapts the generation to novel situations without needing to define sub-goals or the entire motion path. Crucially, intention allows training on datasets that have goal-oriented motions as well as those that do not. WANDR is 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.

Author(s): Markos Diomataris and Nikos Athanasiou and Omid Taheri and Xi Wang and Otmar Hilliges and Michael J. Black
Book Title: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Pages: 927,936
Year: 2024
Month: June
Publisher: IEEE Computer Society
Project(s):
Bibtex Type: Conference Paper (inproceedings)
DOI: 10.1109/CVPR52733.2024.00094
Event Name: CVPR 2024
Event Place: Seattle, USA
State: Published
URL: https://wandr.is.tue.mpg.de/
Electronic Archiving: grant_archive
Links:

BibTex

@inproceedings{diomataris2024wandr,
  title = {{WANDR}: Intention-guided Human Motion Generation},
  booktitle = {2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  abstract = {Synthesizing natural human motions that enable a 3D human avatar to walk and reach for arbitrary goals in 3D space remains an unsolved problem with many applications. Existing methods (data-driven or using reinforcement learning) are limited in terms of generalization and motion naturalness.A primary obstacle is the scarcity of training data that combines locomotion with goal reaching. To address this, we introduce WANDR, a data-driven model that takes an avatar's initial pose and a goal's 3D position and generates natural human motions that place the end effector (wrist) on the goal location. To solve this, we introduce novel \textit{intention} features that drive rich goal-oriented movement. \textit{Intention} guides the agent to the goal, and interactively adapts the generation to novel situations without needing to define sub-goals or the entire motion path. Crucially, intention allows training on datasets that have goal-oriented motions as well as those that do not. WANDR is 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.},
  pages = {927,936},
  publisher = {IEEE Computer Society},
  month = jun,
  year = {2024},
  slug = {diomataris2024wandr},
  author = {Diomataris, Markos and Athanasiou, Nikos and Taheri, Omid and Wang, Xi and Hilliges, Otmar and Black, Michael J.},
  url = {https://wandr.is.tue.mpg.de/},
  month_numeric = {6}
}