Data-driven model generates natural human motions for virtual avatars

WANDR starts from an arbitrary body pose and generates precise and realistic human motions that reach a specified 3D goal (depicted as a red sphere). Employing a purely data-driven approach, WANDR is a conditional Variational Autoencoder guided by intention features (depicted arrows) that steer the human’s orientation (yellow), position (cyan) and wrist (pink) towards the goal. WANDR can reach a wide range of goals even if they deviate significantly from the training data. Credit: Diomataris et al. Humans can innately perform a wide range of movements, as this allows them Read More

Related posts:

  1. Scientists create first mouse model with complete, functional human immune system
  2. The largest repository of transcription factor binding data in human tissues compiled to date
  3. Deep machine-learning speeds assessment of fruit fly heart aging and disease, a model for human disease
  4. Work-related nerve injuries are common with repetitive motions
  5. Using muscular avatars in VR to reduce pain perception
  6. Novel vaccine concept generates immune responses that could produce multiple types of HIV neutralizing antibodies
  7. Clinical study shows zebrafish avatars of cancer patients have high predictive power
  8. New dimensions of haptics in virtual reality

Leave a Reply

Your email address will not be published. Required fields are marked *