Learn the Force We Can: Enabling Sparse Motion Control in Multi-Object Video Generation.
Aram DavtyanPaolo FavaroPublished in: AAAI (2024)
Keyphrases
- multi object
- motion control
- mobile robot
- video data
- human perception
- control system
- multiple objects
- autonomous robots
- motion trajectories
- high dimensional
- video sequences
- statistical shape model
- physical constraints
- space time
- robot control
- real time
- autonomous navigation
- single image
- dynamical systems
- video frames
- control algorithm
- spatio temporal
- real robot
- high quality