We address the problem of generating realistic 3D motions of humans
inte...
Realistic and controllable traffic simulation is a core capability that ...
Modern depth sensors such as LiDAR operate by sweeping laser-beams acros...
Controllable and realistic traffic simulation is critical for developing...
To produce safe human motions, assistive wearable exoskeletons must be
e...
3D multi-object tracking aims to uniquely and consistently identify all
...
Evaluating and improving planning for autonomous vehicles requires scala...
We introduce HuMoR: a 3D Human Motion Model for Robust Estimation of tem...
We propose CaSPR, a method to learn object-centric canonical spatiotempo...
Existing deep models predict 2D and 3D kinematic poses from video that a...
Machines that can predict the effect of physical interactions on the dyn...
We investigate the problem of learning category-specific 3D surface shap...
Humans have a remarkable ability to predict the effect of physical
inter...