The exploding usage of physical object properties has greatly facilitated real-time
applications such as robotics to perceive exactly as it appears in existence. Changes in the …

This application relates generally to augmenting images and videos with dynamic object
compositing, and more specifi cally, to generating synthetic training data to train a machine …

We introduce an approach to model surface properties governing bounces in everyday
scenes. Our model learns end-to-end, starting from sensor inputs, to predict post-bounce …

While learning models of intuitive physics is an active area of research, current approaches
fall short of natural intelligences in one important regard: they require external supervision …

While the basic laws of Newtonian mechanics are well understood, explaining a physical
scenario still requires manually modeling the problem with suitable equations and …

We regularly interact with moving objects in our environment. Yet, little is known about how
we extrapolate the future movements of visually perceived objects. One possibility is that …

We introduce a method to generate videos of dynamic virtual objects plausibly interacting
via collisions with a still image's environment. Given a starting trajectory, physically …

Abstract Machines that can predict the effect of physical interactions on the dynamics of
previously unseen object instances are important for creating better robots and interactive …

Abstract Machines that can predict the effect of physical interactions on the dynamics of
previously unseen object instances are important for creating better robots and interactive …

Humans have a remarkable ability to predict the effect of physical interactions on the
dynamics of objects. Endowing machines with this ability would allow important applications …