This paper presents WALDO (WArping Layer-Decomposed Objects), a novel approach to
the prediction of future video frames from past ones. Individual images are decomposed into …

We propose a novel unsupervised method to autoregressively generate videos from a single
frame and a sparse motion input. Our trained model can generate unseen realistic object-to …

Video extrapolation in space and time (VEST) enables viewers to forecast a 3D scene into
the future and view it from novel viewpoints. Recent methods propose to learn an entangled …

The ability to model the underlying dynamics of visual scenes and reason about the future is
central to human intelligence. Many attempts have been made to empower intelligent …

Abstract Reasoning about the results of their actions is a critical skill for embodied agents. In
this thesis, we study how robots can learn to predict the future from visual observations. We …

We present our method for efficiently learning an implicit neural representation for shape
reconstruction and pose estimation from raw sensor data. In contrast to recent methods, we …