This paper takes a step towards temporal reasoning in a dynamically changing video, not in the pixel space that constitutes its frames, but in a latent space that describes the non-linear dynamics of the objects in its world. We introduce the Kalman variational auto-encoder, a framework for unsupervised learning of sequential data that disentangles two latent representations: an object's representation, coming from a recognition model, and a latent state describing its dynamics. As a result, the evolution of the world can be imagined and missing data imputed, both without the need to generate high dimensional frames at each time step. The model is trained end-to-end on videos of a variety of simulated physical systems, and outperforms competing methods in generative and missing data imputation tasks.
@article{arxiv.1710.05741,
title = {A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learning},
author = {Marco Fraccaro and Simon Kamronn and Ulrich Paquet and Ole Winther},
journal= {arXiv preprint arXiv:1710.05741},
year = {2017}
}