We present a novel framework for unsupervised object-centric 3D scene understanding that generalizes robustly to out-of-distribution images.

In many sequential tasks, a model needs to remember relevant events from the distant past to make correct predictions.

Our main technical contribution is the rigorous analysis of a Bayes estimator and of an approximate message passing (AMP) algorithm, both of which incorrectly assume a Gaussian setup.

In this paper, we show that such a centralized approach makes CEM vulnerable to local optima, thus impairing its sample efficiency.