Keywords: object-centric models, generative models, object permanence
TL;DR: We develop a novel, object-centric, hierarchical generative model of vision, which improves performance on a novel object-permanence task compared to known world models.
Abstract: Object permanence is an important milestone in infant development, when the infant understands that an object continues to exist even when it no longer can be seen. However, current machine learning methods devised to build a world model to predict the future still fail at this task when having to deal with longer time sequences and severe occlusions. In this paper, we compare current machine learning with infant learning, and propose an object-centric approach on learning predictive models. This grounds object representations to an inferred location, effectively resolving the object permanence problem. We demonstrate performance on a novel object-permanence task in a simulated 3D environment.