Humans naturally decompose their environment into entities at the appropriate level of
abstraction to act in the world. Allowing machine learning algorithms to derive this …

Learning structured representations of the visual world in terms of objects promises to
significantly improve the generalization abilities of current machine learning models. While …

In this paper, we study the problem of 3D object segmentation from raw point clouds. Unlike
all existing methods which usually require a large amount of human annotations for full …

Unsupervised video-based object-centric learning is a promising avenue to learn structured
representations from large, unlabeled video collections, but previous approaches have only …

The ability to decompose complex natural scenes into meaningful object-centric abstractions
lies at the core of human perception and reasoning. In the recent culmination of …

Visual scenes are composed of visual concepts and have the property of combinatorial
explosion. An important reason for humans to efficiently learn from diverse visual scenes is …

Unsupervised object-centric learning aims to decompose scenes into interpretable object
entities termed slots. Slot-based auto-encoders stand out as a prominent method for this …

Discovering object-centric representations from images has the potential to greatly improve
the robustness, sample efficiency and interpretability of machine learning algorithms …

Generic re-usable pre-trained image representation encoders have become a standard
component of methods for many computer vision tasks. As visual representations for robots …

In this paper, we study the problem of 3D object segmentation from raw point clouds. Unlike
existing methods which usually require a large amount of human annotations for full …