A comprehensive artificial intelligence system needs to not only perceive the environment
with different “senses”(eg, seeing and hearing) but also infer the world's conditional (or even …

Learning object-centric representations of complex scenes is a promising step towards
enabling efficient abstract reasoning from low-level perceptual features. Yet, most deep …

Object-centric representations are a promising path toward more systematic generalization
by providing flexible abstractions upon which compositional world models can be built …

Unsupervised multi-object segmentation has shown impressive results on images by
utilizing powerful semantics learned from self-supervised pretraining. An additional modality …

Understanding dynamics from visual observations is a challenging problem that requires
disentangling individual objects from the scene and learning their interactions. While recent …

We present ObSuRF, a method which turns a single image of a scene into a 3D model
represented as a set of Neural Radiance Fields (NeRFs), with each NeRF corresponding to …

The binding problem in human cognition, concerning how the brain represents and
connects objects within a fixed network of neural connections, remains a subject of intense …

In this paper, we study the problem of unsupervised object segmentation from single
images. We do not introduce a new algorithm, but systematically investigate the …

The remarkable recent advances in object-centric generative world models raise a few
questions. First, while many of the recent achievements are indispensable for making a …

We propose a new approach to learn to segment multiple image objects without manual
supervision. The method can extract objects form still images, but uses videos for …