Data is the driving force of machine learning, with the amount and quality of training data
often being more important for the performance of a system than architecture and training …

The visual world can be parsimoniously characterized in terms of distinct entities with sparse
interactions. Discovering this compositional structure in dynamic visual scenes has proven …

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

A compositional understanding of the world in terms of objects and their geometry in 3D
space is considered a cornerstone of human cognition. Facilitating the learning of such a …

Unsupervised object-centric learning aims to represent the modular, compositional, and
causal structure of a scene as a set of object representations and thereby promises to …

Although DALL-E has shown an impressive ability of composition-based systematic
generalization in image generation, it requires the dataset of text-image pairs and the …

The promise of self-supervised learning (SSL) is to leverage large amounts of unlabeled
data to solve complex tasks. While there has been excellent progress with simple, image …

In this paper, we study the problem of unsupervised object detection from 3D point clouds in
self-driving scenes. We present a simple yet effective method that exploits (i) point clustering …

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 …