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 …

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 …

Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in
processing vision-language tasks. One of the crux of MLLMs lies in vision tokenization …

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 …

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

Object-centric learning aims to represent visual data with a set of object entities (aka slots),
providing structured representations that enable systematic generalization. Leveraging …

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

The recent success of transformer-based image generative models in object-centric learning
highlights the importance of powerful image generators for handling complex scenes …

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 …

There has been a recent surge in methods that aim to decompose and segment scenes into
multiple objects in an unsupervised manner, ie, unsupervised multi-object segmentation …