NeRF provides unparalleled fidelity of novel view synthesis: rendering a...
We propose ADIOS, a masked image model (MIM) framework for self-supervis...
We present ObSuRF, a method which turns a single image of a scene into a...
We propose NeRF-VAE, a 3D scene generative model that incorporates geome...
A set is an unordered collection of unique elements–and yet many machine...
Few-shot supervised learning leverages experience from previous learning...
Generative models are emerging as promising tools in robotics and
reinfo...
The majority of contemporary object-tracking approaches used in autonomo...
An object can be seen as a geometrically organized set of interrelated p...
Many machine learning tasks such as multiple instance learning, 3D shape...
We present Sequential Attend, Infer, Repeat (SQAIR), an interpretable de...
Discrete latent-variable models, while applicable in a variety of settin...
We provide theoretical and empirical evidence that using tighter evidenc...
Class-agnostic object tracking is particularly difficult in cluttered
en...