We present a general-purpose framework for image modelling and vision ta...
Real-world data is high-dimensional: a book, image, or musical performan...
High Definition (HD) maps are maps with precise definitions of road lane...
Semantically meaningful information content in perceptual signals is usu...
The high dimensionality of images presents architecture and
sampling-eff...
Polygon meshes are an efficient representation of 3D geometry, and are o...
We propose a new family of efficient and expressive deep generative mode...
Neural density estimators are flexible families of parametric models whi...
Understanding the nature of representations learned by supervised machin...
Latent variable models can be used to probabilistically "fill-in" missin...