Intrinsic decomposition from a single image is a highly challenging task...
When encountering novel objects, humans are able to infer a wide range o...
Learning robust value functions given raw observations and rewards is no...
Learning goal-directed behavior in environments with sparse feedback is ...
This paper presents the Deep Convolution Inverse Graphics Network (DC-IG...
Recently, multiple formulations of vision problems as probabilistic
inve...
Approximate inference in high-dimensional, discrete probabilistic models...
The idea of computer vision as the Bayesian inverse problem to computer
...