We study the problem of synthesizing a number of likely future frames from a single input image.
A core challenge for an agent learning to interact with the world is to predict how its actions affect objects in its environment.
The move from hand-designed features to learned features in machine learning has been wildly successful.
We study the problem of 3D object generation.
This metric better reflects perceptually similarity of images and thus leads to better results.
The framework of normalizing flows provides a general strategy for flexible variational inference of posteriors over latent variables.
#4 best model for Image Generation on CIFAR-10 (Model Entropy metric)