DRAW: A Recurrent Neural Network For Image Generation

02/16/2015
by   Karol Gregor, et al.
0

This paper introduces the Deep Recurrent Attentive Writer (DRAW) neural network architecture for image generation. DRAW networks combine a novel spatial attention mechanism that mimics the foveation of the human eye, with a sequential variational auto-encoding framework that allows for the iterative construction of complex images. The system substantially improves on the state of the art for generative models on MNIST, and, when trained on the Street View House Numbers dataset, it generates images that cannot be distinguished from real data with the naked eye.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset