“DRAW: A Recurrent Neural Network For Image Generation”, 2015-02-16 (; backlinks; similar):
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 (SHVN) dataset, it generates images that cannot be distinguished from real data with the naked eye.