DRAW: A Recurrent Neural Network For Image Generation

作者：Karol Gregor, Ivo Danihelka, Alex Graves, Danilo Jimenez Rezende, Daan Wierstra · 年份：2015 · 被引用次数：762 · 研究领域：Advanced Image and Video Retrieval Techniques、Generative Adversarial Networks and Image Synthesis、Advanced Vision and Imaging

This paper introduces the Deep Recurrent Atten-tive 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 distin-guished from real data with the naked eye. 1.