DRAW: A Recurrent Neural Network For Image Generation
1 Introduction
We draw pictures not at once, but in a sequencial, iterative fashion.This work proposes an architecture to create a scene in a time series, and refine the sketches successively.
The core of DRAW is a pair of recurrrent neural networks: an encoder that compresses the real images and a decoder that reconstitutes images after receiving codes. The loss function is a variational upper bound on the log-likelihood of the data.
It generates images step by step , selectively attending to parts of images while ignoring others.
The DRAW architecture is similar to other variational auto-encoders: an encoder network determines a distribution over latent codes that capture salient information about the input data; a decoder network receives samples from the code distribution and uses them to condition its own distribution over images.
2 The DRAW Network
2.1 Network Architecture
Q(Zt|h(t,enc)) is a diagnonal Gaussian
2.2 Loss Function
The final canvas matrix Ct is used to parameterise a model D(X|Ct). D is a Bernoulli distribution.
reconstruction loss
latent loss
2.3 Stochastic data generation
2.4 Read and Write Operation
N*N grid of Gaussian Filters is positioned on the image by specifying the co-ordinates of the grid center and the stride distance between adjacent filters.
(i,j)is a point in the attention patch, (a,b) is a point in the input image.
イメージの各点がどれぐらいフィルターの一つの点Aに貢献するかを定量的に表現する重み行列。