Spatial PixelCNN: Generating Images from Patches

Abstract

In this paper we propose Spatial PixelCNN, a conditional autoregressive model that generates images from small patches. By conditioning on a grid of pixel coordinates and global features extracted from a Variational Autoencoder (VAE), we are able to train on patches of images, and reproduce the full-sized image. We show that it not only allows for generating high quality samples at the same resolution as the underlying dataset, but is also capable of upscaling images to arbitrary resolutions (tested at resolutions up to $50\times$) on the MNIST dataset. Compared to a PixelCNN++ baseline, Spatial PixelCNN quantitatively and qualitatively achieves similar performance on the MNIST dataset.

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Neural Discrete Representation Learning
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Conditional Image Synthesis With Auxiliary Classifier GANs
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• Improved Techniques for Training GANs
• f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
• A note on the evaluation of generative models
• Neural Machine Translation in Linear Time
• Multiplicative LSTM for sequence modelling

Cited by in corpus (4)

• Precise Estimation of Renal Vascular Dominant Regions Using Spatially Aware Fully Convolutional Networks, Tensor-Cut and Voronoi Diagrams
• Visual Anomaly Detection for Images: A Survey
• Locally Masked Convolution for Autoregressive Models
• Predictive Sampling with Forecasting Autoregressive Models