Dilated Spatial Generative Adversarial Networks for Ergodic Image Generation

Abstract

Generative models have recently received renewed attention as a result of adversarial learning. Generative adversarial networks consist of samples generation model and a discrimination model able to distinguish between genuine and synthetic samples. In combination with convolutional (for the discriminator) and de-convolutional (for the generator) layers, they are particularly suitable for image generation, especially of natural scenes. However, the presence of fully connected layers adds global dependencies in the generated images. This may lead to high and global variations in the generated sample for small local variations in the input noise. In this work we propose to use architec-tures based on fully convolutional networks (including among others dilated layers), architectures specifically designed to generate globally ergodic images, that is images without global dependencies. Conducted experiments reveal that these architectures are well suited for generating natural textures such as geologic structures .

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Multi-Scale Context Aggregation by Dilated Convolutions
• Improved Techniques for Training GANs
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• Inversion using a new low-dimensional representation of complex binary geological media based on a deep neural network
• Texture Synthesis with Spatial Generative Adversarial Networks

Cited by in corpus (1)

• Pixel-wise Conditioned Generative Adversarial Networks for Image Synthesis and Completion