Dilated Spatial Generative Adversarial Networks for Ergodic Image Generation
This work addresses image generation issues for applications requiring natural textures, but it appears incremental as it builds on existing GAN methods with architectural modifications.
The paper tackled the problem of global dependencies in GAN-generated images by proposing fully convolutional architectures with dilated layers, resulting in globally ergodic images suitable for natural textures like geologic structures.
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 .