Diverse Single Image Generation with Controllable Global Structure

TL;DR

This paper introduces a novel single-image generative model that employs attention mechanisms and Gaussian blurred inputs to improve the realism, diversity, and global structure control of generated images, especially for complex scenes.

Contribution

The authors propose a new method combining attention blocks and blurred images for better global context capture in single-image generation, outperforming existing approaches.

Findings

Enhanced visual quality over state-of-the-art methods

Improved diversity in generated images

Better global structure control in complex scenes

Abstract

Image generation from a single image using generative adversarial networks is quite interesting due to the realism of generated images. However, recent approaches need improvement for such realistic and diverse image generation, when the global context of the image is important such as in face, animal, and architectural image generation. This is mainly due to the use of fewer convolutional layers for mainly capturing the patch statistics and, thereby, not being able to capture global statistics very well. We solve this problem by using attention blocks at selected scales and feeding a random Gaussian blurred image to the discriminator for training. Our results are visually better than the state-of-the-art particularly in generating images that require global context. The diversity of our image generation, measured using the average standard deviation of pixels, is also better.