English

Diverse Single Image Generation with Controllable Global Structure

Computer Vision and Pattern Recognition 2023-01-26 v4 Image and Video Processing

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.

Keywords

Cite

@article{arxiv.2102.04780,
  title  = {Diverse Single Image Generation with Controllable Global Structure},
  author = {Sutharsan Mahendren and Chamira Edussooriya and Ranga Rodrigo},
  journal= {arXiv preprint arXiv:2102.04780},
  year   = {2023}
}

Comments

Published in the Neurocomputing Journal

R2 v1 2026-06-23T22:58:38.971Z