Spectral Distribution Aware Image Generation

Authors

  • Steffen Jung Max Planck Institute for Informatics
  • Margret Keuper University of Mannheim

Keywords:

Computational Photography, Image & Video Synthesis, General, Other Foundations of Computer Vision

Abstract

Recent advances in deep generative models for photo-realistic images have led to high quality visual results. Such models learn to generate data from a given training distribution such that generated images can not be easily distinguished from real images by the human eye. Yet, recent work on the detection of such fake images pointed out that they are actually easily distinguishable by artifacts in their frequency spectra. In this paper, we propose to generate images according to the frequency distribution of the real data by employing a spectral discriminator. The proposed discriminator is lightweight, modular and works stably with different commonly used GAN losses. We show that the resulting models can better generate images with realistic frequency spectra, which are thus harder to detect by this cue.

Downloads

Published

2021-05-18

How to Cite

Jung, S., & Keuper, M. (2021). Spectral Distribution Aware Image Generation. Proceedings of the AAAI Conference on Artificial Intelligence, 35(2), 1734-1742. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16267

Issue

Section

AAAI Technical Track on Computer Vision I