TL;DR
This paper introduces a spectral discriminator for GANs that guides image generation to match real data frequency distributions, resulting in more realistic images that are harder to detect as fake.
Contribution
It proposes a novel spectral discriminator that improves the frequency realism of generated images, enhancing their authenticity and detection resistance.
Findings
Generated images have more realistic frequency spectra
Spectral discriminator is lightweight and compatible with various GAN losses
Results show improved realism and detection resistance of generated images
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
