Spectral Distribution Aware Image Generation
This work improves the realism of generated images for researchers and practitioners working with deep generative models, making generated content less detectable by frequency analysis.
This paper addresses the issue of detectable frequency spectrum artifacts in images generated by deep generative models. By incorporating a spectral discriminator, the proposed method generates images with more realistic frequency spectra, making them harder to distinguish from real images based on this cue.
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.