DeepAI AI Chat
Log In Sign Up

Spectral Distribution aware Image Generation

by   Steffen Jung, et al.

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.


page 3

page 7

page 10

page 11

page 12

page 13


On the Frequency Bias of Generative Models

The key objective of Generative Adversarial Networks (GANs) is to genera...

Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis

The rapid advances in deep generative models over the past years have le...

Amplifying The Uncanny

Deep neural networks have become remarkably good at producing realistic ...

SSD-GAN: Measuring the Realness in the Spatial and Spectral Domains

This paper observes that there is an issue of high frequencies missing i...

Exploring the Asynchronous of the Frequency Spectra of GAN-generated Facial Images

The rapid progression of Generative Adversarial Networks (GANs) has rais...

Inverse Graphics GAN: Learning to Generate 3D Shapes from Unstructured 2D Data

Recent work has shown the ability to learn generative models for 3D shap...

Refining Deep Generative Models via Wasserstein Gradient Flows

Deep generative modeling has seen impressive advances in recent years, t...