Spatial Frequency Bias in Convolutional Generative Adversarial Networks

Understand

As the success of Generative Adversarial Networks (GANs) on natural images quickly propels them into various real-life applications across different domains, it becomes more and more important to clearly understand their limitations.

• Specifically, understanding GANs' capability across the full spectrum of spatial frequencies, i.e.
• beyond the low-frequency dominant spectrum of natural images, is critical for assessing the reliability of GAN generated data in any detail-sensitive application (e.g.
• denoising, filling and super-resolution in medical and satellite images).