Focal Frequency Loss for Image Reconstruction and Synthesis

TL;DR

This paper introduces a focal frequency loss that adaptively emphasizes difficult frequency components during training, significantly improving image reconstruction and synthesis quality across various models.

Contribution

The paper proposes a novel focal frequency loss that enhances existing models by focusing on hard-to-synthesize frequency components, improving image quality.

Findings

Improves perceptual quality of generated images

Enhances quantitative performance of models like VAE, pix2pix, SPADE

Shows potential benefits on StyleGAN2

Abstract

Image reconstruction and synthesis have witnessed remarkable progress thanks to the development of generative models. Nonetheless, gaps could still exist between the real and generated images, especially in the frequency domain. In this study, we show that narrowing gaps in the frequency domain can ameliorate image reconstruction and synthesis quality further. We propose a novel focal frequency loss, which allows a model to adaptively focus on frequency components that are hard to synthesize by down-weighting the easy ones. This objective function is complementary to existing spatial losses, offering great impedance against the loss of important frequency information due to the inherent bias of neural networks. We demonstrate the versatility and effectiveness of focal frequency loss to improve popular models, such as VAE, pix2pix, and SPADE, in both perceptual quality and quantitative performance. We further show its potential on StyleGAN2.