High-Quality Face Image SR Using Conditional Generative Adversarial Networks

TL;DR

This paper introduces FCGAN, a novel face super-resolution method using conditional GANs that generates high-quality face images from low-resolution inputs without facial priors, emphasizing an end-to-end pipeline with skip connections.

Contribution

The paper presents a new face super-resolution approach based on boundary equilibrium GANs, eliminating the need for facial priors and improving training efficiency with skip-layer connections.

Findings

Achieves competitive super-resolution performance.

End-to-end pipeline with minimal pre/post-processing.

Effective feature propagation and convergence speed.

Abstract

We propose a novel single face image super-resolution method, which named Face Conditional Generative Adversarial Network(FCGAN), based on boundary equilibrium generative adversarial networks. Without taking any facial prior information, our method can generate a high-resolution face image from a low-resolution one. Compared with existing studies, both our training and testing phases are end-to-end pipeline with little pre/post-processing. To enhance the convergence speed and strengthen feature propagation, skip-layer connection is further employed in the generative and discriminative networks. Extensive experiments demonstrate that our model achieves competitive performance compared with state-of-the-art models.