Semi-Cycled Generative Adversarial Networks for Real-World Face Super-Resolution

TL;DR

This paper introduces SCGAN, a novel face super-resolution method that uses independent degradation branches to better handle real-world data, outperforming existing techniques in structure preservation and quantitative metrics.

Contribution

The paper proposes a semi-cycled GAN architecture with separate degradation branches to improve real-world face super-resolution performance.

Findings

SCGAN outperforms state-of-the-art methods on multiple datasets.

The method effectively preserves face structures and details.

Quantitative metrics show significant improvements.

Abstract

Real-world face super-resolution (SR) is a highly ill-posed image restoration task. The fully-cycled Cycle-GAN architecture is widely employed to achieve promising performance on face SR, but prone to produce artifacts upon challenging cases in real-world scenarios, since joint participation in the same degradation branch will impact final performance due to huge domain gap between real-world and synthetic LR ones obtained by generators. To better exploit the powerful generative capability of GAN for real-world face SR, in this paper, we establish two independent degradation branches in the forward and backward cycle-consistent reconstruction processes, respectively, while the two processes share the same restoration branch. Our Semi-Cycled Generative Adversarial Networks (SCGAN) is able to alleviate the adverse effects of the domain gap between the real-world LR face images and the synthetic LR ones, and to achieve accurate and robust face SR performance by the shared restoration branch regularized by both the forward and backward cycle-consistent learning processes. Experiments on two synthetic and two real-world datasets demonstrate that, our SCGAN outperforms the state-of-the-art methods on recovering the face structures/details and quantitative metrics for real-world face SR. The code will be publicly released at https://github.com/HaoHou-98/SCGAN.