Journal
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
Volume 33, Issue 9, Pages 4603-4615Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCSVT.2023.3244786
Keywords
Face restoration; generative adversarial network (GAN); GAN prior; representation learning; feature interpolation
Categories
Ask authors/readers for more resources
In this paper, a novel DEgradation-Aware Restoration network with GAN prior (DEAR-GAN) is proposed for face restoration tasks. By explicitly learning the degradation representations (DR), the network can adapt to various degradation levels and dynamically fuse informative features through a feature interpolation module, achieving superior restoration results compared to existing methods.
With the development of generative adversarial networks (GANs), recent face restoration (FR) methods often utilize pre-trained GAN models (i.e.,, StyleGAN2) as prior to generate rich details. However, these methods usually struggle to balance realness and fidelity when facing various degradation levels. In this paper, we propose a novel DEgradation-Aware Restoration network with GAN prior, dubbed DEAR-GAN, for FR tasks by explicitly learning the degradation representations (DR) to adapt to various degradation. Specifically, an unsupervised degradation representation learning (UDRL) strategy is first developed to extract DR of the input degraded images. Then, a degradation-aware feature interpolation (DAFI) module is proposed to dynamically fuse the two types of informative features (i.e.,, features from degraded images and features from GAN prior network) with flexible adaption to various degradation based on DR. Extensive experiments show that our proposed DEAR-GAN outperforms the state-of-the-art methods for face restoration under multiple degradation and face super-resolution, and demonstrate the effectiveness of feature interpolation, which can be extended to face inpainting to achieve excellent results.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available