Panini-Net: GAN Prior Based Degradation-Aware Feature Interpolation for Face Restoration

TL;DR

Panini-Net introduces a degradation-aware feature interpolation method leveraging GAN priors and unsupervised degradation representations to improve face restoration quality across various degradation levels.

Contribution

It proposes a novel degradation-aware feature interpolation network with unsupervised degradation learning for enhanced face restoration performance.

Findings

Achieves state-of-the-art results in multi-degradation face restoration.

Effectively distinguishes and adapts to various degradation levels.

Demonstrates superior visual quality compared to existing methods.

Abstract

Emerging high-quality face restoration (FR) methods often utilize pre-trained GAN models (\textit{i.e.}, StyleGAN2) as GAN Prior. However, these methods usually struggle to balance realness and fidelity when facing various degradation levels. Besides, there is still a noticeable visual quality gap compared with pre-trained GAN models. In this paper, we propose a novel GAN Prior based degradation-aware feature interpolation network, dubbed Panini-Net, for FR tasks by explicitly learning the abstract representations to distinguish various degradations. Specifically, an unsupervised degradation representation learning (UDRL) strategy is first developed to extract degradation representations (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 (\textit{i.e.}, features from input images and features from GAN Prior) with flexible adaption to various degradations based on DR. Ablation studies reveal the working mechanism of DAFI and its potential for editable FR. Extensive experiments demonstrate that our Panini-Net achieves state-of-the-art performance for multi-degradation face restoration and face super-resolution. The source code is available at https://github.com/jianzhangcs/panini.