Panini-Net: GAN Prior Based Degradation-Aware Feature Interpolation for Face Restoration
This work addresses a specific challenge in computer vision for face restoration, offering an incremental improvement by enhancing degradation handling in existing GAN-based methods.
The paper tackles the problem of balancing realness and fidelity in face restoration across various degradation levels by proposing Panini-Net, which uses a degradation-aware feature interpolation network to dynamically fuse features from input images and GAN prior, achieving state-of-the-art performance in multi-degradation face restoration and face super-resolution.
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.