论文标题
panini-net：基于gan先验的降解感知特征插值用于面部修复
Panini-Net: GAN Prior Based Degradation-Aware Feature Interpolation for Face Restoration
论文作者
论文摘要
新兴的高质量面部恢复（FR）方法经常使用预训练的GAN模型（\ textit {i.e。}，stylegan2）作为GAN PIROR。但是，这些方法通常在面对各种退化水平时努力平衡现实和忠诚。此外，与预训练的GAN模型相比，仍然存在明显的视觉质量差距。在本文中，我们提出了一种新颖的基于GAN的基于降解感知的特征插值网络，称为Panini-Net，用于通过明确学习抽象表示以区分各种降解，以实现FR任务。具体而言，首先制定了无监督的退化表示学习（UDRL）策略，以提取输入降级图像的降解表示（DR）。然后，提出了降解感知特征插值（DAFI）模块，以动态融合两种信息的特征（\ textIt {i.e。}，来自输入图像的特征和GAN PIRES的特征），并具有灵活的适应性，以适应基于DR的各种降级。消融研究揭示了DAFI的工作机制及其对可编辑的FR的潜力。广泛的实验表明，我们的panini-net实现了多降解面部恢复和面部超分辨率的最先进的性能。源代码可从https://github.com/jianzhangcs/panini获得。
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.
