Face restoration (FR) is a specialized field within image restoration that aims to recover low-quality (LQ) face images into high-quality (HQ) face images. Recent advances in deep learning technology have led to significant progress in FR methods. In this paper, we begin by examining the prevalent factors responsible for real-world LQ images and introduce degradation techniques used to synthesize LQ images. We also discuss notable benchmarks commonly utilized in the field. Next, we categorize FR methods based on different tasks and explain their evolution over time. Furthermore, we explore the various facial priors commonly utilized in the restoration process and discuss strategies to enhance their effectiveness. In the experimental section, we thoroughly evaluate the performance of state-of-the-art FR methods across various tasks using a unified benchmark. We analyze their performance from different perspectives. Finally, we discuss the challenges faced in the field of FR and propose potential directions for future advancements. The open-source repository corresponding to this work can be found at https:// github.com/ 24wenjie-li/ Awesome-Face-Restoration.

翻译：人脸恢复（Face Restoration，FR）是图像恢复领域的一个专门分支，旨在将低质量（Low-Quality，LQ）人脸图像恢复为高质量（High-Quality，HQ）人脸图像。近年来，深度学习技术的进步推动了FR方法的显著发展。本文首先梳理了造成真实场景低质量图像的常见因素，并介绍了用于合成低质量图像的退化技术。同时，我们讨论了该领域常用的基准数据集。随后，根据不同任务对FR方法进行分类，并阐述其随时间演进的历程。此外，我们探讨了恢复过程中常用的多种面部先验信息，并讨论了提升其有效性的策略。在实验部分，我们采用统一基准，全面评估了最新FR方法在不同任务上的性能，并从多个角度进行分析。最后，我们探讨了人脸恢复领域面临的挑战，并提出未来发展的潜在方向。本工作的开源代码仓库可访问 https://github.com/24wenjie-li/Awesome-Face-Restoration。