Survey on Deep Face Restoration: From Non-blind to Blind and Beyond

TL;DR

This survey comprehensively reviews deep learning-based face restoration methods, categorizing techniques, analyzing benchmarks, and discussing challenges and future directions in transforming low-quality face images into high-quality ones.

Contribution

It provides a systematic categorization of face restoration methods, evaluates their performance on unified benchmarks, and discusses strategies to improve facial priors, offering a comprehensive overview of the field.

Findings

Deep learning has significantly advanced face restoration.

Benchmark evaluations reveal strengths and weaknesses of current methods.

Facial priors play a crucial role in restoration quality.

Abstract

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.