Deep Learning-based Face Super-Resolution: A Survey
arXiv:2101.03749
Abstract
Face super-resolution (FSR), also known as face hallucination, which is aimed at enhancing the resolution of low-resolution (LR) face images to generate high-resolution (HR) face images, is a domain-specific image super-resolution problem. Recently, FSR has received considerable attention and witnessed dazzling advances with the development of deep learning techniques. To date, few summaries of the studies on the deep learning-based FSR are available. In this survey, we present a comprehensive review of deep learning-based FSR methods in a systematic manner. First, we summarize the problem formulation of FSR and introduce popular assessment metrics and loss functions. Second, we elaborate on the facial characteristics and popular datasets used in FSR. Third, we roughly categorize existing methods according to the utilization of facial characteristics. In each category, we start with a general description of design principles, then present an overview of representative approaches, and then discuss the pros and cons among them. Fourth, we evaluate the performance of some state-of-the-art methods. Fifth, joint FSR and other tasks, and FSR-related applications are roughly introduced. Finally, we envision the prospects of further technological advancement in this field. A curated list of papers and resources to face super-resolution are available at \url{https://github.com/junjun-jiang/Face-Hallucination-Benchmark}
arXiv commentAccepted to ACM Computing Surveys
References in corpus (30)
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Spectral Normalization for Generative Adversarial Networks
- Learning Face Representation from Scratch
- Deep Learning for Single Image Super-Resolution: A Brief Review
- BEGAN: Boundary Equilibrium Generative Adversarial Networks
- HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment
- Progressive Face Super-Resolution via Attention to Facial Landmark
- SiGAN: Siamese Generative Adversarial Network for Identity-Preserving Face Hallucination
- Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network
- SwinIR: Image Restoration Using Swin Transformer
- Joint Face Image Restoration and Frontalization for Recognition
- Edge and Identity Preserving Network for Face Super-Resolution
- Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression
- Attention-Aware Face Hallucination via Deep Reinforcement Learning
- Face Hallucination with Finishing Touches
- Face Super-Resolution Through Wasserstein GANs
- Deep Joint Face Hallucination and Recognition
- High-Quality Face Image SR Using Conditional Generative Adversarial Networks
- Pro-UIGAN: Progressive Face Hallucination from Occluded Thumbnails
- Global-Local Face Upsampling Network
- Verification of Very Low-Resolution Faces Using An Identity-Preserving Deep Face Super-Resolution Network
- Adversarial Discriminative Heterogeneous Face Recognition
- Deep multi-frame face super-resolution
- A Convex Approach for Image Hallucination
- Hallucinating very low-resolution and obscured face images
- VidFace: A Full-Transformer Solver for Video FaceHallucination with Unaligned Tiny Snapshots
- Implicit Subspace Prior Learning for Dual-Blind Face Restoration
- Multiple Exemplars-based Hallucinationfor Face Super-resolution and Editing
- Network Architecture Search for Face Enhancement
- Lightweight Photometric Stereo for Facial Details Recovery