A Comprehensive Survey to Face Hallucination

By N. Wang, Dacheng Tao, Xinbo Gao, Xuelong Li, Jie Li. International Journal of Computer Vision, 2013

350 citations recorded by the source corpus.

This paper comprehensively surveys the development of face hallucination (FH), including both face super-resolution and face sketch-photo synthesis techniques. Indeed, these two techniques share the same objective of inferring a target face image (e.g. high-resolution face image, face sketch and face photo) from a corresponding source input (e.g. low-resolution face image, face photo and face sketch). Considering the critical role of image interpretation in modern intelligent systems for authentication, surveillance, law enforcement, security control, and entertainment, FH has attracted growing attention in recent years. Existing FH methods can be grouped into four categories: Bayesian inference approaches, subspace learning approaches, a combination of Bayesian inference and subspace learning approaches, and sparse representation-based approaches. In spite of achieving a certain level of development, FH is limited in its success by complex application conditions such as variant illuminations, poses, or views. This paper provides a holistic understanding and deep insight into FH, and presents a comparative analysis of representative methods and promising future directions.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/5a0d82e4efb74b1d74baea9ec794c1c66e637571

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Block-Row Sparse Multiview Multilabel Learning for Image Classification (2016, neutral): “[9], [12], [29]–[32].”
Comprehensive Review of Artificial Neural Network Applications to Pattern Recognition (2019, background): “ANN is useful in addressing the problems of crime detection and prevention [39] through PR [40]–[44].”
Weighted Schatten $p$ -Norm Minimization for Image Denoising and Background Subtraction (2015, methodology): “In the future, we will extend the proposed WSNM to other applications such as face hallucination [42], facial deblur [43], and face sketch synthesis [44].”
Object Detection With Deep Learning: A Review (2018, background): “Face detection is essential to many face applications and acts as an important pre-processing procedure to face recognition [160]–[162], face synthesis [163], [164] and facial expression analysis [165].”
High-Quality Face Image SR Using Conditional Generative Adversarial Networks (2017, background): “More realistic and sharper details, which plays a crucial role in intelligence surveillance[1, 3] and face recognition[9], are taken by HR face images than corresponding LR images.”
Ultra-Resolving Face Images by Discriminative Generative Networks (2016, background): “In order to generate high-resolution (HR) face images from low-resolution (LR) inputs, face hallucination [1,2,3,4,5,6,7,8,9,10,11,12] attracted great interest in the past.”
PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models (2020, background): “This subdomain – known as face hallucination – finds application in consumer photography, photo/video restoration, and more [23].”
Training-Free, Single-Image Super-Resolution Using a Dynamic Convolutional Network (2018, methodology): “S INGLE-IMAGE super-resolution (SR) is an important tool in applications such as biomedical imaging [1], face hallucination [2], etc.”
Wavelet-SRNet: A Wavelet-Based CNN for Multi-scale Face Super Resolution (2017, background): “The first one [29, 13, 28, 30, 35] is to exploits the specific static information of face images with the help of face analysis technique.”
Sketch-a-Segmenter: Sketch-Based Photo Segmenter Generation (2020, background): “Details conveyed in sketch have been exploited for ﬁne-grained image retrieval [13]–[16] and image synthesis [17]–[19].”