Multi-view frontal face image generation: A survey

被引:61
|
作者
Ning, Xin [1 ,2 ,3 ]
Nan, Fangzhe [2 ,3 ]
Xu, Shaohui [2 ,3 ]
Yu, Lina [1 ]
Zhang, Liping [1 ,2 ,3 ]
机构
[1] Chinese Acad Sci, Inst Semicond, Beijing 100083, Peoples R China
[2] Wave Grp, Cognit Comp Technol Joint Lab, Beijing, Peoples R China
[3] Shenzhen Wave Kingdom Co Ltd, Shenzhen, Peoples R China
来源
基金
中国国家自然科学基金;
关键词
3D model; deep learning; face frontalization; hybrid model; POSE NORMALIZATION; RECOGNITION; DATABASE;
D O I
10.1002/cpe.6147
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Face images from different perspectives reduce the accuracy of face recognition, and the generation of frontal face images is an important research topic in the field of face recognition. To understand the development of frontal face generation models and grasp the current research hotspots and trends, existing methods based on 3D models, deep learning, and hybrid models are summarized, and the current commonly used face generation methods are introduced. Dataset, and compare the performance of existing models through experiments. The purpose of this paper is to fundamentally understand the advantages of existing frontal face generation, sort out the key issues of such generation, and look toward future development trends.
引用
收藏
页数:18
相关论文
共 50 条
  • [21] AUTOMATIC FRONTAL VIEW FACE IMAGE SYNTHESIS
    Li, Yuelong
    Feng, Jufu
    2010 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, 2010, : 1829 - 1832
  • [22] Multi-view Image Generation by Cycle CVAE-GAN Networks
    Lai, Zhichen
    Tang, Chenwei
    Lv, Jiancheng
    NEURAL INFORMATION PROCESSING (ICONIP 2019), PT I, 2019, 11953 : 43 - 54
  • [23] A Comprehensive Survey on Multi-View Clustering
    Fang, Uno
    Li, Man
    Li, Jianxin
    Gao, Longxiang
    Jia, Tao
    Zhang, Yanchun
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2023, 35 (12) : 12350 - 12368
  • [24] A Survey of Multi-view Gait Recognition
    Wang K.-J.
    Ding X.-N.
    Xing X.-L.
    Liu M.-C.
    Zidonghua Xuebao/Acta Automatica Sinica, 2019, 45 (05): : 841 - 852
  • [25] A survey of multi-view machine learning
    Shiliang Sun
    Neural Computing and Applications, 2013, 23 : 2031 - 2038
  • [26] Virtual view generation from a frontal face image using Invertible Meshwarp Algorithm
    Jun, BH
    IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2004, E87A (06) : 1401 - 1408
  • [27] A Survey of Multi-View Representation Learning
    Li, Yingming
    Yang, Ming
    Zhang, Zhongfei
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2019, 31 (10) : 1863 - 1883
  • [28] A survey of multi-view machine learning
    Sun, Shiliang
    NEURAL COMPUTING & APPLICATIONS, 2013, 23 (7-8): : 2031 - 2038
  • [29] THE THU MULTI-VIEW FACE DATABASE FOR VIDEOCONFERENCES
    Dong, Linhao
    Tao, Xiaoming
    Li, Yang
    Lu, Jichuan
    Zhang, Zizhuo
    Cheng, Jingwen
    Lu, Jianhua
    2015 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2015, : 417 - 421
  • [30] Multi-view Subspace Clustering for Face Images
    Zhang, Xin
    Dinh Phung
    Venkatesh, Svetha
    Duc-Son Pham
    Liu, Wanquan
    2015 INTERNATIONAL CONFERENCE ON DIGITAL IMAGE COMPUTING: TECHNIQUES AND APPLICATIONS (DICTA), 2015, : 555 - 561