Three-Dimensional Face Reconstruction Using Multi-View-Based Bilinear Model

被引:4
|
作者
Tian, Liang [1 ]
Liu, Jing [1 ]
Guo, Wei [1 ]
机构
[1] Hebei Normal Univ, Coll Math & Informat Sci, Key Lab Augmented Real, 20 Rd East,2nd Ring South, Shijiazhuang 050024, Hebei, Peoples R China
来源
SENSORS | 2019年 / 19卷 / 03期
基金
中国国家自然科学基金;
关键词
3D reconstruction; 3D vision; multi-view-based bilinear model; model matching; 3D shape modeling; RECOGNITION; STEREO; POSE; SHAPE;
D O I
10.3390/s19030459
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Face reconstruction is a popular topic in 3D vision system. However, traditional methods often depend on monocular cues, which contain few feature pixels and only use their location information while ignoring a lot of textural information. Furthermore, they are affected by the accuracy of the feature extraction method and occlusion. Here, we propose a novel facial reconstruction framework that accurately extracts the 3D shapes and poses of faces from images captured at multi-views. It extends the traditional method using the monocular bilinear model to the multi-view-based bilinear model by incorporating the feature prior constraint and the texture constraint, which are learned from multi-view images. The feature prior constraint is used as a shape prior to allowing us to estimate accurate 3D facial contours. Furthermore, the texture constraint extracts a high-precision 3D facial shape where traditional methods fail because of their limited number of feature points or the mostly texture-less and texture-repetitive nature of the input images. Meanwhile, it fully explores the implied 3D information of the multi-view images, which also enhances the robustness of the results. Additionally, the proposed method uses only two or more uncalibrated images with an arbitrary baseline, estimating calibration and shape simultaneously. A comparison with the state-of-the-art monocular bilinear model-based method shows that the proposed method has a significantly higher level of accuracy.
引用
收藏
页数:20
相关论文
共 50 条
  • [1] Three-dimensional Reconstruction of Tomato Fruit based on Multi-view Images
    Ye, Rong
    Gao, Yanjun
    Zhang, Jie
    Xu, Junqiang
    Gao, Quan
    [J]. PROCEEDINGS OF 2024 INTERNATIONAL CONFERENCE ON MACHINE INTELLIGENCE AND DIGITAL APPLICATIONS, MIDA2024, 2024, : 75 - 85
  • [2] Three-dimensional profile reconstruction based on infrared Multi-view vision
    Zhao, Shuqi
    Zhang, Zhimin
    Wan, Xiong
    [J]. 8TH INTERNATIONAL SYMPOSIUM ON ADVANCED OPTICAL MANUFACTURING AND TESTING TECHNOLOGY: OPTICAL TEST, MEASUREMENT TECHNOLOGY, AND EQUIPMENT, 2016, 9684
  • [3] Face Reconstruction Method Based on Optimized Three-Dimensional Morphable Model Parameters
    Zhang Hongying
    Yang Weimin
    Wang Huisan
    [J]. LASER & OPTOELECTRONICS PROGRESS, 2021, 58 (20)
  • [4] Three-dimensional model based face recognition
    Lu, XG
    Colbry, D
    Jain, AK
    [J]. PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 1, 2004, : 362 - 366
  • [5] Three-dimensional reconstruction of skin disease using multi-view mobile images
    Hong, Geeyun
    Lee, Onseok
    [J]. SKIN RESEARCH AND TECHNOLOGY, 2019, 25 (04) : 434 - 439
  • [6] Three-dimensional scene reconstruction using multi-view images and depth camera
    Um, GM
    Kim, KY
    Ahn, C
    Lee, KH
    [J]. STEREOSCOPIC DISPLAYS AND VIRTUAL REALITY SYSTEMS XII, 2005, 5664 : 271 - 280
  • [7] Reconstruction of the fetus face from three-dimensional ultrasound using a newborn face statistical shape model
    Alomar, Antonia
    Morales, Araceli
    Vellve, Kilian
    Porras, Antonio R.
    Crispi, Fatima
    Linguraru, Marius George
    Piella, Gemma
    Sukno, Federico
    [J]. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2022, 221
  • [8] Three-Dimensional Reconstruction of Tunnel Face Based on Multiple Images
    Qiu, Wenge
    Jian, Liao
    Cheng, Yunjian
    Bai, Hengbin
    [J]. ADVANCES IN CIVIL ENGINEERING, 2021, 2021
  • [9] An Efficient Three-Dimensional Reconstruction Approach for Pose-Invariant Face Recognition Based on a Single View
    Zhao, Minghua
    Mo, Ruiyang
    Zhao, Yonggang
    Shi, Zhenghao
    Zhang, Feifei
    [J]. KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT (KSEM 2017): 10TH INTERNATIONAL CONFERENCE, KSEM 2017, MELBOURNE, VIC, AUSTRALIA, AUGUST 19-20, 2017, PROCEEDINGS, 2017, 10412 : 422 - 431
  • [10] MANMADE-TARGET THREE-DIMENSIONAL RECONSTRUCTION USING MULTI-VIEW RADAR IMAGES
    Luo, Yin
    Chen, Si-Wei
    Wang, Xue-Song
    [J]. 2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022), 2022, : 3452 - 3455