iPDO: An Effective Feature Depth Estimation Method for 3D Face Reconstruction

被引:0
|
作者
Gong, Xun [1 ]
Li, Xinxin [2 ]
Du, Shengdong [1 ]
Zhao, Yang [1 ]
机构
[1] Southwest Jiaotong Univ, Sch Informat Sci & Technol, Chengdu 611756, Sichuan, Peoples R China
[2] Sichuan Univ, Jincheng Coll, Chengdu 611731, Sichuan, Peoples R China
来源
ROUGH SETS | 2017年 / 10313卷
基金
中国国家自然科学基金;
关键词
3D face reconstruction; Depth estimation; Pose estimation; SHAPE;
D O I
10.1007/978-3-319-60837-2_34
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We present a 3D face modeling approach under uncontrolled conditions. In the heart of this work is an efficient and accurate facial landmark depth estimation algorithm. The objective function is formulated by similarity transformation among face images. In this method, pose parameters and depth values are optimized iteratively. The estimated 3D landmarks then are taken as control points to deform a generic 3D face shape into a specific face shape. Test results on synthesized images show that the proposed methods can obtain landmarks depth both effectively and efficiently. Whats' more, the 3D faces generated from real-world photos are rather realistic based on a set of landmarks.
引用
收藏
页码:407 / 417
页数:11
相关论文
共 50 条
  • [21] Approach to 3D face reconstruction through local deep feature alignment
    Zhang, Jian
    Zhu, Chaoyang
    IET COMPUTER VISION, 2019, 13 (02) : 213 - 223
  • [22] Face Reconstruction Based on Multiscale Feature Fusion and 3D Animation Design
    Xu, Lili
    MOBILE INFORMATION SYSTEMS, 2021, 2021
  • [23] Wound 3D Geometrical Feature Estimation Using Poisson Reconstruction
    Juszczyk, Jan Maria
    Wijata, Agata
    Czajkowska, Joanna
    Krecichwost, Michal
    Rudzki, Marcin
    Biesok, Marta
    Pycinski, Bartlomiej
    Majewski, Jakub
    Kostecki, Jacek
    Pietka, Ewa
    IEEE ACCESS, 2021, 9 : 7894 - 7907
  • [24] A simple 3D face tracking method based on depth information
    Zhao, GQ
    Chen, L
    Chen, GC
    PROCEEDINGS OF 2005 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-9, 2005, : 5022 - 5027
  • [25] A Fast and Robust Depth Estimation Method for 3D Cameras
    Shim, Seong-O
    Choi, Tae-Sun
    2012 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS (ICCE), 2012, : 321 - 322
  • [26] Depth-Based 3D Face Reconstruction and Pose Estimation Using Shape-Preserving Domain Adaptation
    Zhong Y.
    Pei Y.
    Li P.
    Guo Y.
    Ma G.
    Liu M.
    Bai W.
    Wu W.
    Zha H.
    Pei, Yuru (peiyuru@cis.pku.edu.cn), 1600, Institute of Electrical and Electronics Engineers Inc. (03): : 6 - 15
  • [27] Analysis of 3D face reconstruction
    Amin, S. Hassan
    Gillies, Duncan
    14TH INTERNATIONAL CONFERENCE ON IMAGE ANALYSIS AND PROCESSING, PROCEEDINGS, 2007, : 413 - +
  • [28] Unconstrained 3D Face Reconstruction
    Roth, Joseph
    Tong, Yiying
    Liu, Xiaoming
    2015 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2015, : 2606 - 2615
  • [29] A Method Based on Geometric Invariant Feature for 3D Face Recognition
    Guo, Zhe
    Zhang, Yanning
    Lin, Zenggang
    Feng, Dagan
    PROCEEDINGS OF THE FIFTH INTERNATIONAL CONFERENCE ON IMAGE AND GRAPHICS (ICIG 2009), 2009, : 902 - 906
  • [30] A SFM-BASED SPARSE TO DENSE 3D FACE RECONSTRUCTION METHOD ROBUST TO FEATURE TRACKING ERRORS
    Yang, Chang
    Chen, Jiansheng
    Xia, Cong
    Liu, Jing
    Su, Guangda
    2013 20TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2013), 2013, : 3617 - 3621