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 17 条
  • [1] A morphable model for the synthesis of 3D faces
    Blanz, V
    Vetter, T
    [J]. SIGGRAPH 99 CONFERENCE PROCEEDINGS, 1999, : 187 - 194
  • [2] A statistical method for robust 3D surface reconstruction from sparse data
    Blanz, V
    Mehl, A
    Vetter, T
    Seidel, HP
    [J]. 2ND INTERNATIONAL SYMPOSIUM ON 3D DATA PROCESSING, VISUALIZATION, AND TRANSMISSION, PROCEEDINGS, 2004, : 293 - 300
  • [3] Gong X., 2013, LNCS, V8232, P1, DOI [10.1007/978-3-319-02961-0, DOI 10.1007/978-3-319-02961-0]
  • [4] Gong X, 2011, CHINESE J ELECTRON, V20, P671
  • [5] Gong X, 2010, CHINESE J ELECTRON, V19, P676
  • [6] Realistic face modeling based on multiple deformations
    GONG, Xun
    WANG, Guo-yin
    [J]. Journal of China Universities of Posts and Telecommunications, 2007, 14 (04): : 110 - 117
  • [7] Kennedy J, 1995, 1995 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS PROCEEDINGS, VOLS 1-6, P1942, DOI 10.1109/icnn.1995.488968
  • [8] Recovering the 3D shape and poses of face images based on the similarity transform
    Koo, Hei-Sheung
    Lam, Kin-Man
    [J]. PATTERN RECOGNITION LETTERS, 2008, 29 (06) : 712 - 723
  • [9] ACCURATE AND EFFICIENT RECONSTRUCTION OF 3D FACES FROM STEREO IMAGES
    Le, Vuong
    Tang, Hao
    Cao, Liangliang
    Huang, Thomas S.
    [J]. 2010 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, 2010, : 4265 - 4268
  • [10] Head Reconstruction from Internet Photos
    Liang, Shu
    Shapiro, Linda G.
    Kemelmacher-Shlizerman, Ira
    [J]. COMPUTER VISION - ECCV 2016, PT II, 2016, 9906 : 360 - 374