In this paper, we develop an efficient technique for fully automatic recovery of accurate 3D face shape from videos captured by a low cost camera. The method is designed to work with a short video containing a face rotating from frontal view to profile view. The whole approach consists of three components. First, automatic initialization is performed in the first frame with approximately frontal face. Then, to handle the case of low quality image captured by low cost camera, the 2D feature matching, head poses and underlying 3D face shape are estimated and refined iteratively in an efficient way based on image sequence segmentation. Finally, to take advantage of the sparse structure of the proposed algorithm, sparse bundle adjustment technique is further employed to speed up the computation. We demonstrate the accuracy and robustness of the algorithm using a set of experiments.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Automatic 3D face modeling from video


    Contributors:
    Le Xin, (author) / Qiang Wang, (author) / Jianhua Tao, (author) / Xiaoou Tang, (author) / Tieniu Tan, (author) / Shum, H. (author)


    Publication date :

    2005-01-01


    Size :

    555550 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Automatic 3D Face Modeling from Video

    Xin, L. / Wang, Q. / Tao, J. et al. | British Library Conference Proceedings | 2005


    Automatic face segmentation for 3-D model-based video coding

    Sheng, Y. / Sadka, A. H. / Kondoz, A. M. et al. | British Library Conference Proceedings | 2003


    Automatic Video Summarization by Graph Modeling

    Ngo, C. / Ma, Y. / Zhang, H. et al. | British Library Conference Proceedings | 2003


    Dictionary-Based Face Recognition from Video

    Chen, Y.-C. / Patel, V.M. / Phillips, P.J. et al. | British Library Conference Proceedings | 2012


    Towards robust face recognition from video

    Price, J.R. / Gee, T.E. | IEEE | 2001