In this paper, we study face hallucination, or synthesizing a high-resolution face image from low-resolution input, with the help of a large collection of high-resolution face images. We develop a two-step statistical modeling approach that integrates both a global parametric model and a local nonparametric model. First, we derive a global linear model to learn the relationship between the high-resolution face images and their smoothed and down-sampled lower resolution ones. Second, the residual between an original high-resolution image and the reconstructed high-resolution image by a learned linear model is modeled by a patch-based nonparametric Markov network, to capture the high-frequency content of faces. By integrating both global and local models, we can generate photorealistic face images. Our approach is demonstrated by extensive experiments with high-quality hallucinated faces.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    A two-step approach to hallucinating faces: global parametric model and local nonparametric model


    Contributors:


    Publication date :

    2001-01-01


    Size :

    1292351 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    A Two-Step Approach to Hallucinating Faces: Global Parametric Model and Local Nonparametric Model

    Liu, C. / Shum, H.-Y. / Zhang, C.-S. et al. | British Library Conference Proceedings | 2001


    Hallucinating 3D Faces

    Peng, Shiqi / Pan, Gang / Han, Shi et al. | Springer Verlag | 2006


    Hallucinating 3D Faces

    Peng, S. / Pan, G. / Han, S. et al. | British Library Conference Proceedings | 2006