Given a person's neutral face image, we can predict his/her expressive face images by machine learning techniques. Different from the prior expression cloning or image analogy approaches, we try to hallucinate the person's plausible facial expression with the help of a face expression database. In the first step, nonlinear manifold learning technique is used to obtain a smooth estimation for the expressive face image. In the second step, Markov network is adopted to learn the low-level local facial feature's relationship between the residual neutral and the expressional face image's patches in the training set, then belief propagation is employed to infer the expressional residual face image for that person. By integrating the two approaches, we obtain the final result. The experimental results show that the hallucinated facial expression is not only expressive but also close to the ground truth.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Facial Expression Hallucination


    Beteiligte:
    Su, Congyong (Autor:in) / Huang, Li (Autor:in)


    Erscheinungsdatum :

    01.01.2005


    Format / Umfang :

    664154 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    A novel kernel-based framework for facial-image hallucination

    Hu, Y. / Lam, K. M. / Shen, T. et al. | British Library Online Contents | 2011


    Hallucination of facial details from degraded images using 3D face models

    Schumacher, M. / Piotraschke, M. / Blanz, V. | British Library Online Contents | 2015


    Face Hallucination: Theory and Practice

    Liu, C. / Shum, H. Y. / Freeman, W. T. | British Library Online Contents | 2007


    Image hallucination with primal sketch priors

    Jian Sun, / Nan-Ning Zheng, / Hai Tao, et al. | IEEE | 2003


    CHAIR -- Classifier of Hallucination as Improver

    Sun, Ao | ArXiv | 2025

    Freier Zugriff