Example-based Automatic Portraiture
Hong Chen, Liang Lin, Yingqing Xu, Heung‐Yeung Shum, Nanning Zheng · 2002
In this paper, we present an example-based approach for automatically generating a life-like portrait from a frontal face image. Based on an inhomogeneous Markov Random Field Model, an inhomogeneous non-parametric sampling scheme is used to capture the complex statistical characteristics of face image and corresponding portrait. In our approach, only those pixels corresponding to a portrait point are sampled. Such a strategy is crucial for maintaining facial structure and guaranteeing coherence of portrait lines. Experimental results demonstrate the effectiveness and lifelikeness of our approach. 1