Non-Photorealistic Computer Graphics Library

[ home · search · about · links · contact · rss ] [ submit bibtex ] [ BookCite · NPR Books ]



Proceedings Example-based Automatic Portraiture

Author(s): Hong Chen, Lin Liang, Ying-Qing Xu, Heung-Yeung Shum, Nan-Ning Zheng.
Proceedings: The 5th Asian Conference on Computer Vision (ACCV2002), Melbourne, Australia, 23–25 January, 2002.
[BibTeX] Find this paper on Google

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.

Visitors: 117204