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.
A two-step approach to hallucinating faces: global parametric model and local nonparametric model
2001-01-01
1292351 byte
Conference paper
Electronic Resource
English
A Two-Step Approach to Hallucinating Faces: Global Parametric Model and Local Nonparametric Model
British Library Conference Proceedings | 2001
|Springer Verlag | 2006
|British Library Conference Proceedings | 2006
|