A High Resolution Grammatical Model for Face Representation and Sketching

Authors:
Zijian Xu;Hong Chen;Song-Chun Zhu
Affiliations:
University of California at Los Angeles;University of California at Los Angeles;University of California at Los Angeles
Venue:
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Year:
2005

Citing 0
Cited 8

A Generative Sketch Model for Human Hair Analysis and Synthesis

IEEE Transactions on Pattern Analysis and Machine Intelligence
A stochastic grammar of images

Foundations and Trends® in Computer Graphics and Vision
Perceptual Scale-Space and Its Applications

International Journal of Computer Vision
Fast Simplex Optimization for Active Appearance Model

PSIVT '09 Proceedings of the 3rd Pacific Rim Symposium on Advances in Image and Video Technology
Computational methods for modeling facial aging: A survey

Journal of Visual Languages and Computing
Synthesis of exaggerative caricature with inter and intra correlations

ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part I
An automatic portrait system based on and-or graph representation

EMMCVPR'07 Proceedings of the 6th international conference on Energy minimization methods in computer vision and pattern recognition
Adapted active appearance models

Journal on Image and Video Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we present a generative, high resolution face representation which extends the well-known active appearance model (AAM)[5, 6, 7] with two additional layers. (i) One layer refines the global AAM (PCA) model with a dictionary of learned face components to account for the shape and intensity variabilities of eyes, eyebrows, nose and mouth. (ii) The other layer divides the face skin into 9 zones with a learned dictionary of sketch primitives to represent skin marks and wrinkles. This model is no longer of fixed dimensions and is flexible for it can select the diverse representations in the dictionaries of face components and skin features depending on the complexity of the face. The selection is modulated by the grammatical rules through hidden "switch" variables. Our comparison experiments demonstrate that this model can achieve nearly lossless coding of face at high resolution (256 脳 256 pixels) with low bits. We also show that the generative model can easily generate cartoon sketches by changing the rendering dictionary. Our face model is aimed at a number of applications including cartoon sketch in non-photorealistic rendering, superresolution in image processing, and low bit face communication in wireless platforms.