Three dimensional cartoon reconstruction based on Art rules

In this paper, a kind of three dimensional reconstruction method based on aesthetic rules is proposed. In this method, the key features of the human face are captured according to human vision. The cartoon reconstruction process is divided into two parts of global deformation and local feature exaggeration. Our method requires only a few typical manually exaggerated models to generate 3D cartoon faces automatically. Experimental results show that our method can achieve proper exaggerations for the details of the five sense organs while maintaining the global characteristics of the human face with small distortions.