A survey on face modeling: building a bridge between face analysis and synthesis

Face modeling refers to modeling the shape and appearance of human faces which lays the basis for model-based facial analysis, synthesis and animation. This paper summarizes the existing state-of-the-art work on face modeling and animation in the Computer Graphics and the Computer Vision areas. While some models or techniques are exclusively used for facial analysis or for facial animation and synthesis, other models combine analysis and synthesis in an analysis-by-synthesis loop. This paper introduces a taxonomy of face modeling methods in function of the area of application (synthesis and analysis) and builds a link between the two by reviewing analysis-by-synthesis face modeling methods. The interest of such a taxonomy is to introduce new face models that combine ideas from the analysis and synthesis domains. We also provide an overview of the extensions of the seminal works presented in this paper. Within each category, we discuss the advantages and disadvantages of each method with respect to the others.