Facial Expression Cloning with Elastic and Muscle Models

TL;DR

This paper introduces a novel facial expression cloning algorithm that combines elastic and muscle models to improve geometric warping and facial detail accuracy, outperforming existing methods.

Contribution

The paper proposes a new elastic model for balanced warping and a muscle-distribution-based model for detailed facial illumination, enhancing expression cloning effectiveness.

Findings

Outperforms existing expression cloning methods

Balances global and local warping effects effectively

Provides automatic parameter selection for optimal results

Abstract

Expression cloning plays an important role in facial expression synthesis. In this paper, a novel algorithm is proposed for facial expression cloning. The proposed algorithm first introduces a new elastic model to balance the global and local warping effects, such that the impacts from facial feature diversity among people can be minimized, and thus more effective geometric warping results can be achieved. Furthermore, a muscle-distribution-based (MD) model is proposed, which utilizes the muscle distribution of the human face and results in more accurate facial illumination details. In addition, we also propose a new distance-based metric to automatically select the optimal parameters such that the global and local warping effects in the elastic model can be suitably balanced. Experimental results show that our proposed algorithm outperforms the existing methods.