3D Face Reconstruction With Local Feature Refinement

In this paper, we propose 3D face reconstruction from two or three images. The reconstruction process begins with a face localization and facial feature extraction. Global transformation process is done for facial features which have been obtained. Local feature refinement is used to refine the result of global transformation. Last, texture mapping process is done to provide texture of 3D model. The method used for face reconstruction can generate accurate and fast result for various poses and facial expressions, and by using local feature refinement can improve the quality of reconstruction output more similar to the original face image.