On 3D face reconstruction via cascaded regression in shape space

作     者：Feng LIU Dan ZENG Jing LI Qi-jun ZHAO Feng LIU;Dan ZENG;Jing LI;Qi-jun ZHAO

作者机构：College of Computer Science Sichuan University Chengdu 610065 China 

出 版 物：《Frontiers of Information Technology & Electronic Engineering》 (信息与电子工程前沿（英文版）)

年 卷 期：2017年第18卷第12期

页      面：1978-1990页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 08[工学] 

基　　金：Project supported by the National Key Research and Development Program of China(Nos.2017YFB0802303and 2016YFC0801100) the National Key Scientific Instrument and Equipment Development Projects of China(No.2013YQ49087904) the National Natural Science Foundation of China(No.61773270) the Miaozi Key Project in Science and Technology Innovation Program of Sichuan Province,China(No.2017RZ0016) 

主　　题：3D face reconstruction Cascaded regressor Shape space Real-time 

摘      要：Cascaded regression has been recently applied to reconstruct 3D faces from single 2D images directly in shape space, and has achieved state-of-the-art performance. We investigate thoroughly such cascaded regression based 3D face reconstruction approaches from four perspectives that are not well been studied： （1） the impact of the number of 2D landmarks; （2） the impact of the number of 3D vertices; （3） the way of using standalone automated landmark detection methods; （4） the convergence property. To answer these questions, a simplified cascaded regression based 3D face reconstruction method is devised. This can be integrated with standalone automated landmark detection methods and reconstruct 3D face shapes that have the same pose and expression as the input face images, rather than normalized pose and expression. An effective training method is also proposed by disturbing the automatically detected landmarks. Comprehensive evaluation experiments have been carried out to compare to other 3D face reconstruction methods. The results not only deepen the understanding of cascaded regression based 3D face reconstruction approaches, but also prove the effectiveness of the proposed method.