Supervised coordinate descent method with a 3D bilinear model for face alignment and tracking. (21st May 2017)

• Record Type: Journal Article
• Authors: Zhang, Yongqiang; Liu, Shuang; Yang, Xiaosong; Zhang, Jianjun; Shi, Daming
• Is Part Of: Computer animation and virtual worlds. Volume 28:Number 3/4(2017)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2017-05-21
• Subjects: face alignment -- face tracking -- facial performance capture -- supervised coordinate descent method; Computer animation -- Periodicals; Visualization -- Periodicals; 006.6
• DOI: 10.1002/cav.1773
• Languages: English
• ISSNs: 1546-4261

Abstract

Abstract: Face alignment and tracking play important roles in facial performance capture. Existing data‐driven methods for monocular videos suffer from large variations of pose and expression. In this paper, we propose an efficient and robust method for this task by introducing a novel supervised coordinate descent method with 3D bilinear representation. Instead of learning the mapping between the whole parameters and image features directly with a cascaded regression framework in current methods, we learn individual sets of parameters mappings separately step by step by a coordinate descent mean. Because different parameters make different contributions to the displacement of facial landmarks, our method is more discriminative to current whole‐parameter cascaded regression methods. Benefiting from a 3D bilinear model learned from public databases, the proposed method can handle the head pose changes and extreme expressions out of plane better than other 2D‐based methods. We present the reliable result of face tracking under various head poses and facial expressions on challenging video sequences collected online. The experimental results show that our method outperforms state‐of‐art data‐driven methods. Abstract : We propose a novel supervised coordinate descent method for learning different parameters mappings separately to reduce the cross impact caused by learning a whole‐parameter mapping. Taking advantage of a 3‐D bilinear model learned from public databases, our method can handle large pose and expression variations in 3‐D space with accuracy–overcoming the deficiencies of existing methods. Our method is validated and compared in challenging face videos collected online.