Deep, dense and accurate 3D face correspondence for generating population specific deformable models
作者：
Highlights：
• A Deep Network trained on synthetic 3D data to detect facial landmarks is proposed.
• The landmarks are used to establish region based 3D face dense correspondence.
• Correspondence is established across identities and facial expressions.
• A Region based 3D Face deformable model is proposed.
• The model outperforms others in landmarking and face recognition experiments.
摘要
•A Deep Network trained on synthetic 3D data to detect facial landmarks is proposed.•The landmarks are used to establish region based 3D face dense correspondence.•Correspondence is established across identities and facial expressions.•A Region based 3D Face deformable model is proposed.•The model outperforms others in landmarking and face recognition experiments.
论文关键词：Dense 3D face correspondence,3D face morphing,Keypoint detection,Shape descriptor,Face recognition,Landmark identification,Deep learning
论文评审过程：Received 20 October 2016, Revised 13 March 2017, Accepted 12 April 2017, Available online 21 April 2017, Version of Record 2 May 2017.
论文官网地址：https://doi.org/10.1016/j.patcog.2017.04.013
