Lock3DFace: A Large-Scale Database of Low-Cost Kinect 3D Faces



The Lock3DFace database totally consists of 5671 RGBD face video clips belonging to 509 individuals with diverse changes in facial expression, pose, occlusion and time lapse.
It is mainly designed for low cost 3D FR, but also for 2D FR, near infrared FR, multi-modal (RGBD) FR, and heterogeneous FR.

Data organization of the Lock3DFace database in terms of different challenges:



G. Mu, D. Huang, G. Hu, J. Sun, and Y. Wang: Led3D: A Lightweight and Efficient Deep Approach to Recognizing Low-quality 3D Faces, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, USA, 2019. [ PDF ][ Code will be coming soon ]

J. Zhang, D. Huang, Y. Wang, and J. Sun: Lock3DFace: A Large-Scale Database of Low-Cost Kinect 3D Faces, IEEE International Conference on Biometrics (ICB), Halmstad, Sweden, 2016. [ PDF ]


Please complete this agreement [ PDF ], and send the scanned version with the signature of a permanent staff to 'dhuang@buaa.edu.cn'. If the agreement is approved, we will send you a link to download data.