Efficient and Reliable 3D Face Analysis

Along with the fast development of 3D imaging techniques, it has become possible that 3D face scans can be captured in real-time dynamic flows of an acceptable resolution and some low-cost depth cameras, such as Microsoft Kinect and Intel RealSense, have shown their perspectives in practical scenarios. Furthermore, Face ID delivered by iPhone has proved that the 3D solution is able to largely improve person identification applications. Therefore, in recent years, efficient and reliable 3D face analysis, especially for portable smart terminals, has been greatly extended and has received increasing attentions in the academia and industry.

Different from previous research on 3D face analysis, this special session aims at dis-cussing two major aspects: (1) efficient methods for practical 3D face analysis, e.g. light-weight deep model, and (2) reliable 3D face analysis methods robust to illumination, pose, occlusion, spoofing, etc. We welcome submissions on topics related to the two questions.


Dr. Di Huang, Beihang University, China.
Dr. Qijun Zhao, Sichuan University, China.
Dr. Hu Han, Institute of Computing Technology, CAS, China.


  • Full Paper Submission: January 6, 2019 – midnight PST
  • Camera Ready Deadline for Accepted papers: March 13, 2019


Papers are required to be submitted to the CMT system through this link with the name of the special session “Efficient and Reliable 3D Face Analysis”. The system will be open for new submissions before the deadline, and submissions will be peer-reviewed and follow the standard IEEE FG2019 format. Both long and short papers are accepted to Special Sessions, and the review process is similar to that of the main conference, minus the rebuttal stage.

ANONYMISATION POLICY : Double blind reviews are used. Authors should remove author and institutional identi-ties from the title and header areas of the paper. There should also be no acknowledg-ments. Authors can leave citations to their previous work unanonymized so that review-ers can ensure that all previous research has been taken into account. However, they should cite their own work in the third person (e.g., “[22] found that…”).