Learning Flexibly Distributional Representation for Low-quality 3D Face Recognition

Authors

  • Zihui Zhang Xi'an Jiaotong University
  • Cuican Yu Xi'an Jiaotong University
  • Shuang Xu Xi'an Jiaotong University
  • Huibin Li Xi'an Jiaotong University

Keywords:

3D Computer Vision, Biometrics, Face, Gesture & Pose

Abstract

Due to the superiority of using geometric information, 3D Face Recognition (FR) has achieved great successes. Existing methods focus on high-quality 3D FR which is unpractical in real scenarios. Low-quality 3D FR is a more realistic scenario but the low-quality data are born with heavy noises. Therefore, exploring noise-robust low-quality 3D FR methods becomes an urgent and challenging problem. To solve this issue, in this paper, we propose to learn flexibly distributional representation for low-quality 3D FR. Firstly, we introduce the distributional representation for low-quality 3D faces due to that it can weaken the impact of noises. Generally, the distributional representation of a given 3D face is restricted to a specific distribution such as Gaussian distribution. However, the specific distribution may be not up to describing the complex low-quality face. Therefore, we propose to transform this specific distribution to a flexible one via Continuous Normalizing Flow (CNF), which can get rid of the form limitation. This kind of flexible distribution can approximate the latent distribution of the given noisy face more accurately, which further improves accuracy of low-quality 3D FR. Comprehensive experiments show that our proposed method improves both low-quality and cross-quality 3D FR performances on low-quality benchmarks. Furthermore, the improvements are more remarkable on low-quality 3D faces when the intensity of noise increases which indicate the robustness

Downloads

Published

2021-05-18

How to Cite

Zhang, Z., Yu, C., Xu, S., & Li, H. (2021). Learning Flexibly Distributional Representation for Low-quality 3D Face Recognition. Proceedings of the AAAI Conference on Artificial Intelligence, 35(4), 3465-3473. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16460

Issue

Section

AAAI Technical Track on Computer Vision III