Led3D: A Lightweight and Efficient Deep Approach to Recognizing Low-Quality 3D Faces

Guodong Mu, Di Huang, Guosheng Hu, Jia Sun, Yunhong Wang; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 5773-5782

Abstract


Due to the intrinsic invariance to pose and illumination changes, 3D Face Recognition (FR) has a promising potential in the real world. 3D FR using high-quality faces, which are of high resolutions and with smooth surfaces, have been widely studied. However, research on that with low-quality input is limited, although it involves more applications. In this paper, we focus on 3D FR using low-quality data, targeting an efficient and accurate deep learning solution. To achieve this, we work on two aspects: (1) designing a lightweight yet powerful CNN; (2) generating finer and bigger training data. For (1), we propose a Multi-Scale Feature Fusion (MSFF) module and a Spatial Attention Vectorization (SAV) module to build a compact and discriminative CNN. For (2), we propose a data processing system including point-cloud recovery, surface refinement, and data augmentation (with newly proposed shape jittering and shape scaling). We conduct extensive experiments on Lock3DFace and achieve state-of-the-art results, outperforming many heavy CNNs such as VGG-16 and ResNet-34. In addition, our model can operate at a very high speed (136 fps) on Jetson TX2, and the promising accuracy and efficiency reached show its great applicability on edge/mobile devices.

Related Material


[pdf]
[bibtex]
@InProceedings{Mu_2019_CVPR,
author = {Mu, Guodong and Huang, Di and Hu, Guosheng and Sun, Jia and Wang, Yunhong},
title = {Led3D: A Lightweight and Efficient Deep Approach to Recognizing Low-Quality 3D Faces},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}