TY - GEN
T1 - PointFace
T2 - 2021 IEEE International Joint Conference on Biometrics, IJCB 2021
AU - Jiang, Changyuan
AU - Lin, Shisong
AU - Chen, Wei
AU - Liu, Feng
AU - Shen, Linlin
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/8/4
Y1 - 2021/8/4
N2 - Though 2D face recognition (FR) has achieved great success due to powerful 2D CNNs and large-scale training data, it is still challenged by extreme poses and illumination conditions. On the other hand, 3D FR has the potential to deal with aforementioned challenges in the 2D domain. However, most of available 3D FR works transform 3D surfaces to 2D maps and utilize 2D CNNs to extract features. The works directly processing point clouds for 3D FR is very limited in literature. To bridge this gap, in this paper, we propose a light-weight framework, named PointFace, to directly process point set data for 3D FR. Inspired by contrastive learning, our PointFace use two weight-shared encoders to directly extract features from a pair of 3D faces. A feature similarity loss is designed to guide the encoders to obtain discriminative face representations. We also present a pair selection strategy to generate positive and negative pairs to boost training. Extensive experiments on Lock3DFace and Bosphorus show that the proposed PointFace outperforms state-of-The-Art 2D CNN based methods.
AB - Though 2D face recognition (FR) has achieved great success due to powerful 2D CNNs and large-scale training data, it is still challenged by extreme poses and illumination conditions. On the other hand, 3D FR has the potential to deal with aforementioned challenges in the 2D domain. However, most of available 3D FR works transform 3D surfaces to 2D maps and utilize 2D CNNs to extract features. The works directly processing point clouds for 3D FR is very limited in literature. To bridge this gap, in this paper, we propose a light-weight framework, named PointFace, to directly process point set data for 3D FR. Inspired by contrastive learning, our PointFace use two weight-shared encoders to directly extract features from a pair of 3D faces. A feature similarity loss is designed to guide the encoders to obtain discriminative face representations. We also present a pair selection strategy to generate positive and negative pairs to boost training. Extensive experiments on Lock3DFace and Bosphorus show that the proposed PointFace outperforms state-of-The-Art 2D CNN based methods.
UR - http://www.scopus.com/inward/record.url?scp=85113286916&partnerID=8YFLogxK
U2 - 10.1109/IJCB52358.2021.9484368
DO - 10.1109/IJCB52358.2021.9484368
M3 - Conference contribution
AN - SCOPUS:85113286916
T3 - 2021 IEEE International Joint Conference on Biometrics, IJCB 2021
BT - 2021 IEEE International Joint Conference on Biometrics, IJCB 2021
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 4 August 2021 through 7 August 2021
ER -