A Closer Look at Geometric Temporal Dynamics for Face Anti-Spoofing
This addresses the challenge of robustness against domain shifts and unseen spoofing types in face recognition systems, representing a strong specific gain rather than a foundational breakthrough.
The paper tackled the problem of face anti-spoofing by distinguishing normal vs. abnormal movements in live and spoof presentations, achieving state-of-the-art performance with a +10.26% higher AUC score on CASIA-SURF 3DMask in cross-dataset cross-type evaluations.
Face anti-spoofing (FAS) is indispensable for a face recognition system. Many texture-driven countermeasures were developed against presentation attacks (PAs), but the performance against unseen domains or unseen spoofing types is still unsatisfactory. Instead of exhaustively collecting all the spoofing variations and making binary decisions of live/spoof, we offer a new perspective on the FAS task to distinguish between normal and abnormal movements of live and spoof presentations. We propose Geometry-Aware Interaction Network (GAIN), which exploits dense facial landmarks with spatio-temporal graph convolutional network (ST-GCN) to establish a more interpretable and modularized FAS model. Additionally, with our cross-attention feature interaction mechanism, GAIN can be easily integrated with other existing methods to significantly boost performance. Our approach achieves state-of-the-art performance in the standard intra- and cross-dataset evaluations. Moreover, our model outperforms state-of-the-art methods by a large margin in the cross-dataset cross-type protocol on CASIA-SURF 3DMask (+10.26% higher AUC score), exhibiting strong robustness against domain shifts and unseen spoofing types.