Exploiting temporal and depth information for multi-frame face anti-spoofing

TL;DR

This paper introduces a multi-frame depth estimation method for face anti-spoofing that leverages spatiotemporal cues through novel modules, achieving state-of-the-art results on multiple benchmarks.

Contribution

It develops a new depth-supervised architecture using optical flow and ConvGRU modules to encode short-term and long-term motion for improved anti-spoofing.

Findings

Achieves state-of-the-art performance on four benchmark datasets.

Effectively encodes spatiotemporal information for presentation attack detection.

Outperforms previous single-frame depth-based methods.

Abstract

Face anti-spoofing is significant to the security of face recognition systems. Previous works on depth supervised learning have proved the effectiveness for face anti-spoofing. Nevertheless, they only considered the depth as an auxiliary supervision in the single frame. Different from these methods, we develop a new method to estimate depth information from multiple RGB frames and propose a depth-supervised architecture which can efficiently encodes spatiotemporal information for presentation attack detection. It includes two novel modules: optical flow guided feature block (OFFB) and convolution gated recurrent units (ConvGRU) module, which are designed to extract short-term and long-term motion to discriminate living and spoofing faces. Extensive experiments demonstrate that the proposed approach achieves state-of-the-art results on four benchmark datasets, namely OULU-NPU, SiW, CASIA-MFSD, and Replay-Attack.