Text-to-Image Synthesis for Domain Generalization in Face Anti-Spoofing

• Published in: Proceedings / IEEE Workshop on Applications of Computer Vision pp. 1850 - 1860
• Main Authors: Ko, Naeun, Jeong, Yonghyun, Ye, Jong Chul
• Format: Conference Proceeding
• Language: English
• Published: IEEE 26.02.2025
• Subjects: Adaptation models; domain generalization; face anti-spoofing; Face recognition; Facial features; Instruments; Protocols; Robustness; Synthetic data; Technological innovation; Text to image; text-to-image-based synthetic data generation; Training
• ISSN: 2642-9381
• DOI: 10.1109/WACV61041.2025.00618

This paper addresses the challenge of developing robust Face Anti-Spoofing (FAS) models for face recognition systems. Traditional FAS protocols are limited by a lack of diversity in subject identities and environmental conditions, restricting generalization to real-world scenarios. Recent advancements in spoof image synthesis have mitigated data scarcity but still fail to capture the full range of facial attributes and environmental variability needed for effective domain generalization. To address this, we propose a novel framework capable of generating diverse, realistic facial images with text-guided control. We fine-tune Stable Diffusion to extract real facial features and specifically train LoRA layers to capture detailed spoof patterns. Addition-ally, the text-guided control of attributes helps overcome the lack of diversity seen in previous methods. Extensive experiments demonstrate that our text-to-image-based syn-thetic data generation significantly enhances the robustness of FAS models, establishing a new benchmark for domain-independent and reliable anti-spoofing systems.