Quantitative and Qualitative Comparison of Generative Models for Subject-Specific Gaze Synthesis: Diffusion vs GANs

Abstract

Gaze-based biometrics has emerged as a promising approach for user authentication, but advances in this area are constrained by the limited availability of high-quality, subject-specific gaze recordings. Recent generative models have shown promise for synthesizing gaze data, yet most existing approaches rely on random noise distributions or global, predefined latent embeddings and do not explicitly model subject-specific gaze characteristics. To address this limitation, we revisit two recent generative models, diffusion and generative adversarial networks (GANs), and modify both to support subject-aware gaze synthesis. For the diffusion-based approach, we incorporate compact user embeddings to capture subject-level gaze traits. For the GAN-based approach, we introduce a subject-specific conditioning module that guides the generator to preserve idiosyncratic gaze patterns. Later, we evaluate both approaches using standard eye-movement signal quality metrics, including spatial accuracy and precision, and assess whether the generated sequences retain identity-related features relevant to biometric applications. Experimental results show that the diffusion-based approach produces more realistic, identity-preserving gaze sequences than the GAN-based approach. Overall, this work advances the understanding of synthetic gaze quality, realism, and subject specificity and supports the development of gaze-based biometric applications.