SCHIGAND: A Synthetic Facial Generation Mode Pipeline

TL;DR

SCHIGAND is a new pipeline that combines multiple generative models to produce realistic, diverse, and controllable synthetic facial datasets suitable for biometric testing, addressing privacy and data scarcity issues.

Contribution

It introduces a novel integration of StyleCLIP, HyperStyle, InterfaceGAN, and Diffusion models for high-quality synthetic face generation with enhanced identity preservation.

Findings

SCHIGAND produces highly realistic facial images with diverse intra-class variations.

The generated datasets perform comparably to real data in biometric verification tasks.

SCHIGAND effectively balances image quality, diversity, and identity retention.

Abstract

The growing demand for diverse and high-quality facial datasets for training and testing biometric systems is challenged by privacy regulations, data scarcity, and ethical concerns. Synthetic facial images offer a potential solution, yet existing generative models often struggle to balance realism, diversity, and identity preservation. This paper presents SCHIGAND, a novel synthetic face generation pipeline integrating StyleCLIP, HyperStyle, InterfaceGAN, and Diffusion models to produce highly realistic and controllable facial datasets. SCHIGAND enhances identity preservation while generating realistic intra-class variations and maintaining inter-class distinctiveness, making it suitable for biometric testing. The generated datasets were evaluated using ArcFace, a leading facial verification model, to assess their effectiveness in comparison to real-world facial datasets. Experimental results demonstrate that SCHIGAND achieves a balance between image quality and diversity, addressing key limitations of prior generative models. This research highlights the potential of SCHIGAND to supplement and, in some cases, replace real data for facial biometric applications, paving the way for privacy-compliant and scalable solutions in synthetic dataset generation.