arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.16627cs.CVcs.CY
收藏

SCHIGAND:一个合成面部生成模式流水线

SCHIGAND: A Synthetic Facial Generation Mode Pipeline

School of Electronics and Computer Science, University of Southampton(南安普顿大学电子与计算机科学学院)

Ananya Kadali, Sunnie Jehan-Morrison, Orasiki Wellington, Barney Evans, Precious Durojaiye, Richard Guest

AI总结:

SCHIGAND通过集成多种生成模型,生成高质量可控的合成面部数据集,用于生物识别测试,解决了真实感、多样性和身份保持之间的平衡问题。

摘要:

随着对多样且高质量面部数据集的需求增长,隐私法规、数据稀缺性和伦理问题对生物识别系统训练和测试构成了挑战。合成面部图像提供了一种潜在解决方案,但现有生成模型往往难以在真实感、多样性与身份保持之间取得平衡。本文提出了SCHIGAND,一种新的合成面部生成流水线,集成了StyleCLIP、HyperStyle、InterfaceGAN和扩散模型,以生成高度真实且可控的面部数据集。SCHIGAND在生成真实感的同时增强了身份保持,产生了真实的类内变化并保持类间差异性,使其适用于生物识别测试。生成的数据集通过ArcFace,一种领先的面部验证模型,进行评估,以评估其在与真实世界面部数据集比较中的有效性。实验结果表明,SCHIGAND在图像质量和多样性之间实现了平衡,解决了先前生成模型的关键限制。这项研究突显了SCHIGAND在补充甚至在某些情况下替代真实数据以进行面部生物识别应用的潜力,为在合成数据集生成中实现隐私合规和可扩展的解决方案铺平了道路。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑