用3D渲染+扩散模型生成隐私合规的合成人脸，保姿态又保质量。
Rendering-Refined Stable Diffusion for Privacy Compliant Synthetic Data
- 结合3D渲染与扩散模型，按提示词控制人物属性且保留姿势
- 用隐私数据训练的模型在检测任务中表现优于真实数据
- 适合需要保护隐私又兼顾数据实用性的图像生成场景
日益增长的隐私担忧和法规（如GDPR、CCPA）要求对图像数据集进行身份匿名化处理，同时保持数据可用性。传统方法如遮挡或模糊会降低图像质量并掩盖关键上下文，尤其在涉及人类的图像中效果差。我们提出Rendering-Refined Stable Diffusion（RefSD）管道，融合3D渲染与Stable Diffusion，实现基于提示词对人物属性的可控生成，同时保持原始姿态。相比标准扩散模型无法保留姿态，或GAN缺乏真实感和灵活控制的问题，RefSD在姿态保持、真实性和可定制性之间取得平衡。我们还提出HumanGenAI框架用于评估人类感知与数据效用。感知测试揭示了RefSD在不同属性上的优劣势；效用实验表明，使用RefSD生成的匿名数据训练的模型在检测任务中表现优于仅用真实数据训练的模型，且结合真实数据后性能进一步提升。分类任务中，使用混合数据也持续带来性能增益，验证了该匿名数据的有效性。
原文摘要 · Abstract (English)
Growing privacy concerns and regulations like GDPR and CCPA necessitate pseudonymization techniques that protect identity in image datasets. However, retaining utility is also essential. Traditional methods like masking and blurring degrade quality and obscure critical context, especially in human-centric images. We introduce Rendering-Refined Stable Diffusion (RefSD), a pipeline that combines 3D-rendering with Stable Diffusion, enabling prompt-based control over human attributes while preserving posture. Unlike standard diffusion models that fail to retain posture or GANs that lack realism and flexible attribute control, RefSD balances posture preservation, realism, and customization. We also propose HumanGenAI, a framework for human perception and utility evaluation. Human perception assessments reveal attribute-specific strengths and weaknesses of RefSD. Our utility experiments show that models trained on RefSD pseudonymized data outperform those trained on real data in detection tasks, with further performance gains when combining RefSD with real data. For classification tasks, we consistently observe performance improvements when using RefSD data with real data, confirming the utility of our pseudonymized data.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。