不要深度伪造我：无敏感图像的隐私保护神经 3D 头部重建
Do Not DeepFake Me: Privacy-Preserving Neural 3D Head Reconstruction Without Sensitive Images
AI总结：
本文提出一种两阶段隐私保护 3D 面部重建方法，利用非敏感后脑图像和移除隐私的梯度图像重建几何，在保持精度的同时抵御 DeepFake 与面部识别系统。
摘要：
虽然 3D 头部重建被广泛用于建模，但现有的神经重建方法依赖高分辨率多视图图像，引发了显著的隐私问题。个人对面部特征尤为敏感，面部图像泄露可能导致许多恶意活动，如未经授权的跟踪和 deepfake。相比之下，几何数据由于其复杂的处理要求以及缺乏面部纹理特征，较难被滥用。本文提出了一种新颖的两阶段 3D 面部重建方法，旨在避免暴露敏感面部信息的同时保持详细的几何精度。我们的方法首先使用非敏感的后脑图像进行初始几何构建，然后利用处理过的、已移除隐私的梯度图像对该几何进行细化。大量实验表明，所得几何结构与使用完整图像的方法相当，同时该过程对 DeepFake 应用和面部识别（FR）系统具有抵抗力，从而证明了其在隐私保护方面的有效性。
英文摘要：
While 3D head reconstruction is widely used for modeling, existing neural reconstruction approaches rely on high-resolution multi-view images, posing notable privacy issues. Individuals are particularly sensitive to facial features, and facial image leakage can lead to many malicious activities, such as unauthorized tracking and deepfake. In contrast, geometric data is less susceptible to misuse due to its complex processing requirements, and absence of facial texture features. In this paper, we propose a novel two-stage 3D facial reconstruction method aimed at avoiding exposure to sensitive facial information while preserving detailed geometric accuracy. Our approach first uses non-sensitive rear-head images for initial geometry and then refines this geometry using processed privacy-removed gradient images. Extensive experiments show that the resulting geometry is comparable to methods using full images, while the process is resistant to DeepFake applications and facial recognition (FR) systems, thereby proving its effectiveness in privacy protection.
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。
