Human pose estimation (HPE) has become essential in numerous applications including healthcare, activity recognition, and human-computer interaction. However, the privacy implications of processing sensitive visual data present significant deployment barriers in critical domains. While traditional anonymization techniques offer limited protection and often compromise data utility for broader motion analysis, Differential Privacy (DP) provides formal privacy guarantees but typically degrades model performance when applied naively. In this work, we present the first comprehensive framework for differentially private 2D human pose estimation (2D-HPE) by applying Differentially Private Stochastic Gradient Descent (DP-SGD) to this task. To effectively balance privacy with performance, we adopt Projected DP-SGD (PDP-SGD), which projects the noisy gradients to a low-dimensional subspace. Next, we incorporate Feature Differential Privacy(FDP) to selectively privatize only sensitive features while retaining public visual cues. Finally, we propose a hybrid feature-projective DP framework that combines both approaches to balance privacy and accuracy for HPE. We evaluate our approach on the MPII dataset across varying privacy budgets, training strategies, and clipping norms. Our combined feature-projective method consistently outperforms vanilla DP-SGD and individual baselines, achieving up to 82.61\% mean [email protected] at $ε= 0.8$, substantially closing the gap to the non-private performance. This work lays foundation for privacy-preserving human pose estimation in real-world, sensitive applications.

翻译：人体姿态估计（HPE）在医疗健康、行为识别和人机交互等众多应用中已变得至关重要。然而，处理敏感视觉数据所带来的隐私影响，在关键领域构成了显著的部署障碍。传统匿名化技术提供的保护有限，且常为更广泛的运动分析而牺牲数据效用；差分隐私（DP）虽能提供形式化的隐私保证，但若直接应用通常会降低模型性能。本研究首次提出了一个全面的差分隐私二维人体姿态估计（2D-HPE）框架，将差分隐私随机梯度下降（DP-SGD）应用于此任务。为有效平衡隐私与性能，我们采用投影差分隐私随机梯度下降（PDP-SGD），将带噪梯度投影至低维子空间。随后，我们引入特征差分隐私（FDP），以选择性私有化仅敏感特征，同时保留公共视觉线索。最后，我们提出一种结合两种方法的混合特征-投影差分隐私框架，以平衡HPE的隐私性与准确性。我们在MPII数据集上，针对不同隐私预算、训练策略和裁剪范数评估了所提方法。我们的组合特征-投影方法在各项指标上均稳定优于原始DP-SGD及单一基线方法，在$ε=0.8$时达到82.61\%的平均[email protected]，显著缩小了与非隐私性能的差距。此项工作为现实世界敏感应用中的隐私保护人体姿态估计奠定了基础。