PrivateEyes：面向数据共享的注视保持匿名化
PrivateEyes: Gaze-Preserving Anonymization for Data Sharing
用分割掩码与眼姿态作为条件驱动扩散模型合成匿名化眼图，在保留注视方向的同时破坏虹膜身份特征，为隐私敏感场景下的条件生成与身份-任务解耦提供了可复用的三阶段范式。
原文依据 a conditional diffusion model that reconstructs realistic, anonymized eye images conditioned on segmentation and pose
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论从头戴式显示器（HMD）等可穿戴设备采集的眼部图像包含可识别的生物特征线索，给安全的数据共享带来重大挑战。现有的眼部匿名化技术往往会降低下游任务性能，尤其是注视估计，同时还保留虹膜可识别特征。尽管这些方法旨在对虹膜进行匿名化，却引入了明显的视觉伪影，降低了图像保真度。为解决上述局限，我们提出 PrivateEyes，一个隐私保护框架，可合成匿名化且注视一致的眼部图像。该方法采用三阶段流程：（1）深度分割网络，分离语义眼部区域并为合成提供结构控制信号；（2）姿态估计网络（PEN），在解剖学准确的合成眼部渲染图上训练，以推断精确的眼部姿态；（3）条件扩散模型，以分割与姿态为条件重建真实、匿名化的眼部图像。在多个基准数据集上的大量实验表明，与最优匿名化基线相比，PrivateEyes 取得更优的注视估计精度，性能提升超过 10%，同时将虹膜识别准确率降低约 50%。与其他现有方法相比，本方法还能生成保真度更高的图像。通过实现任务保持且隐私安全的眼部图像共享，PrivateEyes 支持 AR/VR 及其他注视驱动应用中的负责任研究与开发。
英文原文摘要 1521 字符
Eye images captured from wearable devices such as head-mounted displays (HMDs) contain identifiable biometric cues, posing significant challenges for safe data sharing. Existing eye anonymization techniques often degrade downstream performance, particularly gaze estimation while still retaining iris-recognizable features. Although these methods aim to anonymize the iris, they introduce noticeable visual artifacts that reduce image fidelity. To address these limitations, we propose PrivateEyes, a privacy-preserving framework that synthesizes anonymized yet gaze-consistent eye images. Our approach employs a three-stage pipeline: (1) a deep segmentation network that isolates semantic eye regions and provides structural control signals for synthesis, (2) a pose estimation network (PEN) trained on anatomically accurate synthetic eye renders to infer precise eye pose, and (3) a conditional diffusion model that reconstructs realistic, anonymized eye images conditioned on segmentation and pose. Extensive experiments across multiple benchmark datasets show that PrivateEyes achieves superior gaze-estimation accuracy compared to state-of-the-art anonymization baselines, improving performance by over 10% while reducing iris-recognition accuracy by ~50%. Our method also produces higher-fidelity images compared to other existing approaches. By enabling task-preserving and privacy-secure sharing of eye images, PrivateEyes supports responsible research and development in AR/VR and other gaze-driven applications.