用户可配置的3D对象再生，以保护空间隐私
User configurable 3D object regeneration for spatial privacy
摘要：
$\textit{augmented}$（AR）和$\textit{mixed reality}$（MR）设备的环境理解能力通过传感、计算机视觉和机器学习的进步而不断提高。各种AR/MR应用展示了这样的能力，即，使用手持或头戴式设备扫描空间并捕获作为真实空间的精确副本的空间的数字表示。然而，这些能力给用户带来隐私风险：个人可识别信息可能从敏感空间的捕获的3D地图和/或映射空间内的捕获的敏感对象泄漏。因此，在这项工作中，我们演示了如何利用3D对象再生来保护3D点云的隐私。也就是说，我们采用中间保护层来转换3D点云，然后再将其提供给第三方应用程序。具体来说，我们使用现有的对抗性自动编码器来生成3D对象的副本，其中副本与原始副本的相似性可以变化。为了测试该方法作为隐私保护机制的可行性和性能，我们使用3D分类器来分类和识别这些变换后的点云，即执行$\textit{super}$类和$\textit{intra}$类分类。为了衡量所提出的隐私框架的性能，我们定义隐私，$Π\in[0,1]$，和效用指标，$Q\in[0,1]$，这是希望被最大化。实验评估表明，隐私框架确实可以通过改变特权级别$l\in[0,1]$，即，如果保持低$l<0.17$，则确保$Π_1,Π_2>0.4$，其中$Π_1,Π_2$是超类和类内隐私，来影响3D对象的隐私。最后，如果特权级别保持在$0.17<l<0.25$的范围内，则隐私框架可以确保相对高的类内隐私和实用性，即$Π_2>0.63$和$Q>0.70$。
英文摘要：
Environmental understanding capability of $\textit{augmented}$ (AR) and $\textit{mixed reality}$ (MR) devices are continuously improving through advances in sensing, computer vision, and machine learning. Various AR/MR applications demonstrate such capabilities i.e. scanning a space using a handheld or head mounted device and capturing a digital representation of the space that are accurate copies of the real space. However, these capabilities impose privacy risks to users: personally identifiable information can leak from captured 3D maps of the sensitive spaces and/or captured sensitive objects within the mapped space. Thus, in this work, we demonstrate how we can leverage 3D object regeneration for preserving privacy of 3D point clouds. That is, we employ an intermediary layer of protection to transform the 3D point cloud before providing it to the third-party applications. Specifically, we use an existing adversarial autoencoder to generate copies of 3D objects where the likeness of the copies from the original can be varied. To test the viability and performance of this method as a privacy preserving mechanism, we use a 3D classifier to classify and identify these transformed point clouds i.e. perform $\textit{super}$-class and $\textit{intra}$-class classification. To measure the performance of the proposed privacy framework, we define privacy, $Π\in[0,1]$, and utility metrics, $Q\in[0,1]$, which are desired to be maximized. Experimental evaluation shows that the privacy framework can indeed variably effect the privacy of a 3D object by varying the privilege level $l\in[0,1]$ i.e. if a low $l<0.17$ is maintained, $Π_1,Π_2>0.4$ is ensured where $Π_1,Π_2$ are super- and intra-class privacy. Lastly, the privacy framework can ensure relatively high intra-class privacy and utility i.e. $Π_2>0.63$ and $Q>0.70$, if the privilege level is kept within the range of $0.17<l<0.25$.
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。
