Depth-Guided Privacy-Preserving Visual Localization Using 3D Sphere Clouds

Abstract

The emergence of deep neural networks capable of revealing high-fidelity scene de- tails from sparse 3D point clouds have raised significant privacy concerns in visual lo- calization involving private maps. Lifting map points to randomly oriented 3D lines is a well-known approach for obstructing undesired recovery of the scene images, but these lines are vulnerable to a density-based attack that can recover the point cloud geometry by observing the neighbourhood statistics of lines. With the aim of nullifying this attack, we present a new privacy-preserving scene representation called sphere cloud, which is constructed by lifting all points to 3D lines crossing the centroid of the map, resembling points on the unit sphere. Since lines are most dense at the map centroid, the sphere cloud mislead the density-based attack algorithm to incorrectly yield points at the cen- troid, effectively neutralizing the attack. Nevertheless, this advantage comes at the cost of i) a new type of attack that may directly recover images from this cloud representation and ii) unresolved translation scale for camera pose estimation. To address these is- sues, we introduce a simple yet effective cloud construction strategy to thwart new attack and propose an efficient localization framework to guide the translation scale by utiliz- ing absolute depth maps acquired from on-device time-of-flight (ToF) sensors. Experi- mental results on public RGB-D datasets demonstrate sphere cloud achieves competitive privacy-preserving ability and localization runtime while not excessively compensating the pose estimation accuracy compared to other depth-guided localization methods.