Privacy-preserving Reflection Rendering for Augmented Reality
Yiqin Zhao, Sheng Wei, Tian Guo
Abstract
When the virtual objects consist of reflective materials, the required lighting information to render such objects can consist of privacy-sensitive information outside the current camera view. In this paper, we show, for the first time, that accuracy-driven multi-view environment lighting can reveal out-of-camera scene information and compromise privacy. We present a simple yet effective privacy attack that extracts sensitive scene information such as human faces and text from rendered objects under several application scenarios.
Topics & Concepts
Computer scienceRendering (computer graphics)Augmented realityInformation sensitivityPrivacy protectionReflection (computer programming)Computer visionCompromiseVirtual realityComputer graphics (images)Artificial intelligenceHuman–computer interactionComputer securitySociologyProgramming languageSocial scienceFace recognition and analysisAdvanced Steganography and Watermarking TechniquesGenerative Adversarial Networks and Image Synthesis