Cloak of Invisibility: Real-Time Privacy-Preserving Volumetric Video Streaming

2026-08-12

AI Summary

This work addresses the privacy leakage inherent in 3D reconstruction from multi-view RGB-D volumetric video streams by proposing InViStream, a system that enforces privacy protection at the camera source. InViStream integrates object detection with depth-aware masking to consistently identify and remove private objects across calibrated views, uploading only sanitized point clouds for cloud-side fusion. It is the first system to achieve real-time, source-end privacy preservation for multi-view RGB-D volumetric video, effectively tackling three key challenges: cross-view appearance discrepancies, depth-based geometric leakage, and distinguishing between public and private instances of the same object category. Experiments demonstrate strong performance, achieving Dice/Recall scores of 0.799/0.891 on synthetic scenes and 0.792/0.908 on real-world data, with SSIM exceeding 0.98 and support for real-time streaming at over 30 FPS.

Abstract

Volumetric video streaming turns privacy into a 3D, multi-view problem. Unlike ordinary video, where sensitive content can often be redacted frame by frame, RGB-D volumetric pipelines capture people, rooms, and personal objects from multiple cameras and fuse them into a shared 3D representation. A private object missed in one view, or only partially removed before fusion, can therefore reappear in the reconstructed scene. This creates a privacy challenge for 3D telepresence, education, entertainment, and immersive applications: private content should be removed before raw visual and geometric data leave the camera side, while the public part of the scene should remain useful for real-time reconstruction. Existing volumetric streaming systems mainly optimize reconstruction, data movement, and latency, while privacy-preserving vision methods are designed for single-camera, single-frame images and do not directly address calibrated multi-view RGB-D fusion. We present InViStream, a real-time "privacy-from-source" system designed for this setting. InViStream addresses three challenges in volumetric capture: private objects may appear differently across views, RGB masking alone can leave geometric privacy leakage in depth, and public/private instances of the same class must be separated consistently before cloud-side fusion. To address these challenges, InViStream combines object detection with depth-aware masking, propagates public/private decisions across calibrated views, and fuses only sanitized point clouds. We evaluate InViStream on synthetic and real RGB-D scenes, including offices, conference rooms, living rooms, and settings with multiple public and private people and objects. InViStream achieves synthetic Dice/Recall of 0.799/0.891 and real Dice/Recall of 0.792/0.908, with synthetic SSIM above 0.98 and real-time streaming above 30 FPS.

Problem

• volumetric video streaming
• privacy preservation
• multi-view RGB-D fusion
• 3D reconstruction
• depth-aware masking

Innovation

• privacy-preserving volumetric streaming
• depth-aware masking
• multi-view RGB-D fusion
• real-time 3D reconstruction
• privacy-from-source