Secure AI-Driven Super-Resolution for Real-Time Mixed Reality Applications

2025-12-17

AI Summary

To address the high bandwidth consumption and encryption/decryption latency bottlenecks in real-time mixed-reality streaming of 360° and 6DoF point cloud videos, this paper proposes an end-to-end low-latency transmission framework integrating server-side partial encryption with downsampling and client-side lightweight CNN-based super-resolution reconstruction. It is the first work to jointly employ AES-based partial encryption and AI-driven super-resolution for point cloud video streaming—achieving security guarantees while significantly reducing bandwidth requirements and cryptographic overhead. Experiments demonstrate near-linear reductions in both bandwidth usage and end-to-end latency; encryption/decryption time is substantially decreased; super-resolution reconstruction achieves a PSNR of 38.2 dB with inference latency under 12 ms on an RTX 4090 GPU. The method establishes a novel trade-off among security, bandwidth efficiency, and visual fidelity.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Hardware-aware ML
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Security and Privacy: Applications of cryptography
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Immersive formats such as 360° and 6DoF point cloud videos require high bandwidth and low latency, posing challenges for real-time AR/VR streaming. This work focuses on reducing bandwidth consumption and encryption/decryption delay, two key contributors to overall latency. We design a system that downsamples point cloud content at the origin server and applies partial encryption. At the client, the content is decrypted and upscaled using an ML-based super-resolution model. Our evaluation demonstrates a nearly linear reduction in bandwidth/latency, and encryption/decryption overhead with lower downsampling resolutions, while the super-resolution model effectively reconstructs the original full-resolution point clouds with minimal error and modest inference time.

Problem

• Reduces bandwidth consumption for real-time AR/VR streaming
• Minimizes encryption and decryption delays in mixed reality applications
• Uses AI super-resolution to reconstruct high-quality point clouds efficiently

Innovation

• Downsamples point cloud content at server
• Applies partial encryption to reduce overhead
• Uses ML super-resolution model for reconstruction