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

arXiv: https://arxiv.org/abs/2512.15823 · HTML: https://mlsanity.com/paper/2512.15823/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 30 references that are in the map.
- First posted on arXiv 17 Dec 2025.

## Builds on (most cited first, 10 of 10)

- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [PU-Net: Point Cloud Upsampling Network](https://mlsanity.com/paper/1801.06761/) (2018)
- [Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensation](https://mlsanity.com/paper/1611.05250/) (2016)
- [PUGeo-Net: A Geometry-centric Network for 3D Point Cloud Upsampling](https://mlsanity.com/paper/2002.10277/) (2020)
- [LAKe-Net: Topology-Aware Point Cloud Completion by Localizing Aligned Keypoints](https://mlsanity.com/paper/2203.16771/) (2022)
- [3D Point Cloud Super-Resolution via Graph Total Variation on Surface Normals](https://mlsanity.com/paper/1908.06261/) (2019)
- [End-to-End Latency Optimization of Multi-view 3D Reconstruction for Disaster Response](https://mlsanity.com/paper/2304.01488/) (2023)
- [Securing Immersive 360 Video Streams through Attribute-Based Selective Encryption](https://mlsanity.com/paper/2505.04466/) (2025)
- [AABAC -- Automated Attribute Based Access Control for Genomics Data](https://mlsanity.com/paper/2204.04591/) (2022)
- [VoLUT: Efficient Volumetric streaming enhanced by LUT-based super-resolution](https://mlsanity.com/paper/2502.12151/) (2025)

## Built on by (most cited first, 1 of 1)

- [Learning-Based Reconstruction Attacks on Coordinate-Obfuscated Point Clouds](https://mlsanity.com/paper/2609.02568/) (2026)

## Abstract (arXiv)

Immersive formats such as 360deg 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.