User-Gaze Aware Tile-Based Encoding for 360° VR Museums in 5G&B Softwarized Networks

Virtual Reality (VR) and Augmented Reality (AR) are revolutionizing immersive 360° video experiences across education, entertainment, and cultural exploration. This paper introduces a Smart Video Encoder (SVE) system, comprising server- and user-side Virtual Network Functions (VNFs), for adaptive compression and transmission of 360° video streams over 5G/6G networks. Leveraging a Supervised Machine Learning (SML) Video Analyzer, the system enhances user-perceived quality by prioritizing key regions, such as artistic content. Using hierarchical tile-based compression, the SVE adjusts compression dynamically based on real-time user behavior and video content. Results show its effectiveness in maintaining high-quality experiences under bandwidth constraints, particularly for applications like virtual museum tours.