# Training-Free Adaptive 360-degree Video Streaming via Semantic Potential Fields

arXiv: https://arxiv.org/abs/2603.20999 · HTML: https://mlsanity.com/paper/2603.20999/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 39 references that are in the map.
- First posted on arXiv 22 Mar 2026.

## Builds on (most cited first, 6 of 6)

- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [BOLA: Near-Optimal Bitrate Adaptation for Online Videos](https://mlsanity.com/paper/1601.06748/) (2016)
- [Pano: Optimizing 360deg Video Streaming with a Better Understanding of Quality Perception](https://mlsanity.com/paper/1911.04139/) (2019)
- [Viewport-Adaptive Navigable 360-Degree Video Delivery](https://mlsanity.com/paper/1609.08042/) (2016)
- [Viewport-aware adaptive 360deg video streaming using tiles for virtual reality](https://mlsanity.com/paper/1711.02386/) (2017)
- [VAD360: Viewport Aware Dynamic 360-Degree Video Frame Tiling](https://mlsanity.com/paper/2105.11563/) (2021)

## Abstract (arXiv)

Adaptive 360deg video streaming for teleoperation faces two coupled challenges: viewport prediction under uncertain gaze patterns and bitrate adaptation over fluctuating wireless channels. While Deep Reinforcement Learning (DRL) methods achieve high Quality of Experience (QoE), their lack of interpretability and dependence on offline training limit deployment in safety-critical systems. We propose OrbitStream, a training-free framework that formulates viewport prediction as a Gravitational Viewport Prediction (GVP) problem, where semantic objects generate potential fields that attract operator gaze, and employs a Saturation-Based Proportional-Derivative (PD) Controller for buffer regulation. On object-rich teleoperation traces, OrbitStream achieves 94.7% zero-shot viewport prediction accuracy without user-specific profiling, approaching trajectory-extrapolation baselines (~98.5%). Across 3,600 Monte Carlo simulations, it ranks second among 12 algorithms (QoE 2.71 vs. BOLA-E's 2.80), outperforming FastMPC (1.84), with 1.01 ms decision latency and minimal rebuffering.