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

TL;DR

OrbitStream is a training-free adaptive 360-degree video streaming framework that predicts viewports using semantic potential fields and employs a PD controller for bitrate adaptation, achieving high accuracy and low latency.

Contribution

It introduces a novel training-free approach combining semantic potential fields and a PD controller for viewport prediction and bitrate adaptation in 360-degree video streaming.

Findings

Achieves 94.7% zero-shot viewport prediction accuracy without user-specific data.

Ranks second among 12 algorithms in Monte Carlo simulations with a QoE of 2.71.

Decision latency is only 1.01 ms with minimal rebuffering.

Abstract

Adaptive 360{\deg} 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.