arXiv:2602.07273cs.LGcs.MM2026-02

通过融合预测与传输反馈,提升全景内容传输效率。

Hybrid Feedback-Guided Optimal Learning for Wireless Interactive Panoramic Scene Delivery

  • 结合全信息与弱反馈,构建双层混合反馈模型。
  • 算法在真实数据下显著降低延迟,提升传输成功率。
  • 适合虚拟现实、实时交互等低延迟场景使用。

沉浸式应用如虚拟现实和增强现实对帧率、延迟及物理与虚拟环境同步提出严苛要求。为满足这些需求,边缘服务器需渲染全景内容、预测用户头部运动,并在无线带宽限制下传输覆盖用户视口的场景片段。每个片段产生两类反馈信号:预测反馈(判断所选片段是否覆盖实际视口)和传输反馈(判断对应数据包是否成功送达)。以往工作将此问题建模为两级多臂赌博机,但未利用用户头部姿态观测后可回溯计算所有候选片段的预测反馈这一事实,导致预测反馈实为全信息反馈而非赌博机反馈。基于此观察,本文提出一种融合全信息与赌博机反馈的双层混合反馈模型,并将片段选择问题形式化为该设定下的在线学习任务。推导出该混合反馈模型的实例相关后悔下界,提出自适应算法AdaPort,充分利用两类反馈以提升学习效率。进一步建立渐近匹配下界的实例相关后悔上界,并通过真实轨迹驱动的仿真验证,显示AdaPort持续优于现有最优基线方法。

原文摘要 · Abstract (English)

Immersive applications such as virtual and augmented reality impose stringent requirements on frame rate, latency, and synchronization between physical and virtual environments. To meet these requirements, an edge server must render panoramic content, predict user head motion, and transmit a portion of the scene that is large enough to cover the user viewport while remaining within wireless bandwidth constraints. Each portion produces two feedback signals: prediction feedback, indicating whether the selected portion covers the actual viewport, and transmission feedback, indicating whether the corresponding packets are successfully delivered. Prior work models this problem as a multi-armed bandit with two-level bandit feedback, but fails to exploit the fact that prediction feedback can be retrospectively computed for all candidate portions once the user head pose is observed. As a result, prediction feedback constitutes full-information feedback rather than bandit feedback. Motivated by this observation, we introduce a two-level hybrid feedback model that combines full-information and bandit feedback, and formulate the portion selection problem as an online learning task under this setting. We derive an instance-dependent regret lower bound for the hybrid feedback model and propose AdaPort, a hybrid learning algorithm that leverages both feedback types to improve learning efficiency. We further establish an instance-dependent regret upper bound that matches the lower bound asymptotically, and demonstrate through real-world trace driven simulations that AdaPort consistently outperforms state-of-the-art baseline methods.

边缘计算虚拟现实在线学习反馈机制

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。