Free-view video (FVV) allows users to explore immersive video content from multiple views. However, delivering FVV poses significant challenges due to the uncertainty in view switching, combined with the substantial bandwidth and computational resources required to transmit and decode multiple video streams, which may result in frequent playback interruptions. Existing approaches, either client-based or cloud-based, struggle to meet high Quality of Experience (QoE) requirements under limited bandwidth and computational resources. To address these issues, we propose VARFVV, a bandwidth- and computationally-efficient system that enables real-time interactive FVV streaming with high QoE and low switching delay. Specifically, VARFVV introduces a low-complexity FVV generation scheme that reassembles multiview video frames at the edge server based on user-selected view tracks, eliminating the need for transcoding and significantly reducing computational overhead. This design makes it well-suited for large-scale, mobile-based UHD FVV experiences. Furthermore, we present a popularity-adaptive bit allocation method, leveraging a graph neural network, that predicts view popularity and dynamically adjusts bit allocation to maximize QoE within bandwidth constraints. We also construct an FVV dataset comprising 330 videos from 10 scenes, including basketball, opera, etc. Extensive experiments show that VARFVV surpasses existing methods in video quality, switching latency, computational efficiency, and bandwidth usage, supporting over 500 users on a single edge server with a switching delay of 71.5ms. Our code and dataset are available at https://github.com/qianghu-huber/VARFVV.
From Ember to Blaze: Swift Interactive Video Adaptation via Meta-Reinforcement Learning
最大化交互式视频流的体验质量（QoE）一直是一个长期存在的挑战，因为其延迟敏感的性质使其更容易受到带宽波动的影响。虽然强化学习（RL）已经展示了巨大的潜力，但现有的工作要么受到固定模型的限制，要么需要大量的数据/时间进行在线适应，难以适应时变和多样化的网络状态。基于这些实际问题，我们对微信商务版的互动视频服务进行了大规模测量，以研究真实世界的网络波动。令人惊讶的是，我们的分析表明，与时变网络指标相比，网络序列表现出明显的短期连续性，足以满足少样本学习的要求。因此，我们提出了Fiammetta，第一个基于元RL的交互式视频流的比特率自适应算法。在短期连续性的基础上，Fiammetta通过离线元训练积累学习经验，并通过一些梯度更新快速在线适应不断变化的网络状态。此外，Fiammetta创新性地引入了一种探测机制来实时监测网络状态，并提出了一种自适应的元测试机制来实现无缝适配。我们在一个测试平台上实现了Fiammetta，其端到端网络遵循真实世界的WeChat for Business跟踪。实验结果表明，Fiammetta算法在不增加停顿率的情况下，视频码率提高了3.6%~ 16.2%，明显优于现有算法。
Statistical Information of the Increased Demand for Watch the VOD with the Increased Sophistication in the Mobile Devices,Communications and Internet Penetration in Asia
Hallo-Live: Real-Time Streaming Joint Audio-Video Avatar Generation with Asynchronous Dual-Stream and Human-Centric Preference Distillation
Shanghai Innovation Institute（上海创新研究院）；Fudan University（复旦大学）；University of Science and Technology of China（中国科学技术大学）；Nanjing University（南京大学）；Baidu（百度）
