用生成模型压缩视频预加载，省带宽又少卡顿
Smaller is Better: Generative Models Can Power Short Video Preloading
- 用生成模型将视频转为小尺寸语义提示，本地解码还原
- 相比传统方法，卡顿和带宽浪费减少超31%
- 适合对流畅性要求高的短视频平台应用
短视频平台广泛采用预加载技术以减少播放卡顿。然而现有策略面临权衡：激进预加载虽降低卡顿但浪费带宽，保守策略节省数据却增加卡顿风险。本文提出PromptPream，一种基于本地计算的预加载范式，通过生成模型显著降低带宽需求。不传输像素级视频块，而是发送紧凑的语义提示，由Stable Diffusion等生成模型本地解码为高质量帧。提出三项核心技术：(1) 基于梯度的提示反演方法，将帧压缩为小型标记嵌入；(2) 考虑计算资源的调度策略，联合优化网络与算力使用；(3) 可扩展的搜索算法，应对调度空间扩大问题。实验表明，PromptPream相比传统策略，卡顿和带宽浪费均减少31%以上，用户体验质量（QoE）提升45%。
原文摘要 · Abstract (English)
Preloading is widely used in short video platforms to minimize playback stalls by downloading future content in advance. However, existing strategies face a tradeoff. Aggressive preloading reduces stalls but wastes bandwidth, while conservative strategies save data but increase the risk of playback stalls. This paper presents PromptPream, a computation powered preloading paradigm that breaks this tradeoff by using local computation to reduce bandwidth demand. Instead of transmitting pixel level video chunks, PromptPream sends compact semantic prompts that are decoded into high quality frames using generative models such as Stable Diffusion. We propose three core techniques to enable this paradigm: (1) a gradient based prompt inversion method that compresses frames into small sets of compact token embeddings; (2) a computation aware scheduling strategy that jointly optimizes network and compute resource usage; and (3) a scalable searching algorithm that addresses the enlarged scheduling space introduced by scheduler. Evaluations show that PromptStream reduces both stalls and bandwidth waste by over 31%, and improves Quality of Experience (QoE) by 45%, compared to traditional strategies.
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。