提出联合码率-解码时间-画质的帕累托优化框架,提升自适应VVC流媒体体验。
Decoding Complexity-Rate-Quality Pareto-Front for Adaptive VVC Streaming
- 基于帕累托前沿构建动态码率阶梯,平衡码率、解码时延与画质
- 在低延迟场景下降低14.86%解码时间,同时节省4.65%码率
- 适合对延迟敏感或带宽受限的视频流应用,如直播与移动端
帕累托前沿优化对于解决视频流媒体中的多目标挑战至关重要,可识别码率、视频质量与解码复杂度之间的最优权衡。本文研究了自适应灵活视频编码(VVC)流媒体中高效码率阶梯的构建,重点优化这些目标间的权衡。我们探讨了基于帕累托前沿的多种阶梯构造方法,包括全枚举速率-画质和固定阶梯方案。提出一种联合解码时间-码率-画质的帕累托前沿,提供全面框架以平衡码率、解码时间和视频质量。该框架使流媒体服务可根据具体需求定制编码策略,优先考虑低解码延迟、带宽效率或均衡方案,从而提升整体用户体验。实验结果验证了该方法在解码时间-码率-画质空间中的有效性。例如,在优先降低解码延迟时,相比传统固定阶梯方案,本方法实现14.86%的解码时间减少,同时在Bjontegaard delta rate上节省4.65%,并提升XPSNR-Rate域0.32dB。
原文摘要 · Abstract (English)
Pareto-front optimization is crucial for addressing the multi-objective challenges in video streaming, enabling the identification of optimal trade-offs between conflicting goals such as bitrate, video quality, and decoding complexity. This paper explores the construction of efficient bitrate ladders for adaptive Versatile Video Coding (VVC) streaming, focusing on optimizing these trade-offs. We investigate various ladder construction methods based on Pareto-front optimization, including exhaustive Rate-Quality and fixed ladder approaches. We propose a joint decoding time-rate-quality Pareto-front, providing a comprehensive framework to balance bitrate, decoding time, and video quality in video streaming. This allows streaming services to tailor their encoding strategies to meet specific requirements, prioritizing low decoding latency, bandwidth efficiency, or a balanced approach, thus enhancing the overall user experience. The experimental results confirm and demonstrate these opportunities for navigating the decoding time-rate-quality space to support various use cases. For example, when prioritizing low decoding latency, the proposed method achieves decoding time reduction of 14.86% while providing Bjontegaard delta rate savings of 4.65% and 0.32dB improvement in the eXtended Peak Signal-to-Noise Ratio (XPSNR)-Rate domain over the traditional fixed ladder solution.
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。