提出可变码率的时域分层自适应视频编码，提升压缩效率。
Variable Rate Learned Wavelet Video Coding using Temporal Layer Adaptivity
- 基于运动补偿的时域滤波，实现时空可扩展性。
- 相比基线模型，码率降低至少32%（BD-rate）。
- 支持多阶段训练，适合需要灵活质量调控的应用。
学习型小波视频编码器通过在时域、水平和垂直维度执行离散小波变换，提供可解释的框架。基于运动补偿时域滤波（MCTF）的时域变换实现了空间与时域可扩展性。本文引入可变码率支持及针对不同时间层的质量自适应机制，以提升编码效率。此外，提出一种多阶段训练策略，支持多时域层训练。实验表明，相较于无这些扩展的学习型MCTF模型，本方法在Bjøntegaard Delta指标上实现至少-32%的码率节省。训练与推理代码已公开于：https://github.com/FAU-LMS/Learned-pMCTF。
原文摘要 · Abstract (English)
Learned wavelet video coders provide an explainable framework by performing discrete wavelet transforms in temporal, horizontal, and vertical dimensions. With a temporal transform based on motion-compensated temporal filtering (MCTF), spatial and temporal scalability is obtained. In this paper, we introduce variable rate support and a mechanism for quality adaption to different temporal layers for a higher coding efficiency. Moreover, we propose a multi-stage training strategy that allows training with multiple temporal layers. Our experiments demonstrate Bjøntegaard Delta bitrate savings of at least -32% compared to a learned MCTF model without these extensions. Training and inference code is available at: https://github.com/FAU-LMS/Learned-pMCTF.
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。