动态路由自编码器实现视频压缩比特率精准控制
Learned Rate Control for Frame-Level Adaptive Neural Video Compression via Dynamic Neural Network
- 设计可变编码路径的动态路由自编码器，支持不同计算复杂度
- 运行时通过速率控制代理将码率误差保持在1.66%以内
- 适用于多比特率场景，兼顾压缩效率与计算开销
近年来，神经视频压缩（NVC）取得了显著进展，但基于学习的编码器在精确码率控制方面仍面临挑战。为此，我们提出一种面向可变比特率场景的动态视频压缩框架。首先，提出具有可变编码路径的动态路由自编码器（DRA），各路径占用网络部分计算量并对应不同的率失真权衡。其次，引入速率控制代理，在运行时估计各路径码率并动态调整编码路径。为覆盖广泛可变比特率并保持整体率失真性能，采用联合路径优化策略，实现多路径协同训练。在HEVC和UVG数据集上的大量实验表明，该方法相比现有最优方法平均获得14.8%的BD-Rate降低和0.47dB的BD-PSNR提升，同时保持平均码率误差仅为1.66%，实现了各类比特率及比特率受限应用下的率失真复杂度优化（RDCO）。代码已开源。
原文摘要 · Abstract (English)
Neural Video Compression (NVC) has achieved remarkable performance in recent years. However, precise rate control remains a challenge due to the inherent limitations of learning-based codecs. To solve this issue, we propose a dynamic video compression framework designed for variable bitrate scenarios. First, to achieve variable bitrate implementation, we propose the Dynamic-Route Autoencoder with variable coding routes, each occupying partial computational complexity of the whole network and navigating to a distinct RD trade-off. Second, to approach the target bitrate, the Rate Control Agent estimates the bitrate of each route and adjusts the coding route of DRA at run time. To encompass a broad spectrum of variable bitrates while preserving overall RD performance, we employ the Joint-Routes Optimization strategy, achieving collaborative training of various routes. Extensive experiments on the HEVC and UVG datasets show that the proposed method achieves an average BD-Rate reduction of 14.8% and BD-PSNR gain of 0.47dB over state-of-the-art methods while maintaining an average bitrate error of 1.66%, achieving Rate-Distortion-Complexity Optimization (RDCO) for various bitrate and bitrate-constrained applications. Our code is available at https://git.openi.org.cn/OpenAICoding/DynamicDVC.
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。