通过帧间速率-失真意识的强化率控实现神经视频压缩
Reinforced Rate Control for Neural Video Compression via Inter-Frame Rate-Distortion Awareness
AI总结：
本文提出基于强化学习的神经视频压缩率控方法，通过联合优化比特率分配和编码参数，实现更高效的压缩性能和更低的开销。
摘要：
神经视频压缩（NVC）已展示了卓越的压缩效率，但有效的率控仍是一个重大挑战，因为存在复杂的时序依赖性。现有率控方案通常利用帧内容来捕捉失真交互，忽略了由于每帧编码参数变化而产生的帧间速率依赖性。这往往导致次优的比特率分配和级联参数决策。为了解决这个问题，我们提出了一种基于强化学习（RL）的率控框架，将任务视为逐帧的顺序决策过程。在每帧中，RL代理观察到时空状态，并选择编码参数以优化长期奖励，该奖励反映了速率-失真（R-D）性能和比特率的遵守情况。与先前方法不同，我们的方法在单一步骤中联合确定比特率分配和编码参数，而不依赖于图片组（GOP）结构。在多样化的NVC架构上进行的广泛实验表明，我们的方法将平均相对比特率误差降低到1.20%，并在典型GOP大小下实现高达13.45%的比特率节省，优于现有方法。此外，我们的框架在内容变化和带宽波动方面表现出改进的鲁棒性，同时具有较低的编码开销，使其非常适合实际部署。
英文摘要：
Neural video compression (NVC) has demonstrated superior compression efficiency, yet effective rate control remains a significant challenge due to complex temporal dependencies. Existing rate control schemes typically leverage frame content to capture distortion interactions, overlooking inter-frame rate dependencies arising from shifts in per-frame coding parameters. This often leads to suboptimal bitrate allocation and cascading parameter decisions. To address this, we propose a reinforcement-learning (RL)-based rate control framework that formulates the task as a frame-by-frame sequential decision process. At each frame, an RL agent observes a spatiotemporal state and selects coding parameters to optimize a long-term reward that reflects rate-distortion (R-D) performance and bitrate adherence. Unlike prior methods, our approach jointly determines bitrate allocation and coding parameters in a single step, independent of group of pictures (GOP) structure. Extensive experiments across diverse NVC architectures show that our method reduces the average relative bitrate error to 1.20% and achieves up to 13.45% bitrate savings at typical GOP sizes, outperforming existing approaches. In addition, our framework demonstrates improved robustness to content variation and bandwidth fluctuations with lower coding overhead, making it highly suitable for practical deployment.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
