面向神经视频编码的内容自适应分层超先验
Content-Adaptive Hierarchical Hyperprior for Neural Video Coding
把「分层超先验」当作从当前帧提取的内容自适应信号，用来同时决定质量分配与参考帧选择；做视频压缩、码率控制或任何需要按内容动态分配比特/参考的视觉任务，都可借鉴这种用超先验引导结构决策而非固定 GOP 配置的思路。
原文依据 a hierarchical hyperprior extracted from the original frame to enable content-aware adaptation of the hierarchical structure
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论尽管神经视频编解码器（NVC）近期通过端到端学习展现出优于传统编解码器的性能，但现有方法主要聚焦于架构改进与编码模块设计，对分层结构——即质量与参考配置——的优化探索有限。当前的分层结构优化方法面临两大局限：（1）内容自适应优化不足；（2）质量结构与参考结构被割裂处理。为克服这些挑战，我们提出一种新的 NVC 框架，通过由当前帧导出的分层超先验来引入内容自适应的分层结构优化。我们的 NVC 集成两个关键组件：（1）从原始帧提取的分层超先验，用于实现分层结构的内容感知自适应；（2）分层超先验编解码器内部的适配器，结合由该超先验引导的双参考方案，以联合优化质量结构与参考结构。借助这种内容自适应的分层结构，我们的 NVC 取得了最优的率失真性能，在帧内周期设置为 -1 和 32 时，相对 VTM-23.4 低延迟 B（LDB）配置分别取得 15.51% 和 12.20% 的 BD-rate 降低，优于此前领先的 NVC 方法 DCVC-FM。
英文原文摘要 1399 字符
While neural video codecs (NVCs) have recently demonstrated superior performance over traditional codecs through end-to-end learning, existing approaches primarily focus on architectural enhancements and coding module design, with limited exploration into optimizing hierarchical structures--specifically, quality and reference configurations. Current hierarchical structure optimization methods face two major limitations: (1) insufficient content-adaptive optimization, and (2) disjointed handling of quality and reference structures. To overcome these challenges, we propose a novel NVC framework that introduces content-adaptive hierarchical structure optimization through a hierarchical hyperprior derived from the current frame. Our NVC integrates two key components: (1) a hierarchical hyperprior extracted from the original frame to enable content-aware adaptation of the hierarchical structure; and (2) an adaptor within the hierarchical hyperprior codec combined with a dual-reference scheme, guided by the hyperprior, to jointly optimize quality and reference structures. By leveraging this content-adaptive hierarchical structure, our NVC achieves state-of-the-art rate-distortion performance, outperforming the previous leading NVC method DCVC-FM with BD-rate reductions of 15.51% and 12.20% relative to VTM-23.4 low-delay B (LDB) under intra-period settings of -1 and 32, respectively.