提出混合显隐时序缓冲机制，提升视频压缩效率并减少内存占用。
Conditional Residual Coding with Explicit-Implicit Temporal Buffering for Learned Video Compression
- 结合显式已解码帧与少量隐式特征作为时序参考
- 2K视频下仅需两帧等效缓存，性能损失可忽略
- 验证了显隐时序信息对编码效果的协同作用
本文提出一种用于条件残差视频编码的混合显隐时序缓冲方案。近期条件编码方法通过传播隐式时序信息实现帧间编码，性能优于仅依赖已解码帧（即显式时序信息）的方法，但需大量内存存储众多隐式特征。本文提出混合缓冲策略：帧间编码时，保留一个已解码帧作为显式时序参考，并缓存少量学习得到的特征作为隐式时序参考。该混合方案在条件残差编码中表现优于单一使用显式或隐式信息。此外，总缓存大小可降至相当于两帧视频数据量，在2K视频序列上性能下降可忽略。消融实验进一步揭示了两类时序参考对编码性能的影响。
原文摘要 · Abstract (English)
This work proposes a hybrid, explicit-implicit temporal buffering scheme for conditional residual video coding. Recent conditional coding methods propagate implicit temporal information for inter-frame coding, demonstrating superior coding performance to those relying exclusively on previously decoded frames (i.e. the explicit temporal information). However, these methods require substantial memory to store a large number of implicit features. This work presents a hybrid buffering strategy. For inter-frame coding, it buffers one previously decoded frame as the explicit temporal reference and a small number of learned features as implicit temporal reference. Our hybrid buffering scheme for conditional residual coding outperforms the single use of explicit or implicit information. Moreover, it allows the total buffer size to be reduced to the equivalent of two video frames with a negligible performance drop on 2K video sequences. The ablation experiment further sheds light on how these two types of temporal references impact the coding performance.
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。