| 注册
首页|期刊导航|信号处理|长短程二次运动补偿的视频编码

长短程二次运动补偿的视频编码

夏凡鑫 孙宇霄 张一凡 刘美琴 姚超 赵耀

信号处理2026,Vol.42Issue(3):310-323,14.
信号处理2026,Vol.42Issue(3):310-323,14.DOI:10.12466/xhcl.2026.03.003

长短程二次运动补偿的视频编码

Short-and Long-Term Aware Two-Stage Motion Compensation for Video Compression

夏凡鑫 1孙宇霄 1张一凡 1刘美琴 1姚超 2赵耀1

作者信息

  • 1. 北京交通大学信息科学研究所,北京 100044||北京交通大学视觉智能交叉创新教育部国际合作联合实验室,北京 100044
  • 2. 北京科技大学计算机与通信工程学院,北京 100083
  • 折叠

摘要

Abstract

In hybrid video coding frameworks,inter-frame prediction is a crucial component for eliminating temporal re-dundancy and improving coding efficiency.Most existing methods rely solely on the previous frame as a reference.Spe-cifically,motion information between the reference and target frames is extracted via neural networks,encoded and transmitted,and then applied to the reference frame to produce an aligned frame.However,these methods rely on short-term reference frames and thus have limited effectiveness in handling complex scenes such as occlusion and fail to fully utilize high-quality reference frames over longer temporal ranges.Although certain recent approaches attempted to incor-porate long-term reference information,they often adopted simple stacking strategies or loss-driven implicit fusion mechanisms that lack targeted guidance for reference frame utilization.To address the issues,this study proposed a Short-and Long-Term Aware Two-Stage Motion Compensation method for video compression.Specifically,we first es-timated motion information from short-term reference frames to generate initially aligned features,establishing basic temporal correspondence.Then,we extracted prompt features from long-term reference frames and used the recon-structed reference content to guide detail enhancement of the initially aligned features,thereby effectively alleviating oc-clusions and motion artifacts with low bitrate overhead.Furthermore,we proposed an Explicit-Implicit Temporal Refer-ence Buffer,in which short-term reference frames were explicitly modeled to preserve high-fidelity spatial details,and long-term reference frames were implicitly modeled to form a compact temporal representation.This mechanism pro-vided stable contextual support for the secondary motion compensation.Experimental results showed that the proposed method achieved superior rate-distortion performance in terms of peak signal-to-noise ratio and multi-scale structural similarity index measure compared with hybrid coding framework VTM-19.0,latest end-to-end video coding method DCVC-RT,and recent representative multi-reference frame video coding method DCVC-SDD.Ablation studies further verified the effectiveness of the proposed Short-and Long-Term Aware Two-Stage Motion Compensation module and the Explicit-Implicit Temporal Reference Buffer module.

关键词

视频编码/运动补偿/参考帧管理

Key words

video compression/motion compensation/reference frame management

分类

信息技术与安全科学

引用本文复制引用

夏凡鑫,孙宇霄,张一凡,刘美琴,姚超,赵耀..长短程二次运动补偿的视频编码[J].信号处理,2026,42(3):310-323,14.

基金项目

国家自然科学基金(62372036,62120106009,62332017,U24B20179) The National Natural Science Foundation of China(62372036,62120106009,62332017,U24B20179) (62372036,62120106009,62332017,U24B20179)

信号处理

1003-0530

访问量0
|
下载量0
段落导航相关论文