logo
科言猫学术研究的AI总结
language
手机端手机端
  • Phone Feature微信小程序
简体中文简体中文
notice消息通知
博客博客
delete
arrow
返回

LGVF: A Low-Bitrate Generative Video Compression Framework With Spatio-Temporal Diffusion Model

delete2026-03-04
delete0
PRE
AI
M
Mengmeng Zhang
Z
Zihao Yu
H
Hongyun Lu
Y
Yuan Li
R
Ran Cheng
H
Huihui Bai
H
Hongyuan Jing
Z
Zhi Liu
DOI：10.1109/LSP.2026.3670748delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
低比特率视频压缩仍然是视频编码中的一个基本挑战。生成技术的最新进展显示出解决该问题的巨大潜力，但现有的生成模型通常因误差累积和不可预测的语义突变而导致控制性差。为解决这些问题，我们提出了一种基于时空扩散模型的新型低比特率生成式视频压缩框架。设计了一个质量比较器来选择生成过程中的最优特征，有效抑制了误差累积。此外，我们设计了语义突变特征提取网络（SMFN）来准确预测帧序列，从而有效处理语义突变特征。大量实验表明，我们的框架在FVD和LPIPS指标上表现优异，在显著降低比特率的同时，保持了视觉保真度和语义一致性。
Keyword:
Video compression
diffusion model
low-bitrate
semantic mutation

期刊

I
IEEE Signal Processing Letters
IF:
3.9
论文数:
833
被引数:
0

机构

B
beijing jiaotong university
学者数:
1.7K
论文数: 689
被引数: 0
N
north china university of technology
学者数:
981
论文数: 415
被引数: 0
B
Beijing Union University
学者数:
1.1K
论文数: 893
被引数: 927
学者 查看更多机构
引用论文

引用论文

Video Probabilistic Diffusion Models in Projected Latent Space
err2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2023-06-01
err0
errOAAI
errSihyun Yu; Kihyuk Sohn; Subin Kim; Jinwoo Shin
err分享
err收藏
The Cityscapes Dataset for Semantic Urban Scene Understanding用于语义城市场景理解的Cityscapes数据集
err2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2016-06-01
err0
errOAAI
errMarius Cordts; Mohamed Omran; Sebastian Ramos; Timo Rehfeld; Markus Enzweiler; Rodrigo Benenson; Uwe Franke; Stefan Roth; Bernt Schiele
err分享
err收藏
Generalized Spatio-Temporal Adaptive Normalization Framework
err2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)
IF0
err2023-02-20
err0
PREAI
errKumar,Neeraj; Narang,Anish
err分享
err收藏
VisualSimBoat: A High-Fidelity Visual Simulator for Autonomous Surface Vehicles
err2025 Brazilian Conference on Robotics (CROS)
IF0
err2025-04-28
err0
PREAI
errSalgado,Alex; Guerra,Raphael; Vasconcellos,Eduardo Charles; Gonçalves,Luiz Marcos Garcia; Clua,Esteban Walter Gonzalez
err分享
err收藏
Rethinking Semantic Change Detection From a Semantic Alignment Perspective从语义对齐角度重新思考语义变化检测
errIEEE Transactions on Geoscience and Remote Sensing
IF8.6
err2025-01-01
err0
PREAI
errSheng Fang; Wen Li; Yue Song; Zhe Li; Jianli Zhao
err分享
err收藏
Decouple Distortion from Perception: Region Adaptive Diffusion for Extreme-low Bitrate Perception Image Compression
err2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2025-06-10
err0
PREAI
errXu,Jinchang; Wang,Shaokang; Chen,Jintao; Li,Zhe; Jia,Peidong; Zhao,Fei; Xiang,Guoqing; Hao,Zhijian; Zhang,Shanghang; Xie,Xiaodong
err分享
err收藏
Hybrid Spatial-Temporal Entropy Modelling for Neural Video Compression
errProceedings of the 30th ACM International Conference on Multimedia
IF0
err2022-10-10
err0
errOAAI
errJiahao Li; Bin Li; Yan Lu
err分享
err收藏
HumanRef-GS: Image-to-3D Human Generation With Reference-Guided Diffusion and 3D Gaussian SplattingHumanRef-GS: 基于参考引导扩散和3D高斯明暗的人像图像到三维生成
errIEEE Transactions on Circuits and Systems for Video Technology
IF11.1
err2025-07-01
err0
PREAI
errJingbo Zhang; Xiaoyu Li; Hongliang Zhong; Qi Zhang; Yanpei Cao; Ying Shan; Jing Liao
err分享
err收藏
Quality assessment of MPEG-4 AVC/H.264 and HEVC compressed video in a telemedicine context
err2017 IEEE International Conference on Image Processing (ICIP)
IF0
err2017-09-01
err0
PREAI
errChaabouni,A.; Lambert,J.; Gaudeau,Y.; Tizon,N.; Nicholson,D.; Moureaux,J.-M.
err分享
err收藏
Semantic Information Collaboration Network for Semantic Change Detection in Remote Sensing Images用于遥感图像语义变化检测的语义信息协作网络
errIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
IF0
err2024-01-01
err0
errOAAI
errXiaogang Ning; You He; Hanchao Zhang; Ruiqian Zhang; Dong Chang; Minghui Hao
err分享
err收藏
学者 查看更多内容