.png){kind=icon}
返回
Enhanced Context Mining and Filtering for Learned Video Compression
.png){kind=icon}
PRE
AI
DOI：10.1109/TMM.2023.3316429.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The Deep Contextual Video Compression framework (DCVC) utilizes a conditional coding paradigm, where the context is extracted and employed as a condition for the contextual encoder-decoder and entropy model. In this paper, we propose enhanced context mining and filtering to improve the compression efficiency of DCVC. Firstly, considering the context of DCVC is generated without supervision and redundancy may exist among context channels, an enhanced context mining model is proposed to mitigate redundancy across context channels to obtain superior context features. Then, we introduce a transformer-based enhancement network as a filtering module to capture long-distance dependencies and further enhance compression efficiency. The transformer-based enhancement adopts a full-resolution pipeline and calculates self-attention across channel dimensions. By combining the local modeling ability of the enhanced context mining model and the non-local modeling ability of the transformer-based enhancement network, our model outperforms LDP configurations of Versatile Video Coding (VVC), achieving an average bit savings of 6.7% in terms of MS-SSIM.
Keyword:
Video compression
Context modeling
Transformers
Image coding
Entropy
Filtering
Codes
Learned video compression
end-to-end training approach
enhanced context mining
in loop filtering
期刊
IF:
9.7
论文数:
4.6K
被引数:
2.4W
机构
引用论文
Inflexibility of mental planning: A characteristic disorder with prefrontal lobe lesions?心理计划的僵化: 前额叶病变的特征性障碍？
PREAI
分享收藏分享收藏Advances in Video Compression System Using Deep Neural Network: A Review and Case Studies.png)
PROCEEDINGS OF THE IEEE
OAAI
PROCEEDINGS OF THE IEEEIF25.9
OAAI分享收藏分享收藏Phase Diagram for Two-Dimensional Spin Systems with Ladder, Plaquette and Mixed-Spin Structures
PREAI
分享收藏
查看更多内容