.png){kind=icon}
返回
Depth aware image compression with multi-reference dynamic entropy model
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2026.132971.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
• Investigates the significance of differentiated feature processing according to network depth in the encoder-decoder architecture. • Establishes neighborhood dependencies through adaptive soft thresholding attention and captures complementary features via multi-context integration. • Constructs an entropy model using a depth-aware adaptive framework and multi-reference dynamic entropy modeling to enhance pixel prediction.
Keyword:
Feature processing
Attention mechanism
Entropy modeling
Image compression
Multi-context integration
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
暂无机构信息
引用论文
.png){kind=icon}
GroupedMixer: An Entropy Model With Group-Wise Token-Mixers for Learned Image CompressionGroupedMixer：一种带有组级Token-Mixers的熵模型，用于学习型图像压缩
OAAI
OAAI分享收藏
Intelligent image compression based on neighborhood dynamic perception and multi-parameter optimized entropy model基于邻域动态感知和多参数优化熵模型的智能图像压缩
PREAI
分享收藏Learned image compression via neighborhood-based attention optimization and context modeling with multi-scale guiding基于邻域注意力优化的学习型图像压缩及多尺度引导上下文建模
PREAI
分享收藏
查看更多内容