<?xml version="1.0" encoding="utf-8" standalone="yes" ?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>JPEG AI | ViLab</title>
    <link>https://vilab.team/tag/jpeg-ai/</link>
      <atom:link href="https://vilab.team/tag/jpeg-ai/index.xml" rel="self" type="application/rss+xml" />
    <description>JPEG AI</description>
    <generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Sun, 27 Oct 2024 00:00:00 +0000</lastBuildDate>
    <image>
      <url>https://vilab.team/media/icon_hu2896232876136423579.png</url>
      <title>JPEG AI</title>
      <link>https://vilab.team/tag/jpeg-ai/</link>
    </image>
    
    <item>
      <title>Optimized decoupled structure with non-local attention for deep image compression</title>
      <link>https://vilab.team/publication/optimized-decoupled-structure-with-non-local-attention-for-d/</link>
      <pubDate>Sun, 27 Oct 2024 00:00:00 +0000</pubDate>
      <guid>https://vilab.team/publication/optimized-decoupled-structure-with-non-local-attention-for-d/</guid>
      <description>&lt;p&gt;本文针对学习型图像压缩中的解耦框架，该框架将样本重建与熵解码分离，实现极快解码，并成为JPEG AI验证模型的核心。然而其分析/合成变换仅由堆叠卷积构成，缺乏数据相关性建模能力。作者引入非局部注意力机制增强变换网络，使模型兼具解耦架构的快速解码优势与非局部注意力的强变换能力，提升了压缩性能。&lt;/p&gt;
</description>
    </item>
    
  </channel>
</rss>
