<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title>哥白尼计划 - Tag - 堂堂一跑堂</title><link>https://spacetop.win/tags/%E5%93%A5%E7%99%BD%E5%B0%BC%E8%AE%A1%E5%88%92/</link><description>哥白尼计划 - Tag - 堂堂一跑堂</description><generator>Hugo -- gohugo.io</generator><language>zh-CN</language><managingEditor>kingcopper@whu.edu.cn (WangTong)</managingEditor><webMaster>kingcopper@whu.edu.cn (WangTong)</webMaster><lastBuildDate>Sun, 31 May 2026 12:00:00 +0800</lastBuildDate><atom:link href="https://spacetop.win/tags/%E5%93%A5%E7%99%BD%E5%B0%BC%E8%AE%A1%E5%88%92/" rel="self" type="application/rss+xml"/><item><title>一个模型吃透所有卫星传感器：Copernicus-FM如何统一地球观测基础模型</title><link>https://spacetop.win/2026/05/20260531_210000_copernicus_fm_unified/</link><pubDate>Sun, 31 May 2026 12:00:00 +0800</pubDate><author><name>WangTong</name></author><guid>https://spacetop.win/2026/05/20260531_210000_copernicus_fm_unified/</guid><description><![CDATA[<h1 id="一个模型吃透所有卫星传感器copernicus-fm如何统一地球观测基础模型" class="headerLink">
    <a href="#%e4%b8%80%e4%b8%aa%e6%a8%a1%e5%9e%8b%e5%90%83%e9%80%8f%e6%89%80%e6%9c%89%e5%8d%ab%e6%98%9f%e4%bc%a0%e6%84%9f%e5%99%a8copernicus-fm%e5%a6%82%e4%bd%95%e7%bb%9f%e4%b8%80%e5%9c%b0%e7%90%83%e8%a7%82%e6%b5%8b%e5%9f%ba%e7%a1%80%e6%a8%a1%e5%9e%8b" class="header-mark"></a>一个模型吃透所有卫星传感器：Copernicus-FM如何统一地球观测基础模型</h1><blockquote>
  <p><strong>论文解读</strong> | ICCV 2025 Oral | 2026-05-31</p>
</blockquote><h2 id="-论文信息" class="headerLink">
    <a href="#-%e8%ae%ba%e6%96%87%e4%bf%a1%e6%81%af" class="header-mark"></a>📄 论文信息</h2><table>
  <thead>
      <tr>
          <th>项目</th>
          <th>内容</th>
      </tr>
  </thead>
  <tbody>
      <tr>
          <td><strong>标题</strong></td>
          <td>Towards a Unified Copernicus Foundation Model for Earth Vision</td>
      </tr>
      <tr>
          <td><strong>作者</strong></td>
          <td>Yi Wang, Zhitong Xiong, Chenying Liu, Adam J. Stewart, Thomas Dujardin, Nikolaos Ioannis Bountos, Angelos Zavras, Franziska Gerken, Ioannis Papoutsis, Laura Leal-Taixé, Xiao Xiang Zhu</td>
      </tr>
      <tr>
          <td><strong>机构</strong></td>
          <td>慕尼黑工业大学(TUM)、慕尼黑机器学习中心(MCML)、雅典国立技术大学(NTUA)、NVIDIA</td>
      </tr>
      <tr>
          <td><strong>会议</strong></td>
          <td><strong>ICCV 2025 Oral</strong></td>
      </tr>
      <tr>
          <td><strong>arXiv</strong></td>
          <td><a href="https://arxiv.org/abs/2503.11849" target="_blank" rel="noopener noreferrer">https://arxiv.org/abs/2503.11849</a></td>
      </tr>
      <tr>
          <td><strong>GitHub</strong></td>
          <td><a href="https://github.com/zhu-xlab/Copernicus-FM" target="_blank" rel="noopener noreferrer">https://github.com/zhu-xlab/Copernicus-FM</a> (141 ⭐)</td>
      </tr>
      <tr>
          <td><strong>HuggingFace</strong></td>
          <td>模型/数据集/基准测试均已开源</td>
      </tr>
      <tr>
          <td><strong>关键词</strong></td>
          <td>地球观测基础模型、多传感器统一、动态超网络、元数据编码、哥白尼计划</td>
      </tr>
  </tbody>
</table>
<h2 id="-解决的核心问题" class="headerLink">
    <a href="#-%e8%a7%a3%e5%86%b3%e7%9a%84%e6%a0%b8%e5%bf%83%e9%97%ae%e9%a2%98" class="header-mark"></a>🎯 解决的核心问题</h2><h3 id="问题背景" class="headerLink">
    <a href="#%e9%97%ae%e9%a2%98%e8%83%8c%e6%99%af" class="header-mark"></a>问题背景</h3><p>遥感卫星是人类观测地球的&quot;天眼&quot;。欧盟哥白尼计划（Copernicus Programme）运营着一组庞大的卫星群——从SAR雷达卫星（Sentinel-1）、光学多光谱卫星（Sentinel-2）、海洋陆地监测卫星（Sentinel-3）到大气成分监测卫星（Sentinel-5P）。这些传感器各有&quot;方言&quot;：波段不同、分辨率不同、甚至数据类型完全不同（光谱 vs 非光谱）。</p>]]></description></item></channel></rss>