<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>3D高斯溅射 on 知识铺的博客</title>
    <link>https://index.zshipu.com/ai001/tags/3D%E9%AB%98%E6%96%AF%E6%BA%85%E5%B0%84/</link>
    <description>Recent content in 3D高斯溅射 on 知识铺的博客</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>zh-CN</language>
    <lastBuildDate>Wed, 02 Sep 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://index.zshipu.com/ai001/tags/3D%E9%AB%98%E6%96%AF%E6%BA%85%E5%B0%84/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>李飞飞World Labs发布Atlas：几张照片即可重建可导航3D世界</title>
      <link>https://index.zshipu.com/ai001/post/20260902/%E6%9D%8E%E9%A3%9E%E9%A3%9EWorld-Labs%E5%8F%91%E5%B8%83Atlas%E5%87%A0%E5%BC%A0%E7%85%A7%E7%89%87%E5%8D%B3%E5%8F%AF%E9%87%8D%E5%BB%BA%E5%8F%AF%E5%AF%BC%E8%88%AA3D%E4%B8%96%E7%95%8C/</link>
      <pubDate>Wed, 02 Sep 2026 00:00:00 +0000</pubDate>
      <guid>https://index.zshipu.com/ai001/post/20260902/%E6%9D%8E%E9%A3%9E%E9%A3%9EWorld-Labs%E5%8F%91%E5%B8%83Atlas%E5%87%A0%E5%BC%A0%E7%85%A7%E7%89%87%E5%8D%B3%E5%8F%AF%E9%87%8D%E5%BB%BA%E5%8F%AF%E5%AF%BC%E8%88%AA3D%E4%B8%96%E7%95%8C/</guid>
      <description>李飞飞World Labs发布Atlas：几张照片即可重建可导航3D世界 World Labs发布了Atlas模型。它能接收几张普通照片，就输出从任意角度观看的连续视频；输入一段手机视频，则能重建出可供机器人模拟导航的完整3D场景。该模型从零预训练，核心架构采用multimodal autoregressive diffusion tran</description>
    </item>
  </channel>
</rss>
