<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>AI研究 on AI 早报</title><link>https://ai-news.example.com/categories/ai%E7%A0%94%E7%A9%B6/</link><description>Recent content in AI研究 on AI 早报</description><generator>Hugo</generator><language>zh-CN</language><lastBuildDate>Sat, 31 Oct 2026 01:32:23 +0800</lastBuildDate><atom:link href="https://ai-news.example.com/categories/ai%E7%A0%94%E7%A9%B6/feed.xml" rel="self" type="application/rss+xml"/><item><title>[EN] 谷歌MELON技术：无需相机位姿即可从图像重建3D物体</title><link>https://ai-news.example.com/articles/en-melon3d/</link><pubDate>Sat, 31 Oct 2026 01:32:23 +0800</pubDate><guid>https://ai-news.example.com/articles/en-melon3d/</guid><description>谷歌研究团队提出MELON技术，能够仅从少量未知相机位姿的图像中重建物体的3D模型。该方法通过轻量级CNN动态回归相机位姿，并利用模运算损失处理伪对称性，无需预训练或复杂训练方案，即可实现高精度NeRF重建。</description></item></channel></rss>