<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
    <channel>
        <title>低光增强 - Tag - 花花世界</title>
        <link>https://shuweiyue.com/tags/%E4%BD%8E%E5%85%89%E5%A2%9E%E5%BC%BA/</link>
        <description>低光增强 - Tag - 花花世界</description>
        <generator>Hugo -- gohugo.io</generator><language>zh-cn</language><lastBuildDate>Sat, 25 Apr 2026 00:00:00 &#43;0800</lastBuildDate><atom:link href="https://shuweiyue.com/tags/%E4%BD%8E%E5%85%89%E5%A2%9E%E5%BC%BA/" rel="self" type="application/rss+xml" /><item>
    <title>6th Place Worldwide at the NTIRE 2026 Low-light Enhancement Challenge (CVPR)</title>
    <link>https://shuweiyue.com/news/announcement_12/</link>
    <pubDate>Sat, 25 Apr 2026 00:00:00 &#43;0800</pubDate>
    <author>岳书威</author>
    <guid>https://shuweiyue.com/news/announcement_12/</guid>
    <description><![CDATA[<p>Our ColorWorld team competed in the <em>NTIRE 2026 Low-light Enhancement: Twilight Cowboy Challenge</em> at CVPR 2026. Targeting noise and inter-frame misalignment in low-light multi-frame RAW images, we proposed a lightweight multi-frame enhancement method that emphasizes inference efficiency while preserving restoration quality.</p>
<p>We finished <strong>6th worldwide</strong>, and ranked <strong>1st in inference speed</strong>! 🎉</p>]]></description>
</item>
</channel>
</rss>
