<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Dense Reconstruction | Jinwoo Jeon</title><link>https://zinuok.github.io/tags/dense-reconstruction/</link><atom:link href="https://zinuok.github.io/tags/dense-reconstruction/index.xml" rel="self" type="application/rss+xml"/><description>Dense Reconstruction</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Thu, 05 Mar 2026 00:00:00 +0000</lastBuildDate><image><url>https://zinuok.github.io/media/icon_hu_758a1e91a503d4de.png</url><title>Dense Reconstruction</title><link>https://zinuok.github.io/tags/dense-reconstruction/</link></image><item><title>AIM-SLAM: Dense Monocular SLAM via Adaptive and Informative Multi-View Keyframe Prioritization with Foundation Model</title><link>https://zinuok.github.io/publication/11_aimslam/</link><pubDate>Thu, 05 Mar 2026 00:00:00 +0000</pubDate><guid>https://zinuok.github.io/publication/11_aimslam/</guid><description>&lt;p&gt;We propose AIM-SLAM, a dense monocular SLAM framework that leverages dense pointmap predictions from a geometric foundation model (VGGT) and adaptively prioritizes informative multi-view keyframes. Our SIGMA module retrieves a candidate keyframe set via voxel overlap and information gain and adaptively determines its size, while a joint multi-view Sim(3) optimization enforces consistent alignment across the selected views, achieving state-of-the-art pose estimation and accurate dense reconstruction with ROS integration.&lt;/p&gt;</description></item></channel></rss>