<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Gaussian Splatting | Jinwoo Jeon</title><link>https://zinuok.github.io/tags/gaussian-splatting/</link><atom:link href="https://zinuok.github.io/tags/gaussian-splatting/index.xml" rel="self" type="application/rss+xml"/><description>Gaussian Splatting</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Mon, 20 Apr 2026 00:00:00 +0000</lastBuildDate><image><url>https://zinuok.github.io/media/icon_hu_758a1e91a503d4de.png</url><title>Gaussian Splatting</title><link>https://zinuok.github.io/tags/gaussian-splatting/</link></image><item><title>GaussianFlow SLAM: Monocular Gaussian Splatting SLAM Guided by GaussianFlow</title><link>https://zinuok.github.io/publication/12_gaussianflowslam/</link><pubDate>Mon, 20 Apr 2026 00:00:00 +0000</pubDate><guid>https://zinuok.github.io/publication/12_gaussianflowslam/</guid><description>&lt;p&gt;We propose GaussianFlow SLAM, a monocular 3D Gaussian Splatting SLAM framework that leverages dense optical flow as a geometry-aware cue. By encouraging the projected motion of Gaussians, termed GaussianFlow, to align with optical flow, our method injects consistent structural supervision into both map reconstruction and camera pose estimation, even without depth measurements. We further introduce normalized error-based densification and pruning to refine inactive and unstable Gaussians, achieving superior rendering quality and tracking accuracy over state-of-the-art methods.&lt;/p&gt;</description></item></channel></rss>