<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Opengl on Benjamin Feldman</title>
    <link>https://bfeldman.me/tags/opengl/</link>
    <description>Recent content in Opengl on Benjamin Feldman</description>
    <generator>Hugo -- 0.147.7</generator>
    <language>en-us</language>
    <lastBuildDate>Wed, 13 May 2026 15:30:00 +0200</lastBuildDate>
    <atom:link href="https://bfeldman.me/tags/opengl/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>3D Gaussian Splatting in a Weekend</title>
      <link>https://bfeldman.me/3dgs-weekend/</link>
      <pubDate>Wed, 13 May 2026 15:30:00 +0200</pubDate>
      <guid>https://bfeldman.me/3dgs-weekend/</guid>
      <description>&lt;h2 id=&#34;introduction&#34;&gt;Introduction&lt;/h2&gt;
&lt;p&gt;3D Gaussian splatting is a technique that answers this question: given a dataset of pictures of a scene, how can I reconstruct it in 3D? This is achieved using a machine learning algorithm that, for many different camera angles, does the following: render the scene, compare it to the picture taken at the same camera angle, and update the scene to reduce the difference between the rendered image and the ground truth. However, unlike traditional 3D renderers, 3DGS does not use triangles as primitives, but objects called &lt;em&gt;Gaussian splats&lt;/em&gt;, making the rendering algorithm unique to 3DGS.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
