<?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>Posts on segonzal</title>
    <link>https://segonzal-ae365.web.app/posts/</link>
    <description>Recent content in Posts on segonzal</description>
    <generator>Hugo</generator>
    <language>en-Us</language>
    <lastBuildDate>Sat, 18 Apr 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://segonzal-ae365.web.app/posts/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Devlog 1: Automating Identity Morph Targets via Neural Depth Mapping</title>
      <link>https://segonzal-ae365.web.app/posts/2026-04-18-devlog-01/</link>
      <pubDate>Sat, 18 Apr 2026 00:00:00 +0000</pubDate>
      <guid>https://segonzal-ae365.web.app/posts/2026-04-18-devlog-01/</guid>
      <description>&lt;p&gt;I’ve recently been working on a utility-focused pipeline to streamline the creation of &lt;strong&gt;3D Morph Targets&lt;/strong&gt; (Blendshapes) for facial models. While traditional manual sculpting is time-consuming, my goal is to leverage deep learning to generate identity-specific shapes based on 2D data.&lt;/p&gt;
&lt;h3 id=&#34;the-foundation-cc0-base-shapes&#34;&gt;The Foundation: CC0 Base Shapes&lt;/h3&gt;
&lt;p&gt;The project starts with the standard &lt;strong&gt;Blender CC0 Base Shapes&lt;/strong&gt; (Male and Female). Using these as a topological anchor ensures that all generated data remains consistent and ready for standard animation pipelines.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
