<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Procedural Modelling | Jon Macey's WebPages</title><link>https://nccastaff.bournemouth.ac.uk/jmacey/tag/Procedural-Modelling/</link><atom:link href="https://nccastaff.bournemouth.ac.uk/jmacey/tag/Procedural-Modelling/index.xml" rel="self" type="application/rss+xml"/><description>Procedural Modelling</description><generator>Source Themes Academic (https://sourcethemes.com/academic/)</generator><language>en-us</language><copyright>Jon Macey 2026</copyright><lastBuildDate>Sun, 23 Jun 2024 12:00:00 +0000</lastBuildDate><image><url>https://nccastaff.bournemouth.ac.uk/jmacey/images/icon_hud717fbbd2ac8fad60548edad7ad9704b_11827_512x512_fill_lanczos_center_3.png</url><title>Procedural Modelling</title><link>https://nccastaff.bournemouth.ac.uk/jmacey/tag/Procedural-Modelling/</link></image><item><title>Jessica Dong</title><link>https://nccastaff.bournemouth.ac.uk/jmacey/MastersProject/MSc26/01/</link><pubDate>Sun, 23 Jun 2024 12:00:00 +0000</pubDate><guid>https://nccastaff.bournemouth.ac.uk/jmacey/MastersProject/MSc26/01/</guid><description>&lt;h2 id="summary">Summary&lt;/h2>
&lt;p>This project explores retrieval-augmented code generation for procedural modelling in Houdini. The prototype connects Houdini to an external FastAPI-based RAG service, a manually curated procedural knowledge base, and a locally hosted Qwen2.5-Coder-7B model served through llama.cpp.&lt;/p>
&lt;p>The project investigates how retrieved Houdini-specific knowledge can support generation of executable Python and SOP node networks, particularly when the model lacks specialised API or procedural conventions.The results show that retrieval can support reuse of verified procedural patterns, but that successful generation still depends on the model&amp;rsquo;s ability to interpret and compose the retrieved knowledge. The project also compares selected local and cloud-model runs and examines issues including retrieval quality, chunking, context size, execution correctness, and geometric correctness.&lt;/p>
&lt;p>
&lt;a href="Exploring_Retrieval_Augmented_Code_Generation_Houdini_CAVE_Thesis.pdf">Thesis&lt;/a>&lt;/p>
&lt;p>GitHub:
&lt;a href="https://github.com/adalek/MasterProject" target="_blank" rel="noopener">https://github.com/adalek/MasterProject&lt;/a>&lt;/p>
&lt;div style="position: relative; padding-bottom: 56.25%; height: 0; overflow: hidden;">
&lt;iframe src="https://player.vimeo.com/video/1218752953" style="position: absolute; top: 0; left: 0; width: 100%; height: 100%; border:0;" title="vimeo video" webkitallowfullscreen mozallowfullscreen allowfullscreen>&lt;/iframe>
&lt;/div>
&lt;h2 id="contact">Contact&lt;/h2>
&lt;p>
&lt;a href="https://xuwendong.com" target="_blank" rel="noopener">https://xuwendong.com&lt;/a>&lt;/p></description></item><item><title>Xingyue Jin</title><link>https://nccastaff.bournemouth.ac.uk/jmacey/MastersProject/MSc26/06/</link><pubDate>Sun, 23 Jun 2024 12:00:00 +0000</pubDate><guid>https://nccastaff.bournemouth.ac.uk/jmacey/MastersProject/MSc26/06/</guid><description>&lt;h2 id="summary">Summary&lt;/h2>
&lt;p>
&lt;a href="Master_Project_Report_s5814691.pdf">Thesis&lt;/a>&lt;/p>
&lt;h2 id="contact">Contact&lt;/h2>
&lt;p>github:
&lt;a href="https://github.com/Oncemore-kk" target="_blank" rel="noopener">https://github.com/Oncemore-kk&lt;/a>&lt;/p></description></item></channel></rss>