Official Codebase of 3DCodeVerse
Python
Embed native GitHub video player and simplify introduction
gaoypeng07db07cd3b3a
diff --git a/README.md b/README.mdindex dfef32f5..cbcda906 100644--- a/README.md+++ b/README.md@@ -26,27 +26,7 @@</div>-<p align="center">- <a href="assets/3dcodeverse_illustration_video.mp4">- <img src="assets/teaser.gif" alt="3DCodeVerse animated showcases: scenes, graphics, articulated objects and 3D objects, all built only by code. Click to watch the full video." width="100%">- </a>-</p>-<p align="center"><a href="assets/3dcodeverse_illustration_video.mp4">Watch the full video with audio</a></p>-<p align="center"><em>Every asset above is built <b>only by code</b> (Blender Python, Three.js, OpenGL, …),-from 3D objects to articulated objects, scenes and graphics renderings.</em></p>--**3DCodeVerse** is a research ecosystem that lets coding agents create **editable, verifiable 3D-content at scale**. It is the official code release of the paper and contains:--- **3DCodeVerse-2M** — a curated corpus of about 2M standalone, executable 3D programs across static- objects, articulated assets, scenes and graphics. Each program comes with its source files and- assets, descriptions and verification records.-- **The 3DCodeVerse Harness** — a multi-agent, DAG-structured coding harness. It plans a 3D project,- has vendor coding agents write it as raw code, then executes, measures, renders and judges the- result. It refines the program from that feedback with no human in the loop, and records every- run as training data.-- **Open-model baselines and recipes** — LoRA/DPO fine-tuning of Qwen models on the corpus, and- the execution-based evaluation stack used to score them.+https://github.com/user-attachments/assets/71374368-ccf0-410b-b2ee-fac7f7405fbc## Highlights