Skip to content

Official Codebase of 3DCodeVerse

Python

Embed native GitHub video player and simplify introduction

gaoypeng07db07cd3b3a
diff --git a/README.md b/README.md
index 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