English

BlenderRAG: High-Fidelity 3D Object Generation via Retrieval-Augmented Code Synthesis

Computer Vision and Pattern Recognition 2026-05-04 v1 Artificial Intelligence Graphics Human-Computer Interaction Machine Learning

Abstract

Automatic generation of executable Blender code from natural language remains challenging, with state-of-the-art LLMs producing frequent syntactic errors and geometrically inconsistent objects. We present BlenderRAG, a retrieval-augmented generation system that operates on a curated multimodal dataset of 500 expert-validated examples (text, code, image) across 50 object categories. By retrieving semantically similar examples during generation, BlenderRAG improves compilation success rates from 40.8% to 70.0% and semantic normalized alignment from 0.41 to 0.77 (CLIP similarity) across four state-of-the-art LLMs, without requiring fine-tuning or specialized hardware, making it immediately accessible for deployment. The dataset and code will be available at https://github.com/MaxRondelli/BlenderRAG.

Keywords

Cite

@article{arxiv.2605.00632,
  title  = {BlenderRAG: High-Fidelity 3D Object Generation via Retrieval-Augmented Code Synthesis},
  author = {Massimo Rondelli and Francesco Pivi and Maurizio Gabbrielli},
  journal= {arXiv preprint arXiv:2605.00632},
  year   = {2026}
}
R2 v1 2026-07-01T12:45:11.413Z