BlenderRAG: High-Fidelity 3D Object Generation via Retrieval-Augmented Code Synthesis
Massimo Rondelli, Francesco Pivi, Maurizio Gabbrielli
TLDR
BlenderRAG uses retrieval-augmented generation to synthesize high-fidelity Blender code from natural language, significantly improving 3D object generation.
Key contributions
- Introduces BlenderRAG, a retrieval-augmented system for generating executable Blender code from text.
- Leverages a curated multimodal dataset of 500 expert-validated examples across 50 categories.
- Increases Blender code compilation success rate from 40.8% to 70.0% across LLMs.
- Boosts semantic alignment (CLIP) from 0.41 to 0.77 without fine-tuning or specialized hardware.
Why it matters
LLMs often produce erroneous Blender code, resulting in inconsistent 3D objects. BlenderRAG tackles this by dramatically enhancing code quality and compilation success. It provides an immediately accessible solution, requiring no fine-tuning or specialized hardware.
Original 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.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.