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.
BlenderRAG: High-Fidelity 3D Object Generation via Retrieval-Augmented Code Synthesis
BlenderRAG enhances natural language to Blender code generation by leveraging a retrieval-augmented approach with a curated multimodal dataset, improving both compilation success and semantic alignment without fine-tuning.
- Year
- 2026
- Venue
- arXiv 2026
- Authors
- 3
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/2605.00632ARXIV-DEFAULT
- TL;DR
- Semantic Scholar