BlenderRAG: High-Fidelity 3D Object Generation via Retrieval-Augmented Code Synthesis
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910183687454720 |
|---|---|
| author | Rondelli, Massimo Pivi, Francesco Gabbrielli, Maurizio |
| author_facet | Rondelli, Massimo Pivi, Francesco Gabbrielli, Maurizio |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_00632 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | BlenderRAG: High-Fidelity 3D Object Generation via Retrieval-Augmented Code Synthesis Rondelli, Massimo Pivi, Francesco Gabbrielli, Maurizio Computer Vision and Pattern Recognition Artificial Intelligence Graphics Human-Computer Interaction Machine Learning 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. |
| title | BlenderRAG: High-Fidelity 3D Object Generation via Retrieval-Augmented Code Synthesis |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Graphics Human-Computer Interaction Machine Learning |
| url | https://arxiv.org/abs/2605.00632 |