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

2026-05-01 · Massimo Rondelli, Francesco Pivi, Maurizio Gabbrielli arxiv

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.

📄 PDF Abstract BibTeX arXiv:2605.00632

Code (0)

등록된 구현이 없습니다.

LL3M: Large Language 3D Modelers

2025-08-11 · Sining Lu, Guan Chen, Nam Anh Dinh, Itai Lang 외 arxiv

We present LL3M, a multi-agent system that leverages pretrained large language models (LLMs) to generate 3D assets by writing interpretable Python code in Blender. We break away from the typical generative approach that …

Re-Imagen: Retrieval-Augmented Text-to-Image Generator

2022-09-29 · Wenhu Chen, Hexiang Hu, Chitwan Saharia, William W. Cohen

Research on text-to-image generation has witnessed significant progress in generating diverse and photo-realistic images, driven by diffusion and auto-regressive models trained on large-scale image-text data. Though stat…

Image Generation Image-text Retrieval Retrieval Text Retrieval+2

Code2Worlds: Empowering Coding LLMs for 4D World Generation

2026-02-12 · Yi Zhang, Yunshuang Wang, Zeyu Zhang, Hao Tang arxiv

Achieving spatial intelligence requires moving beyond visual plausibility to build world simulators grounded in physical laws. While coding LLMs have advanced static 3D scene generation, extending this paradigm to 4D dyn…

Scene Generation Code Generation

FlowScene: Style-Consistent Indoor Scene Generation with Multimodal Graph Rectified Flow

2026-03-20 · Zhifei Yang, Guangyao Zhai, Keyang Lu, YuYang Yin 외 arxiv

Scene generation has extensive industrial applications, demanding both high realism and precise control over geometry and appearance. Language-driven retrieval methods compose plausible scenes from a large object databas…

Scene Generation

Can QPP Choose the Right Query Variant? Evaluating Query Variant Selection for RAG Pipelines

2026-04-24 · Negar Arabzadeh, Andrew Drozdov, Michael Bendersky, Matei Zaharia arxiv

Large Language Models (LLMs) have made query reformulation ubiquitous in modern retrieval and Retrieval-Augmented Generation (RAG) pipelines, enabling the generation of multiple semantically equivalent query variants. Ho…