BlenderRAG：基于检索增强代码合成的高保真三维物体生成

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

May 1, 2026

作者: Massimo Rondelli, Francesco Pivi, Maurizio Gabbrielli

cs.AI

摘要

从自然语言自动生成可执行的Blender代码仍具挑战性，当前最先进的大语言模型常出现语法错误和几何结构不一致的问题。我们提出BlenderRAG，这是一个基于检索增强生成技术的系统，其运作依托于包含50个物体类别、500个经专家验证的多模态样本（文本、代码、图像）的精选数据集。通过在生成过程中检索语义相似的样本，BlenderRAG在四种前沿大语言模型上实现了编译成功率从40.8%提升至70.0%，语义标准化对齐度（CLIP相似度）从0.41提高至0.77。该系统无需微调或专用硬件即可部署，具有即插即用的优势。数据集与代码将在https://github.com/MaxRondelli/BlenderRAG 开源。

English

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.