生物启发123D:用于生物启发结构的生成3D建模系统
Bioinspired123D: Generative 3D Modeling System for Bioinspired Structures
AI总结:
本文提出Bioinspired123D,一种轻量级模块化代码-几何管道,通过参数化程序直接生成可制造的3D结构,而非密集视觉表示。系统基于生物启发3D模型,结合多模态检索增强生成和视觉-语言模型批评者,实现了高效的文本到3D生成。
摘要:
生成式AI在文本、图像和视频合成方面取得了快速进展,但文本到3D建模在科学设计中仍极具挑战性,由于可控性差和计算成本高。现有3D生成方法多依赖网格、体素或点云,训练成本高且难以控制。我们引入Bioinspired123D,一种轻量级且模块化的代码-几何管道,通过参数化程序直接生成可制造的3D结构。Bioinspired123D的核心是Bioinspired3D,一个微调的紧凑语言模型,可将自然语言设计提示转化为Blender Python脚本,编码平滑的生物启发几何。我们整理了一个包含超过4000个生物启发和几何设计脚本的领域特定数据集,涵盖螺旋、细胞和管状图案,并具有参数化变化性。该数据集通过自动LLM驱动的Blender质量控制管道扩展和验证。Bioinspired3D随后嵌入到基于图的代理框架中,整合多模态检索增强生成和视觉-语言模型批评者,以迭代评估、批评和修复生成的脚本。我们评估了新的3D几何脚本生成基准,显示Bioinspired123D在非微调基础模型上实现了近四倍的改进,同时在参数和计算上远少于现有最先进的语言模型。通过优先考虑代码-几何表示,Bioinspired123D实现了计算高效、可控和可解释的文本到3D生成,降低了AI驱动材料和结构设计的科学发现门槛。
英文摘要:
Generative AI has made rapid progress in text, image, and video synthesis, yet text-to-3D modeling for scientific design remains particularly challenging due to limited controllability and high computational cost. Most existing 3D generative methods rely on meshes, voxels, or point clouds which can be costly to train and difficult to control. We introduce Bioinspired123D, a lightweight and modular code-as-geometry pipeline that generates fabricable 3D structures directly through parametric programs rather than dense visual representations. At the core of Bioinspired123D is Bioinspired3D, a compact language model finetuned to translate natural language design cues into Blender Python scripts encoding smooth, biologically inspired geometries. We curate a domain-specific dataset of over 4,000 bioinspired and geometric design scripts spanning helical, cellular, and tubular motifs with parametric variability. The dataset is expanded and validated through an automated LLM-driven, Blender-based quality control pipeline. Bioinspired3D is then embedded in a graph-based agentic framework that integrates multimodal retrieval-augmented generation and a vision-language model critic to iteratively evaluate, critique, and repair generated scripts. We evaluate performance on a new benchmark for 3D geometry script generation and show that Bioinspired123D demonstrates a near fourfold improvement over its non-finetuned base model, while also outperforming substantially larger state-of-the-art language models despite using far fewer parameters and compute. By prioritizing code-as-geometry representations, Bioinspired123D enables compute-efficient, controllable, and interpretable text-to-3D generation, lowering barriers to AI driven scientific discovery in materials and structural design.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。