CADFather：通过协调工具使用实现自主CAD重建
CADFather: Autonomous CAD Reconstruction through Coordinated Tool Use
浏览论文内容
中文总结 AI 辅助
CADFather是一个无需额外训练的自主智能体系统，通过协调视觉-语言助手、学习和算法工具及数值优化，从3D网格恢复参数化CAD程序，在多个基准上验证了重建质量与执行有效性。
中文摘要 AI 辅助
从3D形状重建可编辑的CAD模型仍然是一项具有挑战性的工程任务。现有方法可以提出CAD操作，但没有任何单一的提案来源能在不同的零件几何形状和重建阶段中同样出色地工作。我们引入了CADFather，一个自主智能体系统，它协调互补的工具以从3D网格恢复参数化CAD程序。一个视觉-语言助手检查目标和中间重建的渲染图，然后决定扩展哪些候选CAD程序、调用哪些工具、生成多少提案以及何时完成。学习和算法工具提出CAD操作，而数值优化则优化现有程序的参数。提出的或优化的程序被执行和评估，以提供反馈用于后续决策。智能体为每个目标零件维护备选的候选程序，并在整个重建过程中保留最佳有效结果。CADFather使用预训练的生成和助手模型，无需额外训练。我们在完整的DeepCAD、Fusion360和MCB测试集以及CADENA-Bench、CADBench和BenchCAD上评估重建质量和执行有效性。我们还分析了计算成本以及成本与重建质量之间的权衡。
英文摘要
Reconstructing an editable CAD model from a 3D shape remains a challenging engineering task. Existing methods can propose CAD operations, but no single source of proposals works equally well across different part geometries and stages of reconstruction. We introduce CADFather, an autonomous agentic system that coordinates complementary tools to recover parametric CAD programs from 3D meshes. A vision-language assistant inspects renders of the target and intermediate reconstructions, then decides which candidate CAD programs to extend, which tools to invoke, how many proposals to generate, and when to finish. Learned and algorithmic tools propose CAD operations, while numerical optimization refines the parameters of existing programs. Proposed or refined programs are executed and evaluated to provide feedback for subsequent decisions. The agent maintains alternative candidate programs for each target part and preserves the best valid result throughout reconstruction. CADFather uses pretrained generation and assistant models without additional training. We evaluate reconstruction quality and execution validity on the full DeepCAD, Fusion360, and MCB test sets, as well as on CADENA-Bench, CADBench, and BenchCAD. We additionally analyze computational cost and the trade-off between cost and reconstruction quality.
发表机构
- Lomonosov Moscow State University（莫斯科国立罗蒙诺索夫大学）
- Innopolis University（因诺波利斯大学）
- FusionBrain Lab（FusionBrain实验室）
机构由 AI 辅助整理，请以论文原文为准。
