通过迭代修正生成可运行的CAD程序，提升逆向工程精度
CADReasoner: Iterative Program Editing for CAD Reverse Engineering
- 基于几何差异反馈，逐步优化生成的CadQuery代码
- 在三个基准上达到当前最佳性能，尤其在扫描仿真数据上表现突出
- 适合需要高精度3D建模的工程师和自动化设计场景
计算机辅助设计（CAD）支撑现代工程，但高质量零件制作仍需大量专家投入。现有AI方法多为单次生成，难以捕捉细微几何特征。人类工程师会对比输入形状与重建结果，逐轮修正设计。现有基于代理的方法虽模仿此流程，但受限于当前基础模型对3D空间的弱定位能力，可靠性与效率不足。我们提出CADReasoner，一种可迭代优化预测的模型，利用输入与预测形状间的几何差异进行闭环修正。模型输出可运行的CadQuery Python程序，其渲染网格将作为下一步输入。CADReasoner融合多视角图像与点云作为互补模态。为弥合真实感差距，我们在训练与评估中引入扫描-仿真协议。在DeepCAD、Fusion 360与MCB基准上，CADReasoner在干净数据与扫描仿真数据轨道均达当前最优表现。
原文摘要 · Abstract (English)
Computer-Aided Design (CAD) powers modern engineering, yet producing high-quality parts still demands substantial expert effort. Many AI systems tackle CAD reverse engineering, but most are single-pass and miss fine geometric details. In contrast, human engineers compare the input shape with the reconstruction and iteratively modify the design based on remaining discrepancies. Agent-based methods mimic this loop with frozen VLMs, but weak 3D grounding of current foundation models limits reliability and efficiency. We introduce CADReasoner, a model trained to iteratively refine its prediction using geometric discrepancy between the input and the predicted shape. The model outputs a runnable CadQuery Python program whose rendered mesh is fed back at the next step. CADReasoner fuses multi-view renders and point clouds as complementary modalities. To bridge the realism gap, we propose a scan-simulation protocol applied during both training and evaluation. Across DeepCAD, Fusion 360, and MCB benchmarks, CADReasoner attains state-of-the-art results on clean and scan-sim tracks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。