发表机构
Massachusetts Institute of Technology（麻省理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
StepCAD提出一种结合状态条件CAD策略与IoU引导树搜索的生成优化方法，从网格恢复可执行CAD程序，并引入含150万程序的数据集，在重建基准上实现最高87.2%的相对IoU提升。
AI 中文摘要
从3D网格中恢复可执行的CAD程序具有挑战性，原因在于CAD构造的组合性质以及离散建模选择与连续参数之间的交互。许多基于学习的方法在单次前向中预测完整程序，并主要依赖草图-拉伸表示，这限制了操作多样性以及在重建过程中纠正几何误差的机会。我们提出了StepCAD，一种生成式优化方法，将状态条件的CAD策略与几何引导搜索相结合。给定输入网格，该策略基于目标和中间几何预测构造动作，并通过IoU引导的树搜索通过局部编辑来优化生成的程序。我们还引入了ARCADE-1.5M，一个包含150万个可执行CAD程序的大规模数据集，涵盖多样化的操作、最大长度超过150个计数操作的操作序列，以及1250万个中间状态-动作转换。在多个CAD重建基准上的实验表明，StepCAD实现了最先进的几何重建精度，并具有持续的高有效性，相对于最强评估基线，相对IoU提升最高达87.2%，在复杂形状上尤其获得大幅提升。项目页面：此https URL
英文摘要
Recovering executable CAD programs from 3D meshes is challenging due to the compositional nature of CAD construction and the interaction between discrete modeling choices and continuous parameters. Many learning-based methods predict complete programs in a single pass and rely predominantly on sketch-extrude representations, limiting operation diversity and opportunities to correct geometric errors during reconstruction. We introduce StepCAD, a generative optimization approach that combines a state-conditioned CAD policy with geometry-guided search. Given an input mesh, the policy predicts construction actions conditioned on both target and intermediate geometry, and an IoU-guided tree search refines the resulting program through local edits. We also introduce ARCADE-1.5M, a large-scale dataset of 1.5M executable CAD programs spanning diverse operations, sequences with a maximum length of 150+ counted operations, and 12.5M intermediate state-action transitions. Experiments across multiple CAD reconstruction benchmarks show that StepCAD achieves state-of-the-art geometric reconstruction accuracy with consistently high validity, yielding up to 87.2% relative IoU improvement over the strongest evaluated baseline, with particularly large gains on complex shapes. Project page: https://ghadinehme.com/stepcad.github.io/
