IterCAD: Iterative Program Repair for CAD Code Generation from Orthographic Views

2026-08-24

AI Summary

为解决从正交视图生成CAD代码时出现的几何不一致问题，提出IterCAD框架，通过迭代修正方法逐步改进代码准确性。

Abstract

Generating executable parametric CAD code from dimension-annotated orthographic drawings is a challenging task requiring geometric understanding, procedural reasoning, and precise numerical prediction. Existing vision-language approaches typically formulate this problem as one-shot generation, preventing the model from inspecting intermediate CAD results and correcting early mistakes, often leading to non-executable code or geometrically inconsistent outputs. In this paper, we propose IterCAD, an iterative framework that reformulates orthographic-view-to-CAD generation as a progressive program repair process. Instead of predicting the final CAD code in a single pass, IterCAD repeatedly analyzes the current CAD result, reasons about its discrepancy with the target views, and explicitly decides whether to REVISE the code or STOP the refinement process. To make iterative repair learnable, we further construct IterCAD-RS, a structured revise-or-stop supervision set containing both repairable intermediate CAD states and already-correct states, and develop a three-stage training strategy for initial generation, revision learning, and multi-turn RL optimization. By closing the loop between visual understanding, geometric verification, and code refinement, IterCAD progressively corrects structural and parametric errors. Experiments on CADExpert show that IterCAD consistently improves code executability and geometric fidelity over strong one-shot baselines.

Problem

• Orthographic Views
• CAD Code Generation
• Geometric Understanding
• Procedural Reasoning

Innovation

• Iterative Program Repair
• Orthographic Views
• Parametric CAD Code Generation
• Revise-or-Stop Supervision
• Geometric Verification