Search papers, labs, and topics across Lattice.
This paper introduces IterCAD, an iterative framework for generating executable parametric CAD code from orthographic drawings by reformulating the task as a progressive program repair process. By allowing the model to analyze and revise intermediate CAD outputs rather than relying on a one-shot generation approach, IterCAD effectively addresses structural and parametric errors in the code. Experimental results demonstrate that IterCAD significantly enhances both code executability and geometric fidelity compared to existing one-shot methods.
IterCAD achieves a remarkable improvement in CAD code quality by enabling iterative refinement, correcting errors that traditional one-shot methods overlook.
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.
