CADReview: Automatically Reviewing CAD Programs with Error Detection and Correction

TL;DR

This paper introduces ReCAD, a framework for automatic error detection and correction in CAD programs, supported by a large dataset, improving review accuracy over existing multimodal models.

Contribution

The paper presents ReCAD, a novel framework for CAD program error detection and correction, and introduces CADReview, a large dataset for training and evaluating CAD review models.

Findings

ReCAD outperforms existing multimodal large language models in CAD error detection.

The CADReview dataset contains over 20,000 program-image pairs with diverse errors.

ReCAD demonstrates significant improvements in CAD program review accuracy.

Abstract

Computer-aided design (CAD) is crucial in prototyping 3D objects through geometric instructions (i.e., CAD programs). In practical design workflows, designers often engage in time-consuming reviews and refinements of these prototypes by comparing them with reference images. To bridge this gap, we introduce the CAD review task to automatically detect and correct potential errors, ensuring consistency between the constructed 3D objects and reference images. However, recent advanced multimodal large language models (MLLMs) struggle to recognize multiple geometric components and perform spatial geometric operations within the CAD program, leading to inaccurate reviews. In this paper, we propose the CAD program repairer (ReCAD) framework to effectively detect program errors and provide helpful feedback on error correction. Additionally, we create a dataset, CADReview, consisting of over 20K program-image pairs, with diverse errors for the CAD review task. Extensive experiments demonstrate that our ReCAD significantly outperforms existing MLLMs, which shows great potential in design applications.