GenCAD-Self-Repairing: Feasibility Enhancement for 3D CAD Generation

TL;DR

This paper introduces GenCAD-Self-Repairing, a framework that significantly improves the feasibility of AI-generated 3D CAD models by integrating diffusion guidance and self-repair mechanisms, thereby expanding practical applications.

Contribution

It presents a novel self-repairing framework that enhances the feasibility of generative CAD models using diffusion guidance and correction mechanisms, addressing a key limitation of prior models.

Findings

Converted two-thirds of infeasible designs to feasible ones

Maintained geometric accuracy of generated models

Significantly increased CAD generation feasibility rate

Abstract

With the advancement of generative AI, research on its application to 3D model generation has gained traction, particularly in automating the creation of Computer-Aided Design (CAD) files from images. GenCAD is a notable model in this domain, leveraging an autoregressive transformer-based architecture with a contrastive learning framework to generate CAD programs. However, a major limitation of GenCAD is its inability to consistently produce feasible boundary representations (B-reps), with approximately 10% of generated designs being infeasible. To address this, we propose GenCAD-Self-Repairing, a framework that enhances the feasibility of generative CAD models through diffusion guidance and a self-repairing pipeline. This framework integrates a guided diffusion denoising process in the latent space and a regression-based correction mechanism to refine infeasible CAD command sequences while preserving geometric accuracy. Our approach successfully converted two-thirds of infeasible designs in the baseline method into feasible ones, significantly improving the feasibility rate while simultaneously maintaining a reasonable level of geometric accuracy between the point clouds of ground truth models and generated models. By significantly improving the feasibility rate of generating CAD models, our approach helps expand the availability of high-quality training data and enhances the applicability of AI-driven CAD generation in manufacturing, architecture, and product design.