Img2CAD: Conditioned 3D CAD Model Generation from Single Image with Structured Visual Geometry

TL;DR

Img2CAD is a novel method that converts single 2D images into editable 3D CAD models using a new structured visual geometry representation, bridging AI reconstruction and CAD software.

Contribution

The paper introduces Img2CAD, the first approach to generate editable CAD models from images, utilizing Structured Visual Geometry and new datasets for enhanced research.

Findings

Structured Visual Geometry improves CAD model generation accuracy.

New datasets support conditioned CAD model research.

Method enables integration with CAD tools for editing and control.

Abstract

In this paper, we propose Img2CAD, the first approach to our knowledge that uses 2D image inputs to generate CAD models with editable parameters. Unlike existing AI methods for 3D model generation using text or image inputs often rely on mesh-based representations, which are incompatible with CAD tools and lack editability and fine control, Img2CAD enables seamless integration between AI-based 3D reconstruction and CAD software. We have identified an innovative intermediate representation called Structured Visual Geometry (SVG), characterized by vectorized wireframes extracted from objects. This representation significantly enhances the performance of generating conditioned CAD models. Additionally, we introduce two new datasets to further support research in this area: ABC-mono, the largest known dataset comprising over 200,000 3D CAD models with rendered images, and KOCAD, the first dataset featuring real-world captured objects alongside their ground truth CAD models, supporting further research in conditioned CAD model generation.