Image2CADSeq: Computer-Aided Design Sequence and Knowledge Inference from Product Images

2025-01-09

AI Summary

Reverse engineering without original CAD files remains challenging, particularly for reconstructing parametric B-rep models and recovering explicit design intent from single 2D product images. Method: This paper introduces Image2CADSeq, the first end-to-end method that generates executable, structured CAD operation sequences directly from a single 2D image. Built upon a Transformer architecture, it leverages a synthetically generated image–CAD sequence paired dataset and integrates the OpenCASCADE modeling kernel to ensure geometric validity and executability of the output sequences. Contribution/Results: We propose a novel multi-level evaluation framework that transcends conventional static B-rep metrics by enabling process-level editing and design intent interpretation. On the synthetic benchmark, Image2CADSeq achieves an average B-rep intersection-over-union (IoU) of 0.82, demonstrating the feasibility and practicality of image-driven, process-aware CAD reconstruction for reverse engineering.

Technology Category

• Computer Vision: Image and Video Retrieval
• Machine Learning: Deep Generative Models & Autoencoders
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

Computer-aided design (CAD) tools empower designers to design and modify 3D models through a series of CAD operations, commonly referred to as a CAD sequence. In scenarios where digital CAD files are not accessible, reverse engineering (RE) has been used to reconstruct 3D CAD models. Recent advances have seen the rise of data-driven approaches for RE, with a primary focus on converting 3D data, such as point clouds, into 3D models in boundary representation (B-rep) format. However, obtaining 3D data poses significant challenges, and B-rep models do not reveal knowledge about the 3D modeling process of designs. To this end, our research introduces a novel data-driven approach with an Image2CADSeq neural network model. This model aims to reverse engineer CAD models by processing images as input and generating CAD sequences. These sequences can then be translated into B-rep models using a solid modeling kernel. Unlike B-rep models, CAD sequences offer enhanced flexibility to modify individual steps of model creation, providing a deeper understanding of the construction process of CAD models. To quantitatively and rigorously evaluate the predictive performance of the Image2CADSeq model, we have developed a multi-level evaluation framework for model assessment. The model was trained on a specially synthesized dataset, and various network architectures were explored to optimize the performance. The experimental and validation results show great potential for the model in generating CAD sequences from 2D image data.

Problem

• 3D model reconstruction
• product photo analysis
• automatic design understanding

Innovation

• Image2CADSeq
• 3D model reconstruction
• CAD sequence generation