CADOps-Net: Jointly Learning CAD Operation Types and Steps from Boundary-Representations

TL;DR

This paper introduces CADOps-Net, a deep learning model that jointly predicts CAD operation types and steps from boundary representations, aiding in reconstructing CAD design history, supported by a new extensive dataset.

Contribution

The paper presents a novel neural network architecture for joint learning of CAD operation types and steps, along with the CC3D-Ops dataset that reflects industrial complexity.

Findings

CADOps-Net achieves competitive performance on CC3D-Ops and Fusion360 datasets.

Joint learning improves accuracy in CAD operation classification.

The CC3D-Ops dataset enhances training for industrial CAD models.

Abstract

3D reverse engineering is a long sought-after, yet not completely achieved goal in the Computer-Aided Design (CAD) industry. The objective is to recover the construction history of a CAD model. Starting from a Boundary Representation (B-Rep) of a CAD model, this paper proposes a new deep neural network, CADOps-Net, that jointly learns the CAD operation types and the decomposition into different CAD operation steps. This joint learning allows to divide a B-Rep into parts that were created by various types of CAD operations at the same construction step; therefore providing relevant information for further recovery of the design history. Furthermore, we propose the novel CC3D-Ops dataset that includes over $37k$ CAD models annotated with CAD operation type labels and step labels. Compared to existing datasets, the complexity and variety of CC3D-Ops models are closer to those used for industrial purposes. Our experiments, conducted on the proposed CC3D-Ops and the publicly available Fusion360 datasets, demonstrate the competitive performance of CADOps-Net with respect to state-of-the-art, and confirm the importance of the joint learning of CAD operation types and steps.