CADRec-Net: Reconstruct CAD design from B-Rep to support reuse and redesign

In the CG field, most previous 3D reconstructions try to reconstruct geometric models. Geometric models are dumb models, which are not (or very difficult) to edit, reuse, and redesign. Therefore, the reconstruction of parametric CAD models has enormous significance for the modern CAD/CAM industry. The challenges of reconstructing parametric CAD models involve capturing the design history, design intent, and design semantics, which are more complex and difficult than reconstructing geometric models. To address this problem, this paper presents CADRec-Net, which takes a B-Rep model (STEP format, industry standard) and reconstructs its design history for engineering reuse and redesign. To support potential industry applications, we compare our approach with recent approaches on public datasets. The experiments demonstrate the superiority of the proposed CADRec-Net. Furthermore, for the industry integration experiment, we also successfully integrated the reconstructed design history into mainstream CAD software for reuse and redesign.

Publication Details

Journal
IEEE Computer Graphics and Applications
Published
2026-01-01
DOI
https://doi.org/10.1109/mcg.2026.3677191
Primary Topic
Manufacturing Process and Optimization
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

CADRec-Net: Reconstruct CAD design from B-Rep to support reuse and redesign

IEEE Computer Graphics and Applications
Manufacturing Process and Optimization
article

CADRec-Net: Reconstruct CAD design from B-Rep to support reuse and redesign

article en

Abstract

In the CG field, most previous 3D reconstructions try to reconstruct geometric models. Geometric models are dumb models, which are not (or very difficult) to edit, reuse, and redesign. Therefore, the reconstruction of parametric CAD models has enormous significance for the modern CAD/CAM industry. The challenges of reconstructing parametric CAD models involve capturing the design history, design intent, and design semantics, which are more complex and difficult than reconstructing geometric models. To address this problem, this paper presents CADRec-Net, which takes a B-Rep model (STEP format, industry standard) and reconstructs its design history for engineering reuse and redesign. To support potential industry applications, we compare our approach with recent approaches on public datasets. The experiments demonstrate the superiority of the proposed CADRec-Net. Furthermore, for the industry integration experiment, we also successfully integrated the reconstructed design history into mainstream CAD software for reuse and redesign.

IEEE Computer Graphics and ApplicationsVol. PP
Industry, innovation and infrastructure
Openalex Percentile: Top 9%
Manufacturing Process and Optimization
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.