Brepgen: A b-rep generative diffusion model with structured latent geometry

X Xu, J Lambourne, P Jayaraman, Z Wang… - ACM Transactions on …, 2024 - dl.acm.org
This paper presents BrepGen, a diffusion-based generative approach that directly outputs a
Boundary representation (B-rep) Computer-Aided Design (CAD) model. BrepGen …

Hierarchical neural coding for controllable cad model generation

X Xu, PK Jayaraman, JG Lambourne… - arxiv preprint arxiv …, 2023 - arxiv.org
This paper presents a novel generative model for Computer Aided Design (CAD) that 1)
represents high-level design concepts of a CAD model as a three-level hierarchical tree of …

Extracting 3-D structural lines of building from ALS point clouds using graph neural network embedded with corner information

T Jiang, Y Wang, Z Zhang, S Liu, L Dai… - … on Geoscience and …, 2023 - ieeexplore.ieee.org
The representation quantifies the geometric shape and topology of a building is a necessary
procedure for many urban planning applications. A sharp line framework is a high-level …

Multicad: Contrastive representation learning for multi-modal 3d computer-aided design models

W Ma, M Xu, X Li, X Zhou - Proceedings of the 32nd ACM International …, 2023 - dl.acm.org
CAD models are multimodal data where information and knowledge contained in
construction sequences and shapes are complementary to each other and representation …

Automatic 3D CAD models reconstruction from 2D orthographic drawings

C Zhang, R Pinquié, A Polette, G Carasi… - Computers & …, 2023 - Elsevier
This paper introduces a two-stage approach that automatically generates 3D CAD models
from 2D orthographic drawings. First, a pattern-matching algorithm is proposed to …

CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM

J Xu, C Wang, Z Zhao, W Liu, Y Ma, S Gao - arxiv preprint arxiv …, 2024 - arxiv.org
This paper aims to design a unified Computer-Aided Design (CAD) generation system that
can easily generate CAD models based on the user's inputs in the form of textual …

Draw Step by Step: Reconstructing CAD Construction Sequences from Point Clouds via Multimodal Diffusion.

W Ma, S Chen, Y Lou, X Li… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
Reconstructing CAD construction sequences from raw 3D geometry serves as an interface
between real-world objects and digital designs. In this paper we propose CAD-Diffuser a …

HoW-3D: Holistic 3D wireframe perception from a single image

W Ma, B Tan, N Xue, T Wu, X Zheng… - … Conference on 3D …, 2022 - ieeexplore.ieee.org
This paper studies the problem of holistic 3D wireframe perception (HoW-3D), a new task of
perceiving both the visible 3D wireframes and the invisible ones from single-view 2D …

Geometric Deep Learning for Computer-Aided Design: A Survey

N Heidari, A Iosifidis - arxiv preprint arxiv:2402.17695, 2024 - arxiv.org
Geometric Deep Learning techniques have become a transformative force in the field of
Computer-Aided Design (CAD), and have the potential to revolutionize how designers and …

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

X Li, Z Sha - arxiv preprint arxiv:2501.04928, 2025 - arxiv.org
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 …