Deepcad: A deep generative network for computer-aided design models

R Wu, C **ao, C Zheng - Proceedings of the IEEE/CVF …, 2021 - openaccess.thecvf.com
Deep generative models of 3D shapes have received a great deal of research interest. Yet,
almost all of them generate discrete shape representations, such as voxels, point clouds …

SceneScript: Reconstructing Scenes with an Autoregressive Structured Language Model

A Avetisyan, C **e, H Howard-Jenkins, TY Yang… - … on Computer Vision, 2024 - Springer
We introduce SceneScript, a method that directly produces full scene models as a sequence
of structured language commands using an autoregressive, token-based approach. Our …

Deep learning methods of cross-modal tasks for conceptual design of product shapes: A review

X Li, Y Wang, Z Sha - Journal of Mechanical Design, 2023 - par.nsf.gov
Conceptual design is the foundational stage of a design process that translates ill-defined
design problems into low-fidelity design concepts and prototypes through design search …

Free2cad: Parsing freehand drawings into cad commands

C Li, H Pan, A Bousseau, NJ Mitra - ACM Transactions on Graphics …, 2022 - dl.acm.org
CAD modeling, despite being the industry-standard, remains restricted to usage by skilled
practitioners due to two key barriers. First, the user must be able to mentally parse a final …

Complexgen: Cad reconstruction by b-rep chain complex generation

H Guo, S Liu, H Pan, Y Liu, X Tong, B Guo - ACM Transactions on …, 2022 - dl.acm.org
We view the reconstruction of CAD models in the boundary representation (B-Rep) as the
detection of geometric primitives of different orders, ie, vertices, edges and surface patches …

Skexgen: Autoregressive generation of cad construction sequences with disentangled codebooks

X Xu, KDD Willis, JG Lambourne, CY Cheng… - arxiv preprint arxiv …, 2022 - arxiv.org
We present SkexGen, a novel autoregressive generative model for computer-aided design
(CAD) construction sequences containing sketch-and-extrude modeling operations. Our …

Computer-aided design as language

Y Ganin, S Bartunov, Y Li, E Keller… - Advances in Neural …, 2021 - proceedings.neurips.cc
Abstract Computer-Aided Design (CAD) applications are used in manufacturing to model
everything from coffee mugs to sports cars. These programs are complex and require years …

Neurosymbolic models for computer graphics

D Ritchie, P Guerrero, RK Jones, NJ Mitra… - Computer graphics …, 2023 - Wiley Online Library
Procedural models (ie symbolic programs that output visual data) are a historically‐popular
method for representing graphics content: vegetation, buildings, textures, etc. They offer …

Extrudenet: Unsupervised inverse sketch-and-extrude for shape parsing

D Ren, J Zheng, J Cai, J Li, J Zhang - European Conference on Computer …, 2022 - Springer
Sketch-and-extrude is a common and intuitive modeling process in computer aided design.
This paper studies the problem of learning the shape given in the form of point clouds by …

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 …