Engineering Sketch Generation for Computer-Aided Design

@article{Willis2021EngineeringSG,
  title={Engineering Sketch Generation for Computer-Aided Design},
  author={Karl D. D. Willis and Pradeep Kumar Jayaraman and J. Lambourne and Hang Chu and Yewen Pu},
  journal={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  year={2021},
  pages={2105-2114}
}
Engineering sketches form the 2D basis of parametric Computer-Aided Design (CAD), the foremost modeling paradigm for manufactured objects. In this paper we tackle the problem of learning based engineering sketch generation as a first step towards synthesis and composition of parametric CAD models. We propose two generative models, CurveGen and TurtleGen, for engineering sketch generation. Both models generate curve primitives without the need for a sketch constraint solver and explicitly… 

Figures and Tables from this paper

SketchGen: Generating Constrained CAD Sketches
TLDR
SketchGen is proposed as a generative model based on a transformer architecture to address the heterogeneity problem by carefully designing a sequential language for the primitives and constraints that allows distinguishing between different primitive or constraint types and their parameters, while encouraging the model to re-use information across related parameters, encoding shared structure.
Vitruvion: A Generative Model of Parametric CAD Sketches
TLDR
An approach to generative modeling of parametric CAD sketches, which constitute the basic computational building blocks of modern mechanical design, and its ability to synthesize realistic CAD sketches and its potential to aid the mechanical design work are demonstrated.
Computer-Aided Design as Language
TLDR
This work proposes a machine learning model capable of automatically generating 2D sketches that lie at the heart of every 3D construction and shows that the approach has enough flexibility to accommodate the complexity of the domain and performs well for both unconditional synthesis and image-to-sketch translation.
DeepCAD: A Deep Generative Network for Computer-Aided Design Models
TLDR
This work presents the first 3D generative model for a drastically different shape representation— describing a shape as a sequence of computer-aided design (CAD) operations, and proposes a CAD generative network based on the Transformer.
ComplexGen: CAD Reconstruction by B-Rep Chain Complex Generation
TLDR
A novel neural framework is proposed that consists of a sparse CNN encoder for input point cloud processing and a tri-path transformer decoder for generating geometric primitives and their mutual relationships with estimated probabilities, leading to structurally more faithful and complete CAD B-Rep models than previous results.
Point2Cyl: Reverse Engineering 3D Objects from Point Clouds to Extrusion Cylinders
TLDR
A neural network is introduced that solves the extrusion cylinder decomposition problem in a geometry-grounded way by first learning underlying geometric proxies, and predicts per-point segmentation, base/barrel labels and normals, then estimates for the underlying extrusion parameters in differentiable and closed-form formulations.
Neural Face Identification in a 2D Wireframe Projection of a Manifold Object
TLDR
This paper approaches the classical problem of face identification from a novel data-driven point of view, and adopts a variant of the popular Transformer model to predict the edges associated with the same face in a natural order.
SolidGen: An Autoregressive Model for Direct B-rep Synthesis
TLDR
This paper presents a new approach that enables learning from and synthesizing B-reps without the need for supervision through CAD modeling sequence data, and demonstrates qualitatively, quantitatively and through perceptual evaluation by human subjects that SolidGen can produce high quality, realistic looking CAD models.
Deep Learning for Free-Hand Sketch: A Survey
  • Peng Xu
  • Computer Science
    IEEE transactions on pattern analysis and machine intelligence
  • 2022
TLDR
A comprehensive survey of the deep learning techniques oriented at free-hand sketch data, and the applications that they enable.
The Computer-Aided Design Algorithm of Dyeing and Weaving Graphics from the Perspective of Public Art
  • Yan Cui
  • Computer Science
    Computational intelligence and neuroscience
  • 2022
TLDR
This paper proposes a computer-aided design algorithm for dyeing and weaving graphics in the field of public art by color segmentation of the known visual scene images according to the set threshold, morphological processing of the segmented images, reducing noise and fractures affecting the acquired connected areas, and formulating extraction rules to screen candidate areas.
...
...

References

SHOWING 1-10 OF 43 REFERENCES
SketchGraphs: A Large-Scale Dataset for Modeling Relational Geometry in Computer-Aided Design
TLDR
This work introduces SketchGraphs, a collection of 15 million sketches extracted from real-world CAD models coupled with an open-source data processing pipeline that demonstrates and establishes benchmarks for two use cases of the dataset: generative modeling of sketches and conditional generation of likely constraints given unconstrained geometry.
A benchmark for rough sketch cleanup
TLDR
This work presents the first benchmark to evaluate and focus sketch cleanup research, and identifies shortcomings among state-of-the-art cleanup algorithms and discusses open problems for future research.
Fusion 360 Gallery: A Dataset and Environment for Programmatic CAD Reconstruction
TLDR
This paper provides a dataset of 8,625 designs, comprising sequential sketch and extrude modeling operations, together with a complementary environment called the Fusion 360 Gym, to assist with performing CAD reconstruction and outlines a standard CAD reconstruction task.
Advanced drawing beautification with ShipShape
Deep Vectorization of Technical Drawings
TLDR
This work presents a new method for vectorization of technical line drawings, such as floor plans, architectural drawings, and 2D CAD images, that quantitatively and qualitatively outperforms a number of existing techniques on a collection of representative technical drawings.
Deep Parametric Shape Predictions Using Distance Fields
TLDR
This work uses distance fields to transition between shape parameters like control points and input data on a pixel grid and demonstrates efficacy on 2D and 3D tasks, including font vectorization and surface abstraction.
PolyGen: An Autoregressive Generative Model of 3D Meshes
TLDR
This work presents an approach which models the mesh directly, predicting mesh vertices and faces sequentially using a Transformer-based architecture, and shows that the model is capable of producing high-quality, usable meshes, and establishes log-likelihood benchmarks for the mesh-modelling task.
Learning Manifold Patch-Based Representations of Man-Made Shapes
TLDR
This work proposes a new representation that is usable in conventional CAD modeling pipelines and can also be learned by deep neural networks, and demonstrates the benefits of the representation by applying it to the task of sketch-based modeling.
Constrained fitting in reverse engineering
DeepSpline: Data-Driven Reconstruction of Parametric Curves and Surfaces
TLDR
This work proposes a deep learning architecture that adapts to perform spline fitting tasks accordingly, providing complementary results to the aforementioned traditional methods.
...
...