Awesome AI4CAD Hub Papers · Datasets · Projects
← Back to papers

SketchGraphs: A Large-Scale Dataset for Modeling Relational Geometry in Computer-Aided Design

arXiv 2020 45.6 method

TLDR

Introduces SketchGraphs, a large-scale dataset of 15 million parametric CAD sketches with geometric constraint graphs for machine learning.

Reasoning

The paper's strength is its large-scale, real-world dataset and open-source pipeline, enabling generative and conditional modeling benchmarks. However, it focuses only on 2D sketches, not full 3D CAD models, and lacks broader task coverage like reconstruction or text-to-CAD.

Read-first score

Read-first score 45.6, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 58.

Methodology quality 25%
70

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=benchmark,dataset,metric

Recency 8%
42.4

Uses a gentle age decay so recent papers surface without erasing older foundations. 2020

Reproducibility 25%
38

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=dataset

Topical relevance 42%
36.2

Uses existing LLM keyword relevance scores normalized to 0-100. AI for CAD,computer-aided design,neural CAD,generative CAD,parametric CAD,B-Rep,boundary representation,constructive solid geometry,CSG,sketch extrusion,CAD generation,CAD reconstruction,text-to-CAD,image-to-CAD,point cloud to CAD,CAD program

Field roles

Methodology anchor

Rank sensitivity

Stability: volatile; rank range: 80.

Keyword Scores

computer-aided design
10
parametric CAD
10
generative CAD
8
CAD generation
8
AI for CAD
7
neural CAD
6
sketch extrusion
5
CAD program
4
B-Rep
0
boundary representation
0
constructive solid geometry
0
CSG
0
CAD reconstruction
0
text-to-CAD
0
image-to-CAD
0
point cloud to CAD
0

Deep Analysis

Innovations

  • Introduction of SketchGraphs, a large-scale dataset of 15 million parametric CAD sketches extracted from real-world models.
  • Representation of each sketch as a geometric constraint graph, where nodes are geometric primitives and edges are designer-imposed constraints.
  • Open-source data processing pipeline for extracting and structuring the sketches.

Methodology

The authors collected 15 million 2D sketches from real-world parametric CAD models and represented each as a geometric constraint graph. They then defined and established benchmarks for two tasks: generative modeling of sketches and conditional generation of constraints given unconstrained geometry.

Key Results

Benchmarks were established for generative modeling of sketches and for conditional generation of likely constraints from unconstrained geometry, demonstrating the dataset's utility for these tasks.

Tags