A parametric and feature-based CAD dataset to support human-computer interaction for advanced 3D shape learning

arXiv 2024 47.7 benchmark

TLDR

A parametric and feature-based CAD dataset with a selection mechanism for human-computer interaction, enabling advanced 3D shape learning.

Reasoning

The paper introduces a novel dataset that includes complex engineering features and a selection mechanism to mimic human design intent, which is a strength. However, the abstract is cut off and lacks details on the experimental setup and limitations, and the dataset's real-world applicability is not fully validated.

Read-first score

Read-first score 47.7, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 67.

Methodology quality 25%

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

Recency 8%

75.1

Uses a gentle age decay so recent papers surface without erasing older foundations. 2024

Topical relevance 42%

41.9

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

Reproducibility 25%

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

Field roles

Methodology anchor

Rank sensitivity

Stability: volatile; rank range: 35.

Keyword Scores

parametric CAD

computer-aided design

CAD generation

CAD reconstruction

generative CAD

sketch extrusion

B-Rep

boundary representation

AI for CAD

neural CAD

constructive solid geometry

CSG

text-to-CAD

image-to-CAD

point cloud to CAD

CAD program

Deep Analysis

Innovations

First parametric and feature-based CAD dataset with a selection mechanism to support human-computer interaction in 3D shape learning
Inclusion of complicated engineering features (fillet, chamfer, mirror, pocket, groove, revolve) beyond simple sketch and extrude
Selection mechanism that mimics human focus on topological entities, establishing relationships among features to express design intention and knowledge

Methodology

The authors construct a parametric, feature-based CAD dataset that includes complex engineering features and a selection mechanism capturing how human engineers interact with topological entities. This mechanism encodes design intent by linking features, and the dataset is evaluated on 3D reconstruction and generation tasks against existing parametric datasets.

Key Results

The proposed dataset outperforms existing CAD datasets in both reconstruction and generation tasks, achieves better prediction accuracy, and generates models that comply with human CAD semantics and are editable in mainstream industrial CAD software.