CADParser: A Learning Approach of Sequence Modeling for B-Rep CAD

arXiv 2023 48.6 method

TLDR

A learning approach to infer modeling sequences from B-Rep CAD geometry using graph and sequence modeling, with a new dataset including diverse operations.

Reasoning

The paper presents a novel method for inferring CAD construction sequences from B-Rep geometry, supported by a new dataset with operations like Revolution and Fillet. Strengths include the graph-to-sequence formulation and extensive experiments; weaknesses are the limited scope of operations and lack of real-world application validation beyond benchmarks.

Read-first score

Read-first score 48.6, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 91.

Methodology quality 25%

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

Recency 8%

65.1

Uses a gentle age decay so recent papers surface without erasing older foundations. 2023

Topical relevance 42%

56.9

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=dataset

Field roles

Methodology anchor

Rank sensitivity

Stability: volatile; rank range: 95.

Keyword Scores

B-Rep

boundary representation

computer-aided design

CAD reconstruction

AI for CAD

parametric CAD

CAD program

sketch extrusion

neural CAD

CAD generation

generative CAD

constructive solid geometry

CSG

text-to-CAD

image-to-CAD

point cloud to CAD

Deep Analysis

Innovations

Proposes CADParser, a learning approach to infer modeling sequences from B-Rep CAD models
Treats CAD geometry structure as a graph and construction workflow as a sequence for sequence modeling
Introduces a large-scale dataset with more comprehensive operations (Revolution, Fillet, Chamfer) beyond Sketch and Extrusion

Methodology

CADParser models the B-Rep geometry as a graph and the construction workflow as a sequence, using a learning approach to infer sequences from the graph. A new dataset with diverse CAD operations is introduced to train and evaluate the model.

Key Results

Extensive experiments show that CADParser competes with existing state-of-the-art methods quantitatively and qualitatively.