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

Extrusion Segmentation Strategy to improve CAD Reconstruction from Point Cloud

arXiv 2026 51.7 method

TLDR

Proposes an extrusion segmentation strategy to improve deep learning-based CAD reconstruction from point clouds by decomposing shapes into individual extrusions.

Reasoning

The paper presents a novel segmentation approach that decomposes point clouds into extrusions, enhancing data diversity and model generalization. However, the abstract lacks quantitative results and comparisons, and the methodology details are sparse.

Read-first score

Read-first score 51.7, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 72.

Recency 8%
100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Topical relevance 42%
51.4

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

Methodology quality 25%
50

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

Reproducibility 25%
38

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

Field roles

Frontier

Rank sensitivity

Stability: volatile; rank range: 45.

Keyword Scores

CAD reconstruction
10
point cloud to CAD
10
sketch extrusion
9
computer-aided design
8
parametric CAD
7
CAD generation
7
AI for CAD
6
neural CAD
5
generative CAD
4
CAD program
3
B-Rep
2
constructive solid geometry
1
text-to-CAD
0
image-to-CAD
0

Deep Analysis

Innovations

  • Extrusion segmentation strategy that decomposes CAD models into individual extrusions to increase data diversity
  • End-to-end deep learning model for CAD reconstruction from point clouds

Methodology

The paper proposes an end-to-end deep learning model that reconstructs CAD models from point clouds. A segmentation approach decomposes CAD models into individual extrusions, which are used as partial shapes to augment training data diversity, aiming to improve model generalization and robustness.

Key Results

The extrusion segmentation strategy improves generalization and robustness of deep learning models for CAD reconstruction from point clouds.

Tags

CVAI