CADENA: Stepwise CAD Reverse Engineering

arXiv 2026 68.3 method

TLDR

Introduces CADENA, a stepwise CAD reverse engineering model that reconstructs 3D meshes into parametric CAD programs, outperforming prior methods on multiple benchmarks.

Reasoning

The paper presents a novel approach with strong empirical validation across several datasets and a new benchmark. However, the abstract lacks details on architecture and limitations, and some key terms like B-Rep or CSG are not directly addressed.

Read-first score

Read-first score 68.3, 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

Reproducibility 25%

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

Methodology quality 25%

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

Topical relevance 42%

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

FrontierMethodology anchorReproducibility anchor

Rank sensitivity

Stability: volatile; rank range: 22.

Keyword Scores

CAD reconstruction

CAD program

computer-aided design

parametric CAD

AI for CAD

neural CAD

generative CAD

CAD generation

sketch extrusion

B-Rep

boundary representation

constructive solid geometry

CSG

text-to-CAD

image-to-CAD

point cloud to CAD

Deep Analysis

Innovations

Stepwise CAD reverse engineering with feature-by-feature construction and intermediate geometry comparison
CADENA-Bench: a benchmark for mechanical parts reverse-engineering evaluation across categories

Methodology

CADENA reconstructs a 3D mesh as a parametric CAD program by iteratively adding operations, comparing the predicted geometry with the target at each step. The model is evaluated on the new CADENA-Bench and existing datasets (DeepCAD, Fusion 360, MCB).

Key Results

CADENA outperforms prior methods on CADENA-Bench and the DeepCAD, Fusion 360, and MCB datasets.

Resources

Paper Code