CADFit: Precise Mesh-to-CAD Program Generation with Hybrid Optimization

arXiv 2026 70.9 method

TLDR

CADFit uses hybrid optimization to recover editable parametric CAD construction sequences from meshes, outperforming existing methods in accuracy and validity.

Reasoning

The paper introduces a novel hybrid optimization framework for mesh-to-CAD reconstruction, achieving strong results on benchmarks. However, it lacks learning-based components and may have scalability limitations.

Read-first score

Read-first score 70.9, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 82.

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,experiment,metric

Topical relevance 42%

51.2

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

FrontierMethodology anchorReproducibility anchor

Rank sensitivity

Stability: volatile; rank range: 13.

Keyword Scores

computer-aided design

parametric CAD

CAD reconstruction

CAD program

CAD generation

image-to-CAD

generative CAD

point cloud to CAD

AI for CAD

sketch extrusion

B-Rep

boundary representation

neural CAD

constructive solid geometry

CSG

text-to-CAD

Deep Analysis

Innovations

Hybrid optimization-based CAD reconstruction that incrementally fits and validates parametric operations using geometric feedback
IoU-driven optimization over structured CAD programs
Support for rich operations including extrusions, revolutions, fillets, and chamfers
Multimodal pipeline for end-to-end reconstruction from images

Methodology

CADFit reconstructs CAD construction sequences from meshes by incrementally fitting parametric operations (extrusions, revolutions, fillets, chamfers) and validating them via geometric feedback. The reconstruction is formulated as an IoU-driven optimization over structured CAD programs. A multimodal extension combines image-based geometry reconstruction with CADFit for end-to-end image-to-CAD.

Key Results

CADFit outperforms state-of-the-art mesh-to-CAD methods in volumetric Intersection-over-Union and Chamfer Distance, and substantially reduces the Invalid Ratio of reconstructed CAD programs, especially for complex designs.

Resources

Paper Code