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

CADReasoner: Iterative Program Editing for CAD Reverse Engineering

arXiv 2026 57.2 method

TLDR

CADReasoner iteratively refines CAD reverse engineering by editing programs based on geometric discrepancy, achieving SOTA on multiple benchmarks.

Reasoning

The paper introduces a novel iterative refinement approach for CAD reverse engineering, leveraging geometric discrepancy and complementary modalities. Strengths include state-of-the-art results on multiple benchmarks and a scan-simulation protocol. Weaknesses include reliance on CadQuery and potential generalization issues, though limitations are not detailed in the abstract.

Read-first score

Read-first score 57.2, 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

Methodology quality 25%
80

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

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

Reproducibility 25%
30

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=none

Field roles

FrontierBridgeMethodology anchor

Rank sensitivity

Stability: volatile; rank range: 12.

Keyword Scores

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

Deep Analysis

Innovations

  • Iterative refinement using geometric discrepancy between input and predicted shape
  • Outputs runnable CadQuery Python program with rendered mesh feedback loop
  • Fuses multi-view renders and point clouds as complementary modalities
  • Scan-simulation protocol to bridge realism gap during training and evaluation

Methodology

CADReasoner is a model that iteratively refines CAD reconstructions by generating a CadQuery Python program, rendering its mesh, and feeding back the geometric discrepancy with the input shape. It combines multi-view renders and point clouds as input, and uses a scan-simulation protocol to improve robustness to real-world scans.

Key Results

CADReasoner achieves state-of-the-art performance on DeepCAD, Fusion 360, and MCB benchmarks in both clean and scan-simulated tracks.

Tags

GRCVHC