CADReasoner: Iterative Program Editing for CAD Reverse Engineering
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.
Field roles
Rank sensitivity
Stability: volatile; rank range: 12.
Keyword Scores
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.