aiqbench analysis
CADFit addresses the persistent limitation of existing mesh-to-CAD tools by employing a hybrid optimization framework that successfully reconstructs complex, editable parametric sequences from geometric inputs. The method demonstrates superior performance in volumetric accuracy and invalidity reduction compared to state-of-the-art baselines, particularly for high-complexity designs involving diverse operations like fillets and revolutions. This advancement provides a robust foundation for generating richer datasets and improving future learning-based approaches to CAD reverse engineering.
CADFit: Precise Mesh-to-CAD Program Generation with Hybrid Optimization
arXiv:2605.01171v2 Announce Type: replace-cross Abstract: Despite recent progress, recovering parametric CAD construction sequences from geometric input, such as meshes or point clouds, is a key challenge for design and manufacturing, as existing CAD reconstruction and generation methods are largely restricted to difficult-to-edit formats like meshes or Breps or editable simple sketch-and-extrude pipelines and low-complexity datasets. We introduce CADFit, a hybrid optimization-based CAD reconstruction framework that recovers complex, editable CAD construction sequences from meshes by incrementally fitting and validating parametric operations using geometric feedback. Our approach is distinguished by formulating reconstruction as an IoU-driven optimization over structured CAD programs and supporting a rich set of operations, including extrusions, revolutions, fillets, and chamfers. Experiments on multiple CAD benchmarks show that CADFit outperforms state-of-the-art mesh-to-CAD methods in volumetric Intersection-over-Union and Chamfer Distance, while substantially reducing the Invalid Ratio of reconstructed CAD programs, particularly for complex designs. We further present a multimodal pipeline that enables end-to-end reconstruction of CAD construction sequences from images by combining image-based geometry reconstruction with CADFit. By enabling accurate reconstruction of higher-complexity CAD models, CADFit provides a practical foundation for generating richer datasets and advancing future learning-based approaches to CAD reverse engineering. The code is available at: https://github.com/ghadinehme/CADFit.
Abstract:Despite recent progress, recovering parametric CAD construction sequences from geometric input, such as meshes or point clouds, is a key challenge for design and manufacturing, as existing CAD reconstruction and generation methods are largely restricted to difficult-to-edit formats like meshes or Breps or editable simple sketch-and-extrude pipelines and low-complexity datasets. We introduce CADFit, a hybrid optimization-based CAD reconstruction framework that recovers complex, editable CAD construction sequences from meshes by incrementally fitting and validating parametric operations using geometric feedback. Our approach is distinguished by formulating reconstruction as an IoU-driven optimization over structured CAD programs and supporting a rich set of operations, including extrusions, revolutions, fillets, and chamfers. Experiments on multiple CAD benchmarks show that CADFit outperforms state-of-the-art mesh-to-CAD methods in volumetric Intersection-over-Union and Chamfer Distance, while substantially reducing the Invalid Ratio of reconstructed CAD programs, particularly for complex designs. We further present a multimodal pipeline that enables end-to-end reconstruction of CAD construction sequences from images by combining image-based geometry reconstruction with CADFit. By enabling accurate reconstruction of higher-complexity CAD models, CADFit provides a practical foundation for generating richer datasets and advancing future learning-based approaches to CAD reverse engineering. The code is available at: this https URL.
Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
arXiv:2605.01171 [cs.CV]
(or arXiv:2605.01171v2 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2605.01171 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 293 words
Related coverage
Contextual Decision Making: Predictive or Generative
arXiv · Oct 27, 2026
When Optimization Becomes Manipulation: Defending Generative Search against Malicious Generative Engine Optimization
arXiv · Sep 5, 2026
Launching UI for generative AI inference recommendations in Amazon SageMaker AI
AWS · Jul 13, 2026
New agent skill: Amazon SageMaker optimized generative AI inference for your coding agent
AWS · Oct 5, 2026