Cadfather coordinates tools to rebuild editable 3d models
CADFather: Autonomous CAD Reconstruction through Coordinated Tool Use
Artificial IntelligenceMachine Learning
Summary
Turning a 3D shape into an editable CAD model is tough because different parts need different approaches. The authors created CADFather, a system that uses several tools working together to guess how to build a CAD program from a 3D mesh. It looks at images of the shape and decides what steps to try next, improving its guesses based on feedback. This saves time and works well without extra training on new data.
What this means in practice
- •For industrial designers: Automatically generate editable CAD programs from 3D scans to speed up product redesign and customization.
- •For augmented reality developers: Create parametric 3D models from scanned objects to enable real-time manipulation and interaction in AR applications.
Authors
Gennadiy Savrasov, Maksim Elistratov, Nikita Gavrilov, Albert Garifullin, Oleg Pavlov, Soslan Kabisov, Vladimir Frolov, Anton Konushin, Andrey Kuznetsov, Dmitrii Zhemchuzhnikov
Abstract
Reconstructing an editable CAD model from a 3D shape remains a challenging engineering task. Existing methods can propose CAD operations, but no single source of proposals works equally well across different part geometries and stages of reconstruction. We introduce CADFather, an autonomous agentic system that coordinates complementary tools to recover parametric CAD programs from 3D meshes. A vision-language assistant inspects renders of the target and intermediate reconstructions, then decides which candidate CAD programs to extend, which tools to invoke, how many proposals to generate, and when to finish. Learned and algorithmic tools propose CAD operations, while numerical optimization refines the parameters of existing programs. Proposed or refined programs are executed and evaluated to provide feedback for subsequent decisions. The agent maintains alternative candidate programs for each target part and preserves the best valid result throughout reconstruction. CADFather uses pretrained generation and assistant models without additional training. We evaluate reconstruction quality and execution validity on the full DeepCAD, Fusion360, and MCB test sets, as well as on CADENA-Bench, CADBench, and BenchCAD. We additionally analyze computational cost and the trade-off between cost and reconstruction quality.