VideoCAD: A Dataset and Model for Learning Long‑Horizon 3D CAD UI Interactions from Video

VideoCAD is a large-scale synthetic dataset consisting of over 41K annotated video recordings of CAD operations, generated using an automated framework for collecting high-fidelity UI action data from human-made CAD designs. Comparison with existing datasets shows that VideoCAD offers an order of magnitude higher complexity in UI interaction learning for real-world engineering tasks, having a 20x longer time horizon than other datasets