VideoCAD: A Large-Scale Video Dataset for Learning UI Interactions and 3D Reasoning from CAD Software

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

VideoCAD是一款大规模合成数据集，包含逾4.1万条带标注的计算机辅助设计（Computer-Aided Design，CAD）操作视频录制样本。该数据集依托自动化框架，从人工构建的CAD设计中采集高保真用户界面（User Interface，UI）操作数据生成。与现有同类数据集对比可见，VideoCAD在面向真实工程任务的UI交互学习领域，复杂度高出一个数量级，且任务时间跨度为其他数据集的20倍。

搜集汇总

背景与挑战

背景概述

VideoCAD是一个包含41,000多个带注释CAD操作视频的大规模合成数据集，专为学习CAD软件中的UI交互和3D推理而设计。该数据集通过自动化框架收集高保真UI操作数据，其时间跨度和复杂度远超现有数据集，适用于真实世界工程任务的长期交互学习。