UniCAD: A Unified Benchmark and Universal Model for Multi-Modal Multi-Task CAD
This work provides a comprehensive benchmark and a single model for multiple CAD tasks, addressing the lack of unified evaluation in the field.
UniCAD introduces a unified benchmark for multi-modal CAD learning and a universal model (UniCAD-MLLM) that achieves state-of-the-art performance across point-to-CAD reconstruction, text/image-to-CAD generation, and CAD question answering, outperforming existing baselines.
Computer-Aided Design (CAD) underpins modern engineering and manufacturing by enabling the creation of precise, editable 3D models. However, CAD research typically studies tasks in isolation, and multi-modal, multi-task learning for CAD is hindered by the absence of a unified benchmark. To address this gap, we introduce UniCAD, a comprehensive benchmark for multi-modal CAD learning that covers point-to-CAD reconstruction, text/image-to-CAD generation, and CAD question answering across diverse input modalities. Alongside the benchmark, we present UniCAD-MLLM, a universal multi-modal large language model that ingests text, images, sketches, and point clouds and performs these heterogeneous tasks in an end-to-end fashion within a single framework. Extensive experiments on the UniCAD and Fusion360 benchmarks demonstrate that UniCAD-MLLM achieves state-of-the-art performance across all tasks, outperforming existing task-specific and multi-task baselines. We will release the dataset, code, and pretrained models to accelerate future research.