Publication
DreamCAD: Scaling Multi-modal CAD Generation using Differentiable Parametric Surfaces
Mohammad Sadil Khan; Muhammad Usama; Rolandos Alexandros Potamias; Didier Stricker; Muhammad Zeshan Afzal; Jiankang Deng; Ismail Elezi
In: Proceedings of ECCV 2026. European Conference on Computer Vision (ECCV-2026), The 19th European Conference on Computer Vision, located at ECCV 2026, September 8-12, Malmö, Sweden, Sweden, Springer Cham, 9/2026.
Abstract
Multimodal CAD generation faces a fundamental scalability challenge. Design-history methods are confined to small annotated datasets, while BRep topology is discrete and non-differentiable. Meanwhile, millions of unannotated 3D meshes remain untapped, since existing CAD methods cannot leverage them without explicit CAD annotations. We propose DreamCAD, a multimodal generative framework that bridges this gap by representing shapes as C0-continuous Bézier patches with differentiable tessellation, enabling direct point-level supervision on large-scale 3D meshes without CAD-specific annotations. The resulting surfaces are exportable as STEP files and editable in standard CAD software. We further introduce CADCap-1M, the largest CAD captioning dataset with 1M+ GPT-5-generated descriptions to advance text-to-CAD research. DreamCAD achieves state-of-the-art performance on ABC and Objaverse across text, image, and point modalities, surpassing 75% user preference. Finally, we demonstrate that DreamCAD’s accurate and compact geometric foundation enables topology recovery for production-ready CAD generation.