DreamCAD: Scaling Multi-modal CAD Generation using Differentiable Parametric Surfaces

TL;DR

DreamCAD introduces a scalable, multi-modal framework for generating editable CAD models directly from point data, leveraging differentiable parametric surfaces and large-scale datasets to improve fidelity and user preference.

Contribution

It presents DreamCAD, a novel method for generating editable boundary representations from point supervision without CAD-specific labels, and introduces the large CADCap-1M dataset for text-to-CAD research.

Findings

Achieves state-of-the-art results on ABC and Objaverse benchmarks.

Improves geometric fidelity and surpasses 75% user preference.

Enables large-scale training on unannotated 3D datasets.

Abstract

Computer-Aided Design (CAD) relies on structured and editable geometric representations, yet existing generative methods are constrained by small annotated datasets with explicit design histories or boundary representation (BRep) labels. Meanwhile, millions of unannotated 3D meshes remain untapped, limiting progress in scalable CAD generation. To address this, we propose DreamCAD, a multi-modal generative framework that directly produces editable BReps from point-level supervision, without CAD-specific annotations. DreamCAD represents each BRep as a set of parametric patches (e.g., B\'ezier surfaces) and uses a differentiable tessellation method to generate meshes. This enables large-scale training on 3D datasets while reconstructing connected and editable surfaces. Furthermore, we introduce CADCap-1M, the largest CAD captioning dataset to date, with 1M+ descriptions generated using GPT-5 for advancing text-to-CAD research. DreamCAD achieves state-of-the-art performance on ABC and Objaverse benchmarks across text, image, and point modalities, improving geometric fidelity and surpassing 75% user preference. Code and dataset will be publicly available.