DreamCAD：基于可微分参数曲面的多模态CAD生成规模化应用

摘要

计算机辅助设计（CAD）依赖于结构化且可编辑的几何表示，然而现有生成方法受限于带有显式设计历史或边界表示（BRep）标注的小型标注数据集。与此同时，数百万未标注的三维网格模型尚未被开发利用，限制了可扩展CAD生成技术的发展。为此，我们提出DreamCAD——一种多模态生成框架，能够通过点级监督直接生成可编辑的BRep模型，无需CAD专用标注。DreamCAD将每个BRep表示为参数化曲面片（如贝塞尔曲面）的集合，并采用可微分细分方法生成网格。该技术实现了在三维数据集上的大规模训练，同时能重建具有连通性的可编辑曲面。此外，我们推出了迄今最大的CAD标注数据集CADCap-1M，其中包含使用GPT-5生成的100余万条描述文本，以推进文本到CAD的研究。DreamCAD在ABC和Objaverse基准测试中，针对文本、图像和点云三种模态均实现了最先进的性能表现，在提升几何保真度的同时获得了超过75%的用户偏好度。相关代码和数据集将公开提供。

English

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., Bézier 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.

DreamCAD：基于可微分参数曲面的多模态CAD生成规模化应用

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

摘要

Support