Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.05607 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917316447436800 |
|---|---|
| author | Khan, Mohammad Sadil Usama, Muhammad Potamias, Rolandos Alexandros Stricker, Didier Afzal, Muhammad Zeshan Deng, Jiankang Elezi, Ismail |
| author_facet | Khan, Mohammad Sadil Usama, Muhammad Potamias, Rolandos Alexandros Stricker, Didier Afzal, Muhammad Zeshan Deng, Jiankang Elezi, Ismail |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_05607 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DreamCAD: Scaling Multi-modal CAD Generation using Differentiable Parametric Surfaces Khan, Mohammad Sadil Usama, Muhammad Potamias, Rolandos Alexandros Stricker, Didier Afzal, Muhammad Zeshan Deng, Jiankang Elezi, Ismail Computer Vision and Pattern Recognition Artificial Intelligence 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. |
| title | DreamCAD: Scaling Multi-modal CAD Generation using Differentiable Parametric Surfaces |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2603.05607 |