mlsanityData to 7 Oct 2026

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

arXiv 2603.05607 ↗First posted 5 Mar 2026cs.CV cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 46 of its 75 references that are in the map. First posted on arXiv 5 Mar 2026.

Builds on

46 of 75 references.

References · 46

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  2. 2025Qwen3 Technical Reportcited by 8,195
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  4. 2022Flow Matching for Generative Modelingcited by 5,426
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  6. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  7. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  8. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  9. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  10. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 742
  11. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 444
  12. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 376
34 more
  1. 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 360
  2. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 342
  3. 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 339
  4. 20203D-FUTURE: 3D Furniture shape with TextUREcited by 306
  5. 2021DeepCAD: A Deep Generative Network for Computer-Aided Design Modelscited by 266
  6. 2023Scalable 3D Captioning with Pretrained Modelscited by 201
  7. 2023Habitat Synthetic Scenes Dataset (HSSD-200): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigationcited by 162
  8. 2024GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generationcited by 151
  9. 2021Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Biascited by 115
  10. 2024BrepGen: A B-rep Generative Diffusion Model with Structured Latent Geometrycited by 101
  11. 2020ParSeNet: A Parametric Surface Fitting Network for 3D Point Cloudscited by 96
  12. 2021BRepNet: A topological message passing system for solid modelscited by 92
  13. 2025Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assetscited by 85
  14. 2024Meta 3D AssetGen: Text-to-Mesh Generation with High-Quality Geometry, Texture, and PBR Materialscited by 66
  15. 2025CAD-Llama: Leveraging Large Language Models for Computer-Aided Design Parametric 3D Model Generationcited by 65
  16. 2024CAD-Recode: Reverse Engineering CAD Code from Point Cloudscited by 63
  17. 2024CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attentioncited by 62
  18. 2021Point2Cyl: Reverse Engineering 3D Objects from Point Clouds to Extrusion Cylinderscited by 59
  19. 2024CAD-GPT: Synthesising CAD Construction Sequence with Spatial Reasoning-Enhanced Multimodal LLMscited by 52
  20. 2023SECAD-Net: Self-Supervised CAD Reconstruction by Learning Sketch-Extrude Operationscited by 46
  21. 2025Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Modelscited by 43
  22. 2025Text-to-CadQuery: A New Paradigm for CAD Generation with Scalable Large Model Capabilitiescited by 43
  23. 2022ExtrudeNet: Unsupervised Inverse Sketch-and-Extrude for Shape Parsingcited by 38
  24. 2024Img2CAD: Reverse Engineering 3D CAD Models from Images through VLM-Assisted Conditional Factorizationcited by 34
  25. 2023Point2CAD: Reverse Engineering CAD Models from 3D Point Cloudscited by 33
  26. 2024TransCAD: A Hierarchical Transformer for CAD Sequence Inference from Point Cloudscited by 29
  27. 2025CADmium: Fine-Tuning Code Language Models for Text-Driven Sequential CAD Designcited by 23
  28. 2025DTGBrepGen: A Novel B-rep Generative Model through Decoupling Topology and Geometrycited by 20
  29. 2023SHARP Challenge 2023: Solving CAD History and pArameters Recovery from Point clouds and 3D scans. Overview, Datasets, Metrics, and Baselinescited by 19
  30. 2024MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creationcited by 7
  31. 2024Intelligent CAD 2.0cited by 5
  32. 20243D Representation Methods: A Surveycited by 5
  33. 2025NURBGen: High-Fidelity Text-to-CAD Generation through LLM-Driven NURBS Modelingcited by 5
  34. 2024BRep Boundary and Junction Detection for CAD Reverse Engineeringcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026BRepCLIP: Contrastive Multimodal Pretraining on BRep Primitives for CAD Understandingcited by 1