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

• URL: http://arxiv.org/abs/2603.05607v1
• Date: Thu, 05 Mar 2026 19:04:07 GMT
• Title: DreamCAD: Scaling Multi-modal CAD Generation using Differentiable Parametric Surfaces
• Abstract summary: We propose DreamCAD, a multi-modal generative framework that directly produces editable BReps from point-level supervision.<n>DreamCAD represents each BRep as a set of parametric patches and uses a differentiable tessellation method to generate meshes.<n>DreamCAD achieves state-of-the-art performance on ABC and averse benchmarks across text, image, and point modalities.
• Score: 67.45867367326105
• License: http://creativecommons.org/licenses/by/4.0/
• 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., 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.

Related papers

• Autoregressive B-Rep Shape Generation with Parametric Surfaces [83.03418080213359]
  ParaCAD is an autoregressive framework for point-cloud-conditioned B-Rep generation.<n>Our model first generates parametric surfaces with constrained UV domains, and then constructs a valid B-Rep by globally intersecting these surfaces.<n>Extensive experiments demonstrate that ParaCAD produces accurate B-Reps with faithful point-cloud alignment.
  arXiv  Detail & Related papers  (2026-07-19T06:14:50Z)
• GuideCAD: A Lightweight Multimodal Framework for 3D CAD Model Generation via Prefix Embedding [6.339931887475017]
  We propose GuideCAD, which leverages semantically rich visual-textual representations to generate 3D CAD models.<n>GuideCAD uses a mapping network that converts image embeddings into prefix embeddings, enabling a pretrained large language model to integrate visual and textual information.<n>Our experimental results show that GuideCAD generates comparably high-quality 3D CAD models while using approximately four times fewer parameters and achieving twice the training efficiency compared to fine-tuning approaches.
  arXiv  Detail & Related papers  (2026-06-05T08:14:28Z)
• BRepCLIP: Contrastive Multimodal Pretraining on BRep Primitives for CAD Understanding [22.960026011165706]
  We introduce BRepCLIP, the first framework to align BRep geometry with language and image embeddings.<n>A transformer encoder aggregates these tokens into a global BRep embedding, aligned with CLIP's text and image encoders.<n>BRepCLIP generates more discriminative and semantically grounded embeddings than existing point-based alternatives.
  arXiv  Detail & Related papers  (2026-06-03T23:41:23Z)
• CADFS: A Big CAD Program Dataset and Framework for Computer-Aided Design with Large Language Models [80.47087401394882]
  We introduce CADFS, a data-centric framework that enables large vision-language models to generate complex CAD design histories.<n>We construct a dataset of 450k real-world CAD models spanning 15 modeling operations.<n>Fine-tuning a VLM on this representation yields state-of-the-art results in text-conditioned CAD generation and image-based reconstruction.
  arXiv  Detail & Related papers  (2026-05-03T15:12:36Z)
• CADKnitter: Compositional CAD Generation from Text and Geometry Guidance [8.644079160190175]
  We propose CADKnitter, a compositional CAD generation framework with a geometry-guided diffusion sampling strategy.<n>CADKnitter is able to generate a complementary CAD part that follows both the geometric constraints of the given CAD model and the semantic constraints of the desired design text prompt.<n>We also curate a dataset, so-called KnitCAD, containing over 310,000 samples of CAD models, along with textual prompts and assembly metadata.
  arXiv  Detail & Related papers  (2025-12-12T01:06:38Z)
• CADmium: Fine-Tuning Code Language Models for Text-Driven Sequential CAD Design [14.874524630759332]
  We introduce a new large-scale pipeline of more than 170k CAD models annotated with human-like descriptions.<n>Our experiments and ablation studies on both synthetic and human-annotated data demonstrate that CADmium is able to automate CAD design.
  arXiv  Detail & Related papers  (2025-07-13T21:11:53Z)
• CAD-Coder:Text-Guided CAD Files Code Generation [2.6807043000799524]
  Computer-aided design (CAD) is a way to digitally create 2D drawings and 3D models of real-world products.<n>We propose CAD-Coder, a framework that transforms natural language instructions into CAD script codes to generate human-editable CAD files.
  arXiv  Detail & Related papers  (2025-05-13T15:45:46Z)
• CADCrafter: Generating Computer-Aided Design Models from Unconstrained Images [69.7768227804928]
  CADCrafter is an image-to-parametric CAD model generation framework that trains solely on synthetic textureless CAD data.<n>We introduce a geometry encoder to accurately capture diverse geometric features.<n>Our approach can robustly handle real unconstrained CAD images, and even generalize to unseen general objects.
  arXiv  Detail & Related papers  (2025-04-07T06:01:35Z)
• CAD-Recode: Reverse Engineering CAD Code from Point Clouds [12.864274930732055]
  3D CAD reverse engineering consists of reconstructing the sketch and CAD operation sequences from 3D representations such as point clouds.<n>The proposed CAD-Recode translates a point cloud into Python code that, when executed, reconstructs the CAD model.<n>We show that our CAD Python code output is interpretable by off-the-shelf LLMs, enabling CAD editing and CAD-specific question answering from point clouds.
  arXiv  Detail & Related papers  (2024-12-18T16:55:42Z)
• CADSpotting: Robust Panoptic Symbol Spotting on Large-Scale CAD Drawings [56.05238657033198]
  We introduce CADSpotting, an effective method for panoptic symbol spotting in large-scale architectural CAD drawings.<n>We also propose a novel Sliding Window Aggregation (SWA) technique that combines weighted voting and Non-Maximum Suppression (NMS)<n>Experiments on FloorPlanCAD and LS-CAD demonstrate that CADSpotting significantly outperforms existing methods.
  arXiv  Detail & Related papers  (2024-12-10T10:22:17Z)
• PS-CAD: Local Geometry Guidance via Prompting and Selection for CAD Reconstruction [86.726941702182]
  We introduce geometric guidance into the reconstruction network PS-CAD. We provide the geometry of surfaces where the current reconstruction differs from the complete model as a point cloud. Second, we use geometric analysis to extract a set of planar prompts, that correspond to candidate surfaces.
  arXiv  Detail & Related papers  (2024-05-24T03:43:55Z)
• SECAD-Net: Self-Supervised CAD Reconstruction by Learning Sketch-Extrude Operations [21.000539206470897]
  SECAD-Net is an end-to-end neural network aimed at reconstructing compact and easy-to-edit CAD models. We show superiority over state-of-the-art alternatives including the closely related method for supervised CAD reconstruction.
  arXiv  Detail & Related papers  (2023-03-19T09:26:03Z)
• Patch2CAD: Patchwise Embedding Learning for In-the-Wild Shape Retrieval from a Single Image [58.953160501596805]
  We propose a novel approach towards constructing a joint embedding space between 2D images and 3D CAD models in a patch-wise fashion. Our approach is more robust than state of the art in real-world scenarios without any exact CAD matches.
  arXiv  Detail & Related papers  (2021-08-20T20:58:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.