HistCAD: Geometrically Constrained Parametric History-based CAD Dataset

• URL: http://arxiv.org/abs/2602.19171v1
• Date: Mon, 08 Dec 2025 05:52:14 GMT
• Title: HistCAD: Geometrically Constrained Parametric History-based CAD Dataset
• Authors: Xintong Dong, Chuanyang Li, Chuqi Han, Peng Zheng, Jiaxin Jing, Yanzhi Song, Zhouwang Yang,
• Abstract summary: HistCAD is a large-scale dataset featuring constraint-aware modeling sequences.<n>HistCAD provides a unified benchmark for advancing editable, constraint-aware, and semantically enriched generative CAD modeling.
• Score: 7.7008607520955
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Parametric computer-aided design (CAD) modeling is fundamental to industrial design, but existing datasets often lack explicit geometric constraints and fine-grained functional semantics, limiting editable, constraint-compliant generation. We present HistCAD, a large-scale dataset featuring constraint-aware modeling sequences that compactly represent procedural operations while ensuring compatibility with native CAD software, encompassing five aligned modalities: modeling sequences, multi-view renderings, STEP-format B-reps, native parametric files, and textual annotations. We develop AM\(_\text{HistCAD}\), an annotation module that extracts geometric and spatial features from modeling sequences and uses a large language model to generate complementary annotations of the modeling process, geometric structure, and functional type. Extensive evaluations demonstrate that HistCAD's explicit constraints, flattened sequence format, and multi-type annotations improve robustness, parametric editability, and accuracy in text-driven CAD generation, while industrial parts included in HistCAD further support complex real-world design scenarios. HistCAD thus provides a unified benchmark for advancing editable, constraint-aware, and semantically enriched generative CAD modeling.

Related papers

• Mamba-CAD: State Space Model For 3D Computer-Aided Design Generative Modeling [18.65998676457976]
  We introduce Mamba-CAD, a self-supervised generative modeling for complex CAD models in the industry.<n>We utilize the learned representation to guide a generative adversarial network to produce the fake representation of CAD models.<n>To train Mamba-CAD, we create a new dataset consisting of 77,078 CAD models with longer parametric CAD sequences.
  arXiv  Detail & Related papers  (2026-02-28T03:38:26Z)
• CME-CAD: Heterogeneous Collaborative Multi-Expert Reinforcement Learning for CAD Code Generation [30.08737988265254]
  Existing methods that reconstruct 3D models from sketches often produce non-editable and approximate models.<n>We propose the Heterogeneous Collaborative Multi-Expert Reinforcement Learning (CME-CAD) paradigm, a novel training paradigm for CAD code generation.<n>We introduce a two-stage training process: Multi-Expert Fine-Tuning (MEFT), and Multi-Expert Reinforcement Learning (MERL)
  arXiv  Detail & Related papers  (2025-12-29T09:37:53Z)
• 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)
• CAD-Tokenizer: Towards Text-based CAD Prototyping via Modality-Specific Tokenization [16.26305802216836]
  CAD-Tokenizer represents CAD data with modality-specific tokens using a sequence-based VQ-VAE with primitive-level pooling and constrained decoding.<n>This design produces compact, primitive-aware representations that align with CAD's structural nature.
  arXiv  Detail & Related papers  (2025-09-25T13:38:36Z)
• From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation [47.67703214044401]
  We propose CAD-RL, a multimodal Chain-of-Thought guided reinforcement learning framework for CAD modeling code generation.<n>Our method combines Cold Start with goal-driven reinforcement learning post training using three task-specific rewards.<n>Experiments demonstrate that CAD-RL achieves significant improvements in reasoning quality, output precision, and code executability.
  arXiv  Detail & Related papers  (2025-08-13T18:30:49Z)
• 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)
• 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)
• PHT-CAD: Efficient CAD Parametric Primitive Analysis with Progressive Hierarchical Tuning [52.681829043446044]
  ParaCAD comprises over 10 million annotated drawings for training and 3,000 real-world industrial drawings with complex topological structures and physical constraints for test.<n> PHT-CAD is a novel 2D PPA framework that harnesses the modality alignment and reasoning capabilities of Vision-Language Models.
  arXiv  Detail & Related papers  (2025-03-23T17:24:32Z)
• GenCAD: Image-Conditioned Computer-Aided Design Generation with Transformer-Based Contrastive Representation and Diffusion Priors [3.796768352477804]
  The creation of manufacturable and editable 3D shapes through Computer-Aided Design (CAD) remains a highly manual and time-consuming task.<n>This paper introduces GenCAD, a generative model that employs autoregressive transformers with a contrastive learning framework and latent diffusion models to transform image inputs into parametric CAD command sequences.
  arXiv  Detail & Related papers  (2024-09-08T23:49:11Z)
• 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)
• Geometric Deep Learning for Computer-Aided Design: A Survey [76.3325417461511]
  Geometric Deep Learning techniques have become a transformative force in the field of Computer-Aided Design.<n>The ability to process the CAD designs represented by geometric data and to analyze their encoded features enables the identification of similarities.<n>This survey offers a comprehensive overview of learning-based methods in computer-aided design across various categories.
  arXiv  Detail & Related papers  (2024-02-27T17:11:35Z)
• HybridSDF: Combining Free Form Shapes and Geometric Primitives for effective Shape Manipulation [58.411259332760935]
  Deep-learning based 3D surface modeling has opened new shape design avenues. These advances have not yet been accepted by the CAD community because they cannot be integrated into engineering. We propose a novel approach to effectively combining geometric primitives and free-form surfaces represented by implicit surfaces for accurate modeling.
  arXiv  Detail & Related papers  (2021-09-22T14:45:19Z)

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.