Draw it like Euclid: Teaching transformer models to generate CAD profiles using ruler and compass construction steps

• URL: http://arxiv.org/abs/2601.09428v1
• Date: Wed, 14 Jan 2026 12:17:34 GMT
• Title: Draw it like Euclid: Teaching transformer models to generate CAD profiles using ruler and compass construction steps
• Abstract summary: We introduce a new method of generating Computer Aided Design (CAD) profiles via a sequence of simple geometric constructions.<n>These sequences start with geometry provided by a designer and build up the points and curves of the final profile step by step.
• Score: 14.337843963490071
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: We introduce a new method of generating Computer Aided Design (CAD) profiles via a sequence of simple geometric constructions including curve offsetting, rotations and intersections. These sequences start with geometry provided by a designer and build up the points and curves of the final profile step by step. We demonstrate that adding construction steps between the designer's input geometry and the final profile improves generation quality in a similar way to the introduction of a chain of thought in language models. Similar to the constraints in a parametric CAD model, the construction sequences reduce the degrees of freedom in the modeled shape to a small set of parameter values which can be adjusted by the designer, allowing parametric editing with the constructed geometry evaluated to floating point precision. In addition we show that applying reinforcement learning to the construction sequences gives further improvements over a wide range of metrics, including some which were not explicitly optimized.

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)
• HierCAD: Hierarchical Text-to-CAD Design via Structure Alignment and Parameter Grounding [45.92807927638433]
  HierCAD is a hierarchical text-to-CAD framework that improves both structural reasoning and parameter prediction.<n>Our code is available at https://github.com/Collab-Gen/HierCAD.
  arXiv  Detail & Related papers  (2026-07-13T10:00:53Z)
• Pointer-CAD v2: Plan-Then-Construct CAD Generation with Dimension-Aware Parametric Precision [30.320445641359466]
  Computer-aided design (CAD) plays a fundamental role in modern manufacturing by providing the high precision required for industrial production.<n>Recent large language model based approaches formulate CAD generation as a sequence prediction problem and have achieved promising results.<n>Small numerical deviations that are negligible at the shape-level may still violate industrial tolerance requirements.<n>We present Pointer-CAD v2, which directly predicts continuous values, bypassing the need for quantized numerical parameters and thereby eliminating quantization errors.
  arXiv  Detail & Related papers  (2026-06-28T09:40:20Z)
• CADFit: Precise Mesh-to-CAD Program Generation with Hybrid Optimization [3.8824066002669855]
  We introduce CADFit, a hybrid optimization-based CAD reconstruction framework.<n>Our approach is distinguished by formulating reconstruction as an IoU-driven optimization over structured CAD programs.<n> Experiments on multiple CAD benchmarks show that CADFit outperforms state-of-the-art mesh-to-CAD methods.
  arXiv  Detail & Related papers  (2026-05-02T00:19:52Z)
• DreamCAD: Scaling Multi-modal CAD Generation using Differentiable Parametric Surfaces [67.45867367326105]
  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.
  arXiv  Detail & Related papers  (2026-03-05T19:04:07Z)
• Point or Line? Using Line-based Representation for Panoptic Symbol Spotting in CAD Drawings [67.5600169375126]
  We study the task of panoptic symbol spotting in computer-aided design (CAD) drawings composed of vector graphical primitives.<n>Existing methods typically rely on imageization, graph construction, or point-based representation.<n>We propose VecFormer, a novel method that addresses these challenges through line-based representation of primitives.
  arXiv  Detail & Related papers  (2025-05-29T12:33:11Z)
• Aligning Constraint Generation with Design Intent in Parametric CAD [14.67058586198014]
  Engineering sketches consist of geometric primitives connected by constraints.<n>For a design to be easily editable, the constraints must effectively capture design intent.<n>A critical first step towards aligning generative CAD models is to generate constraints which fully-constrain all geometric primitives.
  arXiv  Detail & Related papers  (2025-04-17T17:59:54Z)
• 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)
• Automatic Parameterization for Aerodynamic Shape Optimization via Deep Geometric Learning [60.69217130006758]
  We propose two deep learning models that fully automate shape parameterization for aerodynamic shape optimization. Both models are optimized to parameterize via deep geometric learning to embed human prior knowledge into learned geometric patterns. We perform shape optimization experiments on 2D airfoils and discuss the applicable scenarios for the two models.
  arXiv  Detail & Related papers  (2023-05-03T13:45:40Z)
• Reconstructing editable prismatic CAD from rounded voxel models [16.03976415868563]
  We introduce a novel neural network architecture to solve this challenging task. Our method reconstructs the input geometry in the voxel space by decomposing the shape. During inference, we obtain the CAD data by first searching a database of 2D constrained sketches.
  arXiv  Detail & Related papers  (2022-09-02T16:44:10Z)
• Vitruvion: A Generative Model of Parametric CAD Sketches [22.65229769427499]
  We present an approach to generative modeling of parametric CAD sketches. Our model, trained on real-world designs from the SketchGraphs dataset, autoregressively synthesizes sketches as sequences of primitives. We condition the model on various contexts, including partial sketches (primers) and images of hand-drawn sketches.
  arXiv  Detail & Related papers  (2021-09-29T01:02:30Z)
• DSG-Net: Learning Disentangled Structure and Geometry for 3D Shape Generation [98.96086261213578]
  We introduce DSG-Net, a deep neural network that learns a disentangled structured and geometric mesh representation for 3D shapes. This supports a range of novel shape generation applications with disentangled control, such as of structure (geometry) while keeping geometry (structure) unchanged. Our method not only supports controllable generation applications but also produces high-quality synthesized shapes, outperforming state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-08-12T17:06:51Z)
• SketchGraphs: A Large-Scale Dataset for Modeling Relational Geometry in Computer-Aided Design [18.041056084458567]
  Parametric computer-aided design (CAD) is the dominant paradigm in mechanical engineering for physical design. SketchGraphs is a collection of 15 million sketches extracted from real-world CAD models coupled with an open-source data processing pipeline.
  arXiv  Detail & Related papers  (2020-07-16T17:56:25Z)
• Quantization in Relative Gradient Angle Domain For Building Polygon Estimation [88.80146152060888]
  CNN approaches often generate imprecise building morphologies including noisy edges and round corners. We propose a module that uses prior knowledge of building corners to create angular and concise building polygons from CNN segmentation outputs. Experimental results demonstrate that our method refines CNN output from a rounded approximation to a more clear-cut angular shape of the building footprint.
  arXiv  Detail & Related papers  (2020-07-10T21:33:06Z)
• CoSE: Compositional Stroke Embeddings [52.529172734044664]
  We present a generative model for complex free-form structures such as stroke-based drawing tasks. Our approach is suitable for interactive use cases such as auto-completing diagrams.
  arXiv  Detail & Related papers  (2020-06-17T15:22:54Z)

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.