mlsanityData to 14 Oct 2026

DAVINCI: A Single-Stage Architecture for Constrained CAD Sketch Inference

arXiv 2410.22857 ↗First posted 30 Oct 2024cs.CV cs.HCcited by 6

Not on the map. Why?

Abstract (arXiv)

This work presents DAVINCI, a unified architecture for single-stage Computer-Aided Design (CAD) sketch parameterization and constraint inference directly from raster sketch images. By jointly learning both outputs, DAVINCI minimizes error accumulation and enhances the performance of constrained CAD sketch inference. Notably, DAVINCI achieves state-of-the-art results on the large-scale SketchGraphs dataset, demonstrating effectiveness on both precise and hand-drawn raster CAD sketches. To reduce DAVINCI's reliance on large-scale annotated datasets, we explore the efficacy of CAD sketch augmentations. We introduce Constraint-Preserving Transformations (CPTs), i.e. random permutations of the parametric primitives of a CAD sketch that preserve its constraints. This data augmentation strategy allows DAVINCI to achieve reasonable performance when trained with only 0.1% of the SketchGraphs dataset. Furthermore, this work contributes a new version of SketchGraphs, augmented with CPTs. The newly introduced CPTSketchGraphs dataset includes 80 million CPT-augmented sketches, thus providing a rich resource for future research in the CAD sketch domain.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 31 of its 46 references that are in the map. First posted on arXiv 30 Oct 2024.

Builds on

31 of 46 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2020End-to-End Object Detection with Transformerscited by 7,414
  5. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  6. 2018Image Transformercited by 772
  7. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  8. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  9. 2021DeepCAD: A Deep Generative Network for Computer-Aided Design Modelscited by 271
  10. 2020TransPose: Keypoint Localization via Transformercited by 126
  11. 2017Compositional Human Pose Regressioncited by 124
  12. 2022RelTR: Relation Transformer for Scene Graph Generationcited by 96
19 more
  1. 2019Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Networkcited by 92
  2. 2021Computer-Aided Design as Languagecited by 82
  3. 2020SketchGraphs: A Large-Scale Dataset for Modeling Relational Geometry in Computer-Aided Designcited by 72
  4. 2021SketchGen: Generating Constrained CAD Sketchescited by 68
  5. 2022Relationformer: A Unified Framework for Image-to-Graph Generationcited by 67
  6. 2021Vitruvion: A Generative Model of Parametric CAD Sketchescited by 66
  7. 2024CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attentioncited by 64
  8. 2020Deep Learning for Free-Hand Sketch: A Surveycited by 59
  9. 2021Engineering Sketch Generation for Computer-Aided Designcited by 49
  10. 2016Structured Prediction of 3D Human Pose with Deep Neural Networkscited by 43
  11. 2019Unsupervised Sketch-to-Photo Synthesiscited by 38
  12. 2022CADOps-Net: Jointly Learning CAD Operation Types and Steps from Boundary-Representationscited by 31
  13. 2023SHARP Challenge 2023: Solving CAD History and pArameters Recovery from Point clouds and 3D scans. Overview, Datasets, Metrics, and Baselinescited by 19
  14. 2021BGT-Net: Bidirectional GRU Transformer Network for Scene Graph Generationcited by 18
  15. 2023SepicNet: Sharp Edges Recovery by Parametric Inference of Curves in 3D Shapescited by 13
  16. 2022Discovering Design Concepts for CAD Sketchescited by 10
  17. 2021RelTransformer: A Transformer-Based Long-Tail Visual Relationship Recognitioncited by 9
  18. 2024PICASSO: A Feed-Forward Framework for Parametric Inference of CAD Sketches via Rendering Self-Supervisioncited by 9
  19. 2019Sketch-Specific Data Augmentation for Freehand Sketch Recognitioncited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 2.

6 papers.

  1. 2024CAD-Assistant: Tool-Augmented VLLMs as Generic CAD Task Solverscited by 40
  2. 2026Text-to-CAD Evaluation with CADTestscited by 10
  3. 2025Aligning Constraint Generation with Design Intent in Parametric CADcited by 8
  4. 2025MiCADangelo: Fine-Grained Reconstruction of Constrained CAD Models from 3D Scanscited by 5
  5. 2025PHT-CAD: Efficient CAD Parametric Primitive Analysis with Progressive Hierarchical Tuningcited by 3
  6. 2026CIT-CAD: Constraint Intent Tree-based CAD Code Generation and Verificationcited by 0