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

arXiv: https://arxiv.org/abs/2410.22857 · HTML: https://mlsanity.com/paper/2410.22857/

## 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 (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Image Transformer](https://mlsanity.com/paper/1802.05751/) (2018)
- [Simple Baselines for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1804.06208/) (2018)
- [A simple yet effective baseline for 3d human pose estimation](https://mlsanity.com/paper/1705.03098/) (2017)
- [DeepCAD: A Deep Generative Network for Computer-Aided Design Models](https://mlsanity.com/paper/2105.09492/) (2021)
- [TransPose: Keypoint Localization via Transformer](https://mlsanity.com/paper/2012.14214/) (2020)
- [Compositional Human Pose Regression](https://mlsanity.com/paper/1704.00159/) (2017)
- [RelTR: Relation Transformer for Scene Graph Generation](https://mlsanity.com/paper/2201.11460/) (2022)
- [Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network](https://mlsanity.com/paper/1904.05547/) (2019)
- [Computer-Aided Design as Language](https://mlsanity.com/paper/2105.02769/) (2021)
- [SketchGraphs: A Large-Scale Dataset for Modeling Relational Geometry in Computer-Aided Design](https://mlsanity.com/paper/2007.08506/) (2020)
- [SketchGen: Generating Constrained CAD Sketches](https://mlsanity.com/paper/2106.02711/) (2021)
- [Relationformer: A Unified Framework for Image-to-Graph Generation](https://mlsanity.com/paper/2203.10202/) (2022)
- [Vitruvion: A Generative Model of Parametric CAD Sketches](https://mlsanity.com/paper/2109.14124/) (2021)
- [CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attention](https://mlsanity.com/paper/2402.17678/) (2024)
- [Deep Learning for Free-Hand Sketch: A Survey](https://mlsanity.com/paper/2001.02600/) (2020)
- [Engineering Sketch Generation for Computer-Aided Design](https://mlsanity.com/paper/2104.09621/) (2021)
- [Structured Prediction of 3D Human Pose with Deep Neural Networks](https://mlsanity.com/paper/1605.05180/) (2016)
- [Unsupervised Sketch-to-Photo Synthesis](https://mlsanity.com/paper/1909.08313/) (2019)
- [CADOps-Net: Jointly Learning CAD Operation Types and Steps from Boundary-Representations](https://mlsanity.com/paper/2208.10555/) (2022)
- [SHARP Challenge 2023: Solving CAD History and pArameters Recovery from Point clouds and 3D scans. Overview, Datasets, Metrics, and Baselines](https://mlsanity.com/paper/2308.15966/) (2023)
- [BGT-Net: Bidirectional GRU Transformer Network for Scene Graph Generation](https://mlsanity.com/paper/2109.05346/) (2021)
- [SepicNet: Sharp Edges Recovery by Parametric Inference of Curves in 3D Shapes](https://mlsanity.com/paper/2304.06531/) (2023)
- [Discovering Design Concepts for CAD Sketches](https://mlsanity.com/paper/2210.14451/) (2022)
- [RelTransformer: A Transformer-Based Long-Tail Visual Relationship Recognition](https://mlsanity.com/paper/2104.11934/) (2021)
- [PICASSO: A Feed-Forward Framework for Parametric Inference of CAD Sketches via Rendering Self-Supervision](https://mlsanity.com/paper/2407.13394/) (2024)

## Built on by (most cited first, 6 of 6)

- [CAD-Assistant: Tool-Augmented VLLMs as Generic CAD Task Solvers](https://mlsanity.com/paper/2412.13810/) (2024)
- [Text-to-CAD Evaluation with CADTests](https://mlsanity.com/paper/2605.07807/) (2026)
- [Aligning Constraint Generation with Design Intent in Parametric CAD](https://mlsanity.com/paper/2504.13178/) (2025)
- [MiCADangelo: Fine-Grained Reconstruction of Constrained CAD Models from 3D Scans](https://mlsanity.com/paper/2510.23429/) (2025)
- [PHT-CAD: Efficient CAD Parametric Primitive Analysis with Progressive Hierarchical Tuning](https://mlsanity.com/paper/2503.18147/) (2025)
- [CIT-CAD: Constraint Intent Tree-based CAD Code Generation and Verification](https://mlsanity.com/paper/2609.07434/) (2026)

## 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.