# Deep Vectorization of Technical Drawings

arXiv: https://arxiv.org/abs/2003.05471 · HTML: https://mlsanity.com/paper/2003.05471/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Mar 2020.

## Built on by (most cited first, 23 of 23)

- [Im2Vec: Synthesizing Vector Graphics without Vector Supervision](https://mlsanity.com/paper/2102.02798/) (2021)
- [Computer-Aided Design as Language](https://mlsanity.com/paper/2105.02769/) (2021)
- [Towards Layer-wise Image Vectorization](https://mlsanity.com/paper/2206.04655/) (2022)
- [Engineering Sketch Generation for Computer-Aided Design](https://mlsanity.com/paper/2104.09621/) (2021)
- [LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer](https://mlsanity.com/paper/2502.01105/) (2025)
- [De-rendering Stylized Texts](https://mlsanity.com/paper/2110.01890/) (2021)
- [Layered Image Vectorization via Semantic Simplification](https://mlsanity.com/paper/2406.05404/) (2024)
- [Segmentation-guided Layer-wise Image Vectorization with Gradient Fills](https://mlsanity.com/paper/2408.15741/) (2024)
- [PICASSO: A Feed-Forward Framework for Parametric Inference of CAD Sketches via Rendering Self-Supervision](https://mlsanity.com/paper/2407.13394/) (2024)
- [Image Vectorization: a Review](https://mlsanity.com/paper/2306.06441/) (2023)
- [SAMVG: A Multi-stage Image Vectorization Model with the Segment-Anything Model](https://mlsanity.com/paper/2311.05276/) (2023)
- [SketchGPT: Autoregressive Modeling for Sketch Generation and Recognition](https://mlsanity.com/paper/2405.03099/) (2024)
- [3D Parametric Wireframe Extraction Based on Distance Fields](https://mlsanity.com/paper/2107.06165/) (2021)
- [Image Vectorization with Depth: convexified shape layers with depth ordering](https://mlsanity.com/paper/2409.06648/) (2024)
- [BG-Triangle: B'ezier Gaussian Triangle for 3D Vectorization and Rendering](https://mlsanity.com/paper/2503.13961/) (2025)
- [SVG-Net: An SVG-based Trajectory Prediction Model](https://mlsanity.com/paper/2110.03706/) (2021)
- [MARVEL: Raster Manga Vectorization via Primitive-wise Deep Reinforcement Learning](https://mlsanity.com/paper/2110.04830/) (2021)
- [Historical Astronomical Diagrams Decomposition in Geometric Primitives](https://mlsanity.com/paper/2403.08721/) (2024)
- [PPI-NET: End-to-End Parametric Primitive Inference](https://mlsanity.com/paper/2308.01521/) (2023)
- [Structure-aware Contrastive Learning for Diagram Understanding of Multimodal Models](https://mlsanity.com/paper/2509.01959/) (2025)
- [AnchorFlow: Learning Anchor Placement for Faithful and Editable SVG Reconstruction](https://mlsanity.com/paper/2605.19551/) (2026)
- [Robust reconstructions by multi-scale/irregular tangential covering](https://mlsanity.com/paper/2111.05688/) (2021)
- [Curve-based Neural Style Transfer](https://mlsanity.com/paper/2401.08579/) (2023)

## Abstract (arXiv)

We present a new method for vectorization of technical line drawings, such as floor plans, architectural drawings, and 2D CAD images. Our method includes (1) a deep learning-based cleaning stage to eliminate the background and imperfections in the image and fill in missing parts, (2) a transformer-based network to estimate vector primitives, and (3) optimization procedure to obtain the final primitive configurations. We train the networks on synthetic data, renderings of vector line drawings, and manually vectorized scans of line drawings. Our method quantitatively and qualitatively outperforms a number of existing techniques on a collection of representative technical drawings.