mlsanityData to 7 Oct 2026

Deep Vectorization of Technical Drawings

arXiv 2003.05471 ↗First posted 11 Mar 2020cs.CV cs.GRcited by 23

Not on the map. Why?

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.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 1; 2023: 4; 2024: 6; 2025: 3; 2026: 1.

23 papers.

Sort:

By area:

  1. 2021Im2Vec: Synthesizing Vector Graphics without Vector Supervisioncited by 114
  2. 2021Computer-Aided Design as Languagecited by 82
  3. 2022Towards Layer-wise Image Vectorizationcited by 77
  4. 2021Engineering Sketch Generation for Computer-Aided Designcited by 49
  5. 2025LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformercited by 43
  6. 2021De-rendering Stylized Textscited by 24
  7. 2024Layered Image Vectorization via Semantic Simplificationcited by 18
  8. 2024Segmentation-guided Layer-wise Image Vectorization with Gradient Fillscited by 11
  9. 2024PICASSO: A Feed-Forward Framework for Parametric Inference of CAD Sketches via Rendering Self-Supervisioncited by 9
  10. 2023Image Vectorization: a Reviewcited by 7
  11. 2023SAMVG: A Multi-stage Image Vectorization Model with the Segment-Anything Modelcited by 6
  12. 2024SketchGPT: Autoregressive Modeling for Sketch Generation and Recognitioncited by 5
11 more
  1. 20213D Parametric Wireframe Extraction Based on Distance Fieldscited by 4
  2. 2024Image Vectorization with Depth: convexified shape layers with depth orderingcited by 4
  3. 2025BG-Triangle: B'ezier Gaussian Triangle for 3D Vectorization and Renderingcited by 4
  4. 2021SVG-Net: An SVG-based Trajectory Prediction Modelcited by 2
  5. 2021MARVEL: Raster Manga Vectorization via Primitive-wise Deep Reinforcement Learningcited by 2
  6. 2024Historical Astronomical Diagrams Decomposition in Geometric Primitivescited by 2
  7. 2023PPI-NET: End-to-End Parametric Primitive Inferencecited by 1
  8. 2025Structure-aware Contrastive Learning for Diagram Understanding of Multimodal Modelscited by 1
  9. 2026AnchorFlow: Learning Anchor Placement for Faithful and Editable SVG Reconstructioncited by 1
  10. 2021Robust reconstructions by multi-scale/irregular tangential coveringcited by 0
  11. 2023Curve-based Neural Style Transfercited by 0