microsoft/YOLaT-VectorGraphicsRecognition

Source Code of NeurIPS21 and T-PAMI24 paper: Recognizing Vector Graphics without Rasterization

45
/ 100
Emerging

This project helps engineers and designers automatically identify elements within technical drawings like floor plans and diagrams. Instead of converting these vector graphics into blurry pixel images, it directly analyzes the underlying structural data. This allows for precise recognition of features and components, taking in the raw vector graphic files and outputting recognized objects and their characteristics.

101 stars. No commits in the last 6 months.

Use this if you need to precisely understand and extract information from vector-based technical drawings or schematics without losing detail to image rasterization.

Not ideal if your primary input is rasterized images (like JPEGs or PNGs) rather than native vector graphic files.

CAD technical-drawing-analysis architecture engineering-diagrams graphic-recognition
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

101

Forks

18

Language

Python

License

MIT

Last pushed

Sep 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/microsoft/YOLaT-VectorGraphicsRecognition"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.