# TerraLab

> AI plugins for QGIS. TerraLab builds AI-powered QGIS plugins that automate raster digitization and bring generative AI image editing into GIS workflows. Based at Station F, Paris.

TerraLab is the AI plugin stack for QGIS. Our two flagship products are QGIS plugins: AI Segmentation (free, open source) for automated raster-to-vector digitization, and AI Edit (paid) for natural-language image editing of satellite, drone, and aerial imagery. We also deliver custom 3D digital twin solutions for territorial analysis.

## Products

- [AI Segmentation](https://terra-lab.ai/ai-segmentation): Free, open-source QGIS plugin for automated raster digitization. Point-and-click extraction of buildings, roads, and vegetation as vector polygons. 33,000+ downloads, 4.7/5 over 260 votes on the QGIS plugin marketplace.
- [AI Edit](https://terra-lab.ai/ai-edit): Paid QGIS plugin (19 EUR/month, 5 free generations) powered by Google Nano Banana 2 for natural-language editing of satellite, drone, and aerial imagery. Outputs georeferenced GeoTIFFs at up to 4K resolution. 4.8/5 over 110 votes on the QGIS plugin marketplace.
- [Digital Twin solutions](https://terra-lab.ai/digital-twin): Custom 3D digital twins for territorial analysis, terrain modeling, vegetation rendering, and before/after spatial comparison.

## QGIS plugin marketplace

- [AI Segmentation on plugins.qgis.org](https://plugins.qgis.org/plugins/AI_Segmentation/): Canonical download page, free and open source.
- [AI Edit on plugins.qgis.org](https://plugins.qgis.org/plugins/AI_Edit/): Canonical download page.

## About TerraLab

- [About TerraLab](https://terra-lab.ai/about): Team, mission, manifesto, and backers (Station F, NVIDIA Inception, 42 Incubateur, 42 Startup Club).
- [Blog](https://terra-lab.ai/blog): Engineering and research write-ups on geospatial AI, digital twins, and QGIS workflows.

## Team

- Yvann Barbot (Co-founder): 42 Paris alumnus, ex-AI Engineer at Mago (Station F), 1,200+ GitHub stars. [LinkedIn](https://www.linkedin.com/in/yvann-barbot/) - [GitHub](https://github.com/yvann-ba)
- Lilien Auger (Co-founder): 42 Paris alumnus, ex-AI Engineer at Publicis, 500+ GitHub stars. [LinkedIn](https://www.linkedin.com/in/lilien-auger/)
- Stéphane Barbot (Advisor): 25+ years in real-time 3D and geospatial engines. Past: ADAS at Magneti Marelli, PSA, BMW, Maserati. [LinkedIn](https://www.linkedin.com/in/stephane-barbot/)
- Valérie Barbot (Advisor): 20 years in GIS. [LinkedIn](https://www.linkedin.com/in/valerie-barbot/)

## Articles

- [AI Edit for QGIS: The Complete Guide](https://terra-lab.ai/blog/ai-edit-complete-guide): Full walkthrough of the AI Edit plugin: first edit, prompt library, Markup (draw to guide the edit), Vectorize (trace AI results into vector polygons), reference images and layers (feed the model aligned context like OSM footprints or a DEM), and the 1K/2K/4K resolution tiers. Published 2026-06-19 by Yvann Barbot.
- [Building a Digital Twin of Quebec's Forests from 115,000 Orthophotos](https://terra-lab.ai/blog/quebec-forest-digital-twin): Case study on processing 115,000 Quebec MRNF orthophoto tiles across 10 MTM zones, including the color calibration defect we found in the 2015 campaigns (B/R ratio 1.30 vs ~0.88 normal). Published 2026-04-07 by Stéphane Barbot.

## Professional services

- Custom AI solutions for GIS workflows
- Geospatial machine learning implementation
- Spatial data analysis and optimization
- GIS workflow automation
- Contact: [Calendly with Lilien](https://calendly.com/lilienauger/30min) or contact@terra-lab.ai

## Location

Station F, 5 Parvis Alan Turing, 75013 Paris, France

## Optional

- [Legal notice](https://terra-lab.ai/legal-notice)
- [Privacy policy](https://terra-lab.ai/privacy-policy)
- [Terms of use](https://terra-lab.ai/terms-of-use)
- [LinkedIn (company)](https://www.linkedin.com/company/terralab-3d)
- [YouTube channel](https://youtube.com/@terra-lab)
- [GitHub organization (TerraLabAI)](https://github.com/TerraLabAI)
- [llms-full.txt](https://terra-lab.ai/llms-full.txt): Single-file concatenation of all key pages in markdown for AI ingestion.