README.md

---
library_name: ultralytics
license: agpl-3.0
pipeline_tag: image-segmentation
---

# Delineate Anything v2: A Global Foundation Model for Field Delineation

<a href='https://lavreniuk.github.io/Delineate-Anything/'><img src='https://img.shields.io/badge/Project-Page-Green'></a>
<a href='https://github.com/Lavreniuk/Delineate-Anything'><img src='https://img.shields.io/badge/Code-GitHub-blue'></a>
<a href='https://arxiv.org/abs/2504.02534'><img src='https://img.shields.io/badge/Paper-DelAny-red'></a>
<a href='https://arxiv.org/abs/2511.13417'><img src='https://img.shields.io/badge/Paper-DelAnyFlow-red'></a>
<a href='https://arxiv.org/abs/2607.19069'><img src='https://img.shields.io/badge/Paper-DelAny_v2-red'></a>
<a href='https://explorer.delineate-anything.apex.esa.int/'><img src='https://img.shields.io/badge/Map-Explorer-blue'></a>
<a href='https://huggingface.co/datasets/MykolaL/FBIS-73M'><img src='https://img.shields.io/badge/Dataset-HuggingFace-DA0000'></a>
<a href='https://colab.research.google.com/drive/10KSLwYDTgU-WhpqqG39yyvB6K8MdB0X9?usp=sharing'><img src='https://img.shields.io/badge/Colab-Demo-F9AB00'></a>

by [Mykola Lavreniuk](https://scholar.google.com/citations?hl=en&user=-oFR-RYAAAAJ), [Nataliia Kussul](https://scholar.google.com/citations?user=e3TWBuwAAAAJ&hl=en), [Andrii Shelestov](https://scholar.google.com/citations?user=tqoQKZAAAAAJ&hl=en), [Yevhenii Salii](https://scholar.google.com/citations?user=4jgAsBIAAAAJ&hl=en), [Volodymyr Kuzin](https://www.researchgate.net/profile/Volodymyr-Kuzin), [Charlotte Julia Li-Xing Wang](https://orcid.org/0009-0007-0270-3470), [Zoltan Szantoi](https://scholar.google.com/citations?user=P_pyhi8AAAAJ&hl=en)

**Delineate Anything v2** extends Delineate Anything into a globally representative, resolution-agnostic foundation model that scales agricultural field boundary detection to a planetary level from any imagery source. Trained on **FBIS-73M**, a massive 73-million-instance dataset spanning 61 countries with diverse imagery sources ranging from 0.25m to 10m resolution, built through a resolution-specific curation pipeline that solves the parcel-versus-field mismatch, Delineate Anything v2 sets a new state-of-the-art in global zero-shot delineation. 
It delivers a **+103.3% relative gain in mAP@0.5** over Delineate Anything while maintaining extreme efficiency, mapping all of Ukraine (603,000 km²) in 5.4 hours on a regular PC with 1 GPU NVIDIA RTX 5070 Ti 16 GB.

![intro v1](figs/intro.jpg)

![intro v2](figs/intro_v2.jpg)

## Papers
- **[Delineate Anything v2: A Global Foundation Model for Field Delineation](https://arxiv.org/abs/2607.19069)** (ECCV 2026)
- **[Delineate Anything Flow: Fast, Country-Level Field Boundary Detection from Any Source](https://arxiv.org/abs/2511.13417)**
- **[Delineate Anything: Resolution-Agnostic Field Boundary Delineation on Satellite Imagery](https://arxiv.org/abs/2504.02534)** (ECAI 2025)

## Citation
```bibtex
@inproceedings{lavreniuk2026delanyv2,
      title={Delineate Anything v2: A Global Foundation Model for Field Delineation}, 
      author={Mykola Lavreniuk and Nataliia Kussul and Andrii Shelestov and Yevhenii Salii and Volodymyr Kuzin and Charlotte Julia Li-Xing Wang and Zoltan Szantoi},
      year={2026},
      booktitle={European Conference on Computer Vision Workshops (ECCVW)},
}

@inproceedings{lavreniuk2025delineateanything,
      title={Delineate Anything: Resolution-Agnostic Field Boundary Delineation on Satellite Imagery}, 
      author={Mykola Lavreniuk and Nataliia Kussul and Andrii Shelestov and Bohdan Yailymov and Yevhenii Salii and Volodymyr Kuzin and Zoltan Szantoi},
      year={2025},
      booktitle={European Conference on Artificial Intelligence},
}

@article{lavreniuk2025delineateanythingflow,
      title={Delineate Anything Flow: Fast, Country-Level Field Boundary Detection from Any Source}, 
      author={Mykola Lavreniuk and Nataliia Kussul and Andrii Shelestov and Yevhenii Salii and Volodymyr Kuzin and Sergii Skakun and Zoltan Szantoi},
      year={2025},
      journal={[https://arxiv.org/abs/2511.13417](https://arxiv.org/abs/2511.13417)},
}