{"id":13949035,"url":"https://github.com/Orion-AI-Lab/KuroSiwo","last_synced_at":"2025-07-20T11:31:04.933Z","repository":{"id":208579222,"uuid":"720397394","full_name":"Orion-AI-Lab/KuroSiwo","owner":"Orion-AI-Lab","description":"Code and data for Kuro Siwo flood mapping dataset","archived":false,"fork":false,"pushed_at":"2025-04-03T08:24:04.000Z","size":32167,"stargazers_count":63,"open_issues_count":10,"forks_count":6,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-07-19T17:31:34.994Z","etag":null,"topics":["computer-vision","flood","remote-sensing","sar","synthetic-aperture-radar"],"latest_commit_sha":null,"homepage":"https://orion-ai-lab.github.io/publication/bountos-2023-kuro/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Orion-AI-Lab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2023-11-18T11:09:25.000Z","updated_at":"2025-06-24T12:15:04.000Z","dependencies_parsed_at":"2024-02-07T22:42:26.434Z","dependency_job_id":"277cbc15-670d-474d-875c-3d63b0f92b01","html_url":"https://github.com/Orion-AI-Lab/KuroSiwo","commit_stats":{"total_commits":66,"total_committers":3,"mean_commits":22.0,"dds":0.5454545454545454,"last_synced_commit":"5c3727750c8bd3d2057c01a1985fedbac48fa61f"},"previous_names":["orion-ai-lab/kurosiwo"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Orion-AI-Lab/KuroSiwo","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Orion-AI-Lab%2FKuroSiwo","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Orion-AI-Lab%2FKuroSiwo/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Orion-AI-Lab%2FKuroSiwo/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Orion-AI-Lab%2FKuroSiwo/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Orion-AI-Lab","download_url":"https://codeload.github.com/Orion-AI-Lab/KuroSiwo/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Orion-AI-Lab%2FKuroSiwo/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266116858,"owners_count":23878961,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["computer-vision","flood","remote-sensing","sar","synthetic-aperture-radar"],"created_at":"2024-08-08T05:01:36.763Z","updated_at":"2025-07-20T11:31:04.926Z","avatar_url":"https://github.com/Orion-AI-Lab.png","language":"Python","funding_links":[],"categories":["Multi-Modal and SAR Datasets","Climate Change"],"sub_categories":["Natural Hazard and Storms"],"readme":"# [Kuro Siwo: A global multi-temporal SAR dataset for rapid flood mapping](https://arxiv.org/abs/2311.12056)\n\n  #### Latest updates:\n    - [✔️] Update codebase for KuroSiwo v2 + updated mean/stds\n    - [✔️] Updated citation \n    - [ ] TODO: Expand README with more elaborate guidelines\n    - [ ] TODO: Upload Kuro-Siwo to HuggingFace\n\n![Kuro Siwo](imgs/kuro_spatial.png)\n\n\n# Table of Contents\n- [Download the dataset](#download-kuro-siwo)\n- [Data preprocessing](#data-preprocessing)\n- [Repository structure](#kuro-siwo-repo-structure)\n- [Pretrained models](#pretrained-models)\n- [Citation](#citation)\n\n\n### Download Kuro Siwo\n\n  #### GRD Data\n- The Kuro Siwo GRD Dataset can be downloaded either:\n  - from the following [link](https://www.dropbox.com/scl/fo/xc69aclh0q4lykd22ynkb/AAaDu8gBtoSdOpmffv7JY50?rlkey=uds2b2aot6oubc9hmnrm7myy7\u0026st=21u41kwx\u0026dl=0),\n\n\n  - or by executing ```scripts/download_kuro_siwo.sh```. This script will download and prepare the Kuro Siwo GRDD dataset for deep learning.\n\n    #### Usage \n\n    1. Make sure to grant the necessary rights by executing `chmod +x scripts/download_kuro_siwo.sh`\n    2. Execute `scripts/download_kuro_siwo.sh DESIRED_DATASET_ROOT_PATH` e.g: `./download_kuro_siwo.sh KuroRoot`\n\n\n#### SLC Data\n  - The SLC Preprocessed products can be downloaded from the following [link](https://www.dropbox.com/scl/fo/kknf6ycz6ywffopjxroys/AOIedl2NgWnOXQBEDUGv4m0?rlkey=rb18w8rzpwitg2w3nlhzklnyy\u0026st=p1vv516h\u0026dl=0).\n\n  - Similarly, the cropped SLC patches (224x224 pixels) can be acquired from the following [link](https://www.dropbox.com/scl/fo/6u1bhbhd34rnn0u47o8dj/AK9vblAzDWqhPTqYvioPUb8?rlkey=i7k862563n936akuqlsdf3w66\u0026st=0f7q3vno\u0026dl=0).  \n\n\n### Data preprocessing\n\nThe preprocessing pipelines used to generate the GRD and SLC products can be found at `configs/grd_preprocessing.xml` and `configs/slc_preprocessing.xml` repsectively.\n\n\n### Kuro Siwo repo structure \n  - Kuro Siwo uses the [black](https://github.com/psf/black) python formatter. To activate it install pre-commit, running `pip install pre-commit`\nand execute `pre-commit install`.\n  - Training starts by running `python main.py`. The configurations are defined in the `configs` directory\n e.g \n    - model,\n    - training pipeline \n      - Segmentation,\n      - change detection\n    - hyperparameters\n  - `main.py` supports command line arguments that override the config files.\n     e.g \n      ```\n         python main.py --method=unet --backbone=resnet18 --dem=True --slope=False --batch_size=32\n      ```\n\n\n### Pretrained models\nThe weights of the top performing models can be accessed using the following links:\n  - [FloodViT](https://www.dropbox.com/scl/fi/srw7u4cw1gtxrf4xzmsh7/floodvit.pt?rlkey=snskpq1qrdav5u2jya8k2bocg\u0026dl=0)\n  - [SNUNet](https://www.dropbox.com/scl/fi/3vlsveoobqe1wc71s5z2d/best_segmentation.pt?rlkey=xpy2thmozzxfzymr8b13m7n51\u0026dl=0)\n\n\n### Citation\nIf you use this work please cite:\n```\n@inproceedings{NEURIPS2024_43612b06,\n author = {Bountos, Nikolaos Ioannis and Sdraka, Maria and Zavras, Angelos and Karavias, Andreas and Karasante, Ilektra and Herekakis, Themistocles and Thanasou, Angeliki and Michail, Dimitrios and Papoutsis, Ioannis},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {A. Globerson and L. Mackey and D. Belgrave and A. Fan and U. Paquet and J. Tomczak and C. Zhang},\n pages = {38105--38121},\n publisher = {Curran Associates, Inc.},\n title = {Kuro Siwo: 33 billion m\\^{}2 under the water. A global multi-temporal satellite dataset for rapid flood mapping},\n url = {https://proceedings.neurips.cc/paper_files/paper/2024/file/43612b0662cb6a4986edf859fd6ebafe-Paper-Datasets_and_Benchmarks_Track.pdf},\n volume = {37},\n year = {2024}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FOrion-AI-Lab%2FKuroSiwo","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FOrion-AI-Lab%2FKuroSiwo","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FOrion-AI-Lab%2FKuroSiwo/lists"}