{"success":true,"data":{"author":"Florian Kitzler, Norbert Barta, Reinhard W. Neugschwandtner, Andreas Gronauer and Viktoria Motsch (University of Natural Resources and Life Sciences, Vienna); Hugging Face mirror by Project-AgML","bucketAccessType":"public","bucketName":"Project-AgML/WE3DS_weed_segmentation","bucketPrefix":"","category":"Agriculture & Environment","cloudProvider":"huggingface","createdAt":"2026-11-22T01:09:12.786Z","description":"WE3DS is an RGB-D image database for multi-class plant species semantic segmentation in crop farming: 2,568 images, each a color image plus a distance (depth) map, with hand-annotated ground-truth masks separating crop and weed species from soil. Images were taken under natural light with an RGB-D sensor made of two RGB cameras in a stereo setup, and the authors describe it as the first RGB-D dataset for multi-class plant species segmentation. The original train, validation and test split is kept in a split column. Useful for weed mapping, depth-aided segmentation, and selective weeding. Stored as Parquet shards with the image bytes and annotations in columns; load with datasets.load_dataset(\"Project-AgML/WE3DS_weed_segmentation\") or through the AgML Python library (Project-AgML, UC Davis), which reformatted the original release. License: CC BY 4.0, as stated by the original publisher; cite Florian Kitzler, Norbert Barta, Reinhard W. Neugschwandtner, Andreas Gronauer and Viktoria Motsch et al. and the DOI 10.5281/zenodo.7457983.","displayTitle":"WE3DS: RGB-D Stereo Images of Crops and Weeds with Hand-Annotated Semantic Segmentation Masks, 2,568 Images (BOKU Vienna, AgML Mirror)","doi":"10.5281/zenodo.7457983","huggingFaceUrl":"https://huggingface.co/datasets/Project-AgML/WE3DS_weed_segmentation","id":"09194559-dc5d-5489-b330-6ef8afe94f57","license":"CC-BY-4.0","licenseEvidenceUrl":"https://zenodo.org/records/7457983","objectCountEstimate":21,"probeStatus":"ok","referenceUrl":"https://huggingface.co/datasets/Project-AgML/WE3DS_weed_segmentation","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"Project-AgML/WE3DS_weed_segmentation\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"Project-AgML/WE3DS_weed_segmentation\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=Project-AgML, license:cc-by-4.0, size_categories:1K<n<10K, format:parquet, downloads=282"],"format":"mixed","generatedAt":"2026-11-22T01:10:02.602Z","layout":{"example":"data/train-00000-of-00019.parquet","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"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","encoding":"hex","key":"data/train-00000-of-00019.parquet","truncatedAt":512}],"sampleObjects":["data/train-00000-of-00019.parquet","data/train-00001-of-00019.parquet","data/train-00002-of-00019.parquet","data/train-00003-of-00019.parquet","data/train-00004-of-00019.parquet"],"sidecars":[{"bytes":"---\ndataset_info:\n  features:\n  - name: image\n    dtype: image\n  - name: mask\n    dtype: image\n  - name: split\n    dtype: string\n  - name: date\n    dtype: string\n  - name: time\n    dtype: string\n  - name: lat\n    dtype: string\n  - name: lon\n    dtype: string\n  - name: utc\n    dtype: string\n  - name: weather\n    dtype: string\n  - name: wind\n    dtype: string\n  - name: seeding_date\n    dtype: string\n  - name: height_mm\n    dtype: string\n  - name: depth\n    dtype: image\n  - name: depth_refined\n    dtype: string\n  splits:\n  - name: train\n    num_bytes: 9013751981\n    num_examples: 2568\n  download_size: 8747620007\n  dataset_size: 9013751981\nconfigs:\n- config_name: default\n  data_files:\n  - split: train\n    path: data/train-*\nlicense: cc-by-4.0\ntask_categories:\n- image-segmentation\nsize_categories:\n- 1K<n<10K\n---\n# We3ds Weed Segmentation\n\nThis dataset provides real-world RGB imagery focused on weed segmentation within agricultural fields. It captures diverse weed and crop patterns under natural field conditions, offering a practical resource for developing and evaluating semantic segmentation models in precision agriculture applications. The dataset contains 2,568 images with pixel-level mask annotations.\n\nThis dataset is indexed on https://project-agml.github.io/ as part of the AgML python library.\n\nThe original train/test/val split has been preserved in the `split` column.\n\n## Citation\n\n```bibtex\n@article{kitzler2023we3ds,\n  title={WE3DS: An RGB-D image dataset for semantic segmentation in agriculture},\n  author={Kitzler, Florian and Barta, Norbert and Neugschwandtner, Reinhard W and Gronauer, Andreas and Motsch, Viktoria},\n  journal={Sensors},\n  volume={23},\n  number={5},\n  pages={2713},\n  year={2023},\n  publisher={MDPI}\n}\n```\n\nKitzler, F., Barta, N., Neugschwandtner, R. W., Gronauer, A., & Motsch, V. (2023). WE3DS: An RGB-D image dataset for semantic segmentation in agriculture [Dataset]. In Sensors (Vol. 23, Issue 5, p. 2713). Zenodo. https://doi.org/10.5281/zenodo.7457983\n\n*This dataset was reformatted from its original format to match HuggingFace standards.*\n","encoding":"utf8","key":"README.md","name":"README.md","size":2097,"truncated":false}],"sourceObjectKey":"data/train-00000-of-00019.parquet","starterCell":"from datasets import load_dataset\nds = load_dataset(\"Project-AgML/WE3DS_weed_segmentation\")\nprint(ds)","starterSamplePath":"data/train-00000-of-00019.parquet","totalObjects":21},"summary":"WE3DS is an RGB-D image database for multi-class plant species semantic segmentation in crop farming: 2,568 images, each a color image plus a distance (depth) map, with…","title":"WE3DS: RGB-D Stereo Images of Crops and Weeds with Hand-Annotated Semantic Segmentation Masks, 2,568 Images (BOKU Vienna, AgML Mirror)","updatedAt":"2026-11-22T04:06:31.721Z","visibility":"public","websiteUrl":"https://project-agml.github.io/"}}