{"name": "EasySegment", "package_name": "hitl_sketcher", "description": "Interactive HITL labeling and training plugin for geospatial segmentation using SAM3 and DINOv3-sat", "about": "EasySegment connects QGIS to a GPU inference backend for human-in-the-loop geospatial segmentation. Use it purely as a labeling tool, or run the full pipeline.\n\nWorkflow: create a project \u2192 define classes \u2192 draw exhaustive annotation regions \u2192 label with SAM3 or polygon tool \u2192 train \u2192 run batch inference \u2192 promote best model \u2192 correct and retrain.\n\nLabeling: SAM3 interactive segmentation via multi-click prompts directly on the QGIS viewport (left-click adds, right-click negates). Polygon draw tool available as an alternative. Labels are stored as polygons.\n\nTraining: DINOv3-sat backbone pretrained on 493M satellite images with a UperNet head. Only the head trains \u2014 50\u2013100 labelled features per class is enough to start.\n\nInference: Batch inference over any raster extent. Results load as a styled vector layer with a confidence heatmap for guided correction.\n\nRaster support: Works with any QGIS layer \u2014 GeoTIFF, WMS, XYZ tile URLs. Captures the viewport directly for SAM3 prompts and training chips.\n\nBackend: Requires a separate FastAPI + GPU server (https://github.com/anemes/backend_samdino). Supports remote hosting with optional API key authentication.", "homepage": "https://github.com/anemes/qgis_sam3plugin", "repository": "https://github.com/anemes/qgis_sam3plugin", "tracker": "https://github.com/anemes/qgis_sam3plugin/issues", "author": "Andras Nemes", "tags": ["labeling", "remote sensing", "machine learning", "segmentation", "sam", "sam3", "dino", "hitl"], "downloads": 196, "latest_version": "0.1.3", "versions": [{"version": "0.1.3", "experimental": true, "qgis_min": "3.44.0", "qgis_max": "3.99.0", "downloads": 130, "uploaded_by": "anemes", "upload_datetime": "2026-04-24T08:10:14.409874"}, {"version": "0.1.1", "experimental": true, "qgis_min": "3.44.0", "qgis_max": "3.99.0", "downloads": 66, "uploaded_by": "anemes", "upload_datetime": "2026-03-31T20:32:52.019835"}]}