{"name": "AITracer by LAD", "package_name": "aitracer", "description": "Click any feature on a georeferenced raster and SAM2 segments it instantly. Refine with positive/negative prompts, then accept to create a vector polygon. All processing runs locally \u2014 by LAD, Sapienza University of Rome.", "about": "AITracer by LAD brings AI-assisted raster digitization to QGIS 4.\n\nActivate the tool, click any feature in a georeferenced raster \u2014\naerial photo, drone orthophoto, scanned plan \u2014 and the SAM2-tiny\nmodel segments it instantly as a polygon preview. Refine the result\nwith positive or negative point prompts, adjust Douglas-Peucker\nsimplification, then accept to add the polygon to any vector layer.\n\nHOW IT WORKS: AITracer captures a screenshot of the current QGIS\ncanvas and sends it to SAM2 \u2014 it does not read the original raster\nfile. This keeps processing fast and memory-light on modest hardware.\nThe output resolution depends on your zoom level, not the raster\nresolution. Features that extend beyond the canvas edge will be\npartially traced. The canvas is locked during a session to keep\npixel-to-map coordinates consistent.\n\nFirst-time setup automatically downloads a standalone Python runtime\nand the SAM2-tiny model weights (~160 MB). An internet connection is\nrequired for this one-time step only. All subsequent processing runs\nentirely on your machine; no data is ever sent to external servers.\n\nDeveloped by LAD \u2014 Laboratorio di Archeologia Digitale,\nSapienza University of Rome.", "homepage": "https://github.com/lad-sapienza/ai-tracer", "repository": "https://github.com/lad-sapienza/ai-tracer", "tracker": "https://github.com/lad-sapienza/ai-tracer/issues", "author": "Julian Bogdani | LAD \u2013 Laboratorio di Archeologia Digitale, Sapienza University of Rome", "tags": ["raster", "digitizing", "remote sensing", "archaeology", "drone", "machine learning", "segmentation", "vectorization", "ai", "sam", "instance segmentation", "sam2", "digitisation", "segment anything", "vectorisation", "aerial photo"], "downloads": 670, "latest_version": "0.1.33", "versions": [{"version": "0.1.33", "experimental": true, "qgis_min": "4.0.0", "qgis_max": "4.99.0", "downloads": 255, "uploaded_by": "jbogdani", "upload_datetime": "2026-06-11T12:33:40.595352"}, {"version": "0.1.32", "experimental": true, "qgis_min": "4.0.0", "qgis_max": "4.99.0", "downloads": 221, "uploaded_by": "jbogdani", "upload_datetime": "2026-05-03T14:40:54.756932"}, {"version": "0.1.31", "experimental": true, "qgis_min": "4.0.0", "qgis_max": "4.99.0", "downloads": 110, "uploaded_by": "jbogdani", "upload_datetime": "2026-05-02T01:44:48.847760"}, {"version": "0.1.30", "experimental": true, "qgis_min": "4.0.0", "qgis_max": "4.99.0", "downloads": 84, "uploaded_by": "jbogdani", "upload_datetime": "2026-04-29T05:45:22.507660"}]}