July 13, 2026 Dataset Open Access

Radoynova, Martina; Pantze, Samuel; De, Trina; Günther, Ulrik; Yakimovich, Artur

JSON Export

{
  "conceptrecid": "4779", 
  "created": "2026-07-13T08:27:53.081909+00:00", 
  "stats": {
    "volume": 0.0, 
    "unique_downloads": 0.0, 
    "version_unique_downloads": 0.0, 
    "unique_views": 107.0, 
    "downloads": 0.0, 
    "version_unique_views": 107.0, 
    "version_views": 116.0, 
    "version_downloads": 0.0, 
    "version_volume": 0.0, 
    "views": 116.0
  }, 
  "updated": "2026-07-13T10:02:27.849409+00:00", 
  "revision": 4, 
  "links": {
    "badge": "https://rodare.hzdr.de/badge/doi/10.14278/rodare.4780.svg", 
    "doi": "https://doi.org/10.14278/rodare.4780", 
    "conceptbadge": "https://rodare.hzdr.de/badge/doi/10.14278/rodare.4779.svg", 
    "conceptdoi": "https://doi.org/10.14278/rodare.4779", 
    "bucket": "https://rodare.hzdr.de/api/files/39d3f2b4-445c-4876-ac79-d5e93e60a768", 
    "html": "https://rodare.hzdr.de/record/4780", 
    "latest": "https://rodare.hzdr.de/api/records/4780", 
    "latest_html": "https://rodare.hzdr.de/record/4780"
  }, 
  "files": [
    {
      "key": "blender.zip", 
      "type": "zip", 
      "size": 253530792, 
      "links": {
        "self": "https://rodare.hzdr.de/api/files/39d3f2b4-445c-4876-ac79-d5e93e60a768/blender.zip"
      }, 
      "checksum": "md5:b7b9b33cbe3f1a233c4be98f0fcb6d90", 
      "bucket": "39d3f2b4-445c-4876-ac79-d5e93e60a768"
    }, 
    {
      "key": "dataset_high-L.zip", 
      "type": "zip", 
      "size": 798358357, 
      "links": {
        "self": "https://rodare.hzdr.de/api/files/39d3f2b4-445c-4876-ac79-d5e93e60a768/dataset_high-L.zip"
      }, 
      "checksum": "md5:3b0ee6b6a2933b7e508ddbd9acb5a52f", 
      "bucket": "39d3f2b4-445c-4876-ac79-d5e93e60a768"
    }, 
    {
      "key": "dataset_high-S.zip", 
      "type": "zip", 
      "size": 79701167, 
      "links": {
        "self": "https://rodare.hzdr.de/api/files/39d3f2b4-445c-4876-ac79-d5e93e60a768/dataset_high-S.zip"
      }, 
      "checksum": "md5:2152030f1bd2fa389b093def30d2c8cf", 
      "bucket": "39d3f2b4-445c-4876-ac79-d5e93e60a768"
    }, 
    {
      "key": "dataset_low-L.zip", 
      "type": "zip", 
      "size": 527874457, 
      "links": {
        "self": "https://rodare.hzdr.de/api/files/39d3f2b4-445c-4876-ac79-d5e93e60a768/dataset_low-L.zip"
      }, 
      "checksum": "md5:25f72dac4902d12fcd8b5d4b29213153", 
      "bucket": "39d3f2b4-445c-4876-ac79-d5e93e60a768"
    }, 
    {
      "key": "dataset_low-S.zip", 
      "type": "zip", 
      "size": 52122808, 
      "links": {
        "self": "https://rodare.hzdr.de/api/files/39d3f2b4-445c-4876-ac79-d5e93e60a768/dataset_low-S.zip"
      }, 
      "checksum": "md5:67df196138195355800e6bbcc4324307", 
      "bucket": "39d3f2b4-445c-4876-ac79-d5e93e60a768"
    }, 
    {
      "key": "dataset_medium-L.zip", 
      "type": "zip", 
      "size": 616510707, 
      "links": {
        "self": "https://rodare.hzdr.de/api/files/39d3f2b4-445c-4876-ac79-d5e93e60a768/dataset_medium-L.zip"
      }, 
      "checksum": "md5:0798aa898c0757ae37016e07b3cf99f1", 
      "bucket": "39d3f2b4-445c-4876-ac79-d5e93e60a768"
    }, 
    {
      "key": "dataset_medium-S.zip", 
      "type": "zip", 
      "size": 61594229, 
      "links": {
        "self": "https://rodare.hzdr.de/api/files/39d3f2b4-445c-4876-ac79-d5e93e60a768/dataset_medium-S.zip"
      }, 
      "checksum": "md5:06f4c8e9250d01ccf76e26cf228d428f", 
      "bucket": "39d3f2b4-445c-4876-ac79-d5e93e60a768"
    }, 
    {
      "key": "dataset_mix.zip", 
      "type": "zip", 
      "size": 78937319, 
      "links": {
        "self": "https://rodare.hzdr.de/api/files/39d3f2b4-445c-4876-ac79-d5e93e60a768/dataset_mix.zip"
      }, 
      "checksum": "md5:62f86b529ba7f985b6f4439dd4d1ea42", 
      "bucket": "39d3f2b4-445c-4876-ac79-d5e93e60a768"
    }, 
    {
      "key": "model_high-L.zip", 
      "type": "zip", 
      "size": 223507341, 
      "links": {
        "self": "https://rodare.hzdr.de/api/files/39d3f2b4-445c-4876-ac79-d5e93e60a768/model_high-L.zip"
      }, 
      "checksum": "md5:d36bf6e93956cea3e04babe2793498ff", 
      "bucket": "39d3f2b4-445c-4876-ac79-d5e93e60a768"
    }, 
    {
      "key": "model_high-S.zip", 
      "type": "zip", 
      "size": 222653860, 
      "links": {
        "self": "https://rodare.hzdr.de/api/files/39d3f2b4-445c-4876-ac79-d5e93e60a768/model_high-S.zip"
      }, 
      "checksum": "md5:a1d568aca0dc863a4e897ee5a11c1f61", 
      "bucket": "39d3f2b4-445c-4876-ac79-d5e93e60a768"
    }, 
    {
      "key": "model_low-L.zip", 
      "type": "zip", 
      "size": 223659983, 
      "links": {
        "self": "https://rodare.hzdr.de/api/files/39d3f2b4-445c-4876-ac79-d5e93e60a768/model_low-L.zip"
      }, 
      "checksum": "md5:d2748250e5704cd9a884fbd593318edf", 
      "bucket": "39d3f2b4-445c-4876-ac79-d5e93e60a768"
    }
  ], 
  "owners": [
    506
  ], 
  "doi": "10.14278/rodare.4780", 
  "id": 4780, 
  "metadata": {
    "version": "Version 1", 
    "language": "eng", 
    "pub_id": "43634", 
    "communities": [
      {
        "id": "health"
      }, 
      {
        "id": "rodare"
      }
    ], 
    "license": {
      "id": "CC-BY-4.0"
    }, 
    "doc_id": "1", 
    "publication_date": "2026-07-13", 
    "access_right": "open", 
    "relations": {
      "version": [
        {
          "last_child": {
            "pid_value": "4780", 
            "pid_type": "recid"
          }, 
          "count": 1, 
          "is_last": true, 
          "parent": {
            "pid_value": "4779", 
            "pid_type": "recid"
          }, 
          "index": 0
        }
      ]
    }, 
    "related_identifiers": [
      {
        "scheme": "url", 
        "relation": "isIdenticalTo", 
        "identifier": "https://www.hzdr.de/publications/Publ-43634"
      }, 
      {
        "scheme": "doi", 
        "relation": "isVersionOf", 
        "identifier": "10.14278/rodare.4779"
      }
    ], 
    "title": "Metric-Guided Synthetic Image Data Rendering for Deep Learning compatible with Agentic AI", 
    "doi": "10.14278/rodare.4780", 
    "keywords": [
      "deep learning", 
      "synthetic data", 
      "procedural image rendering", 
      "Blender", 
      "computer vision", 
      "instance segmentation"
    ], 
    "resource_type": {
      "title": "Dataset", 
      "type": "dataset"
    }, 
    "access_right_category": "success", 
    "creators": [
      {
        "name": "Radoynova, Martina", 
        "orcid": "0009-0003-4358-0391", 
        "affiliation": "Center for Advanced Systems Understanding (CASUS), G\u00f6rlitz, Germany"
      }, 
      {
        "name": "Pantze, Samuel", 
        "orcid": "0009-0000-1388-8959", 
        "affiliation": "Center for Advanced Systems Understanding (CASUS), G\u00f6rlitz, Germany"
      }, 
      {
        "name": "De, Trina", 
        "orcid": "0000-0003-1111-9851", 
        "affiliation": "Center for Advanced Systems Understanding (CASUS), G\u00f6rlitz, Germany"
      }, 
      {
        "name": "G\u00fcnther, Ulrik", 
        "orcid": "0000-0002-1179-8228", 
        "affiliation": "Center for Advanced Systems Understanding (CASUS), G\u00f6rlitz, Germany"
      }, 
      {
        "name": "Yakimovich, Artur", 
        "orcid": "0000-0003-2458-4904", 
        "affiliation": "Center for Advanced Systems Understanding (CASUS), G\u00f6rlitz, Germany"
      }
    ], 
    "description": "<p>This repository contains the datasets, 3D rendering scene files, and trained model weights accompanying the manuscript <strong>&quot;Metric-Guided Synthetic Image Data Rendering for Deep Learning compatible with Agentic AI.&quot;</strong> The deposited files provide the complete procedural pipeline and resulting artefacts used to evaluate zero-shot instance segmentation of virological plaque assays (based on the <a href=\"https://rodare.hzdr.de/record/3003\">VACVPlaque dataset</a>).</p>\n\n<p>Repository Contents</p>\n\n<ul>\n\t<li>\n\t<p><strong><code>datasets/</code></strong> Contains the synthetic image datasets generated at three varying levels of perceived realism (High, Medium, Low) and in two sizes (Small [S]: 100 images; Large [L]: 1,000 images). It also includes the <code>Mix</code> dataset, which consists of 90 high-realism synthetic images and 10 real images.</p>\n\t</li>\n\t<li>\n\t<p><strong><code>blender/</code></strong> Includes the procedural 3D scene files used to generate the synthetic datasets via Blender. These files can be used manually or coupled with the SynthClaw agentic skill for automated rendering.</p>\n\n\t<ul>\n\t\t<li>\n\t\t<p><code>Scene_High.blend</code></p>\n\t\t</li>\n\t\t<li>\n\t\t<p><code>Scene_Medium.blend</code></p>\n\t\t</li>\n\t\t<li>\n\t\t<p><code>Scene_Low.blend</code></p>\n\t\t</li>\n\t</ul>\n\t</li>\n\t<li>\n\t<p><strong><code>model_weights/</code></strong> Contains the trained single-shot architecture model weights and threshold configurations used to evaluate the zero-shot performance of each generated dataset.</p>\n\n\t<ul>\n\t\t<li>\n\t\t<p><strong>Evaluated Conditions:</strong> <code>High_L</code>, <code>High_S</code>, <code>Medium_L</code>, <code>Medium_S</code>, <code>Low_L</code>, <code>Low_S</code>, and <code>Mix</code>.</p>\n\t\t</li>\n\t\t<li>\n\t\t<p><strong>Files per Condition:</strong> Each subdirectory includes the best and last model weights (<code>weights_best.h5</code>, <code>weights_last.h5</code>) alongside the corresponding threshold optimization parameters (<code>thresholds1.json</code>, <code>thresholds2.json</code>) for large and small object segmentation.</p>\n\t\t</li>\n\t</ul>\n\t</li>\n</ul>"
  }, 
  "conceptdoi": "10.14278/rodare.4779"
}