{
  "abstract": "Accurate tree segmentation is a key step in extracting individual tree metrics from forest laser scans, and is essential to understanding ecosystem functions in carbon cycling and beyond. Over the past decade, tree segmentation algorithms have advanced rapidly due to developments in AI. However, existing public 3D forest datasets are not large enough to build robust tree segmentation systems. Motivated by the success of synthetic data in other domains such as self-driving, we investigate whether similar approaches can help with tree segmentation. In place of expensive field data collection and annotation, we use synthetic data during pretraining, and then require only minimal, real forest plot annotation for fine-tuning. We have developed Cambridge Arboreal Modelling Panoptic 3D (CAMP3D), a new synthetic data generation pipeline to do this for forest vision tasks, integrating advances in game engines with physics-based LiDAR simulation. Using CAMP3D, we have produced a comprehensive, diverse, annotated 3D forest dataset on an unprecedented scale. Extensive experiments with a state-of-the-art tree segmentation algorithm and a popular real dataset show that our synthetic data can substantially reduce the need for labelled real data. After fine-tuning on just a single, real, forest plot of less than 0.1 hectare, the pretrained model achieves segmentations that are competitive with a model trained on the full scale real data. We have also identified critical factors for successful use of synthetic data: physics, diversity, and scale, paving the way for more robust 3D forest vision systems in the future. Our CAMP3D pipeline and the resulting dataset are available at https://github.com/yihshe/CAMP3D.git.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Computer Science and Technology, University of Cambridge, 15 JJ Thomson Avenue, Cambridge, CB3 0FD United Kingdom",
    "Clare Hall, University of Cambridge, Herschel Road, Cambridge, CB3 9AL United Kingdom",
    "Department of Plant Sciences, University of Cambridge, Downing Street, Cambridge, CB2 3EA United Kingdom"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Yihang She",
      "orcid": "0009-0004-4205-1874"
    },
    {
      "affs": [
        1
      ],
      "name": "Andrew Blake",
      "orcid": "0000-0002-3577-3906"
    },
    {
      "affs": [
        2
      ],
      "name": "David A. Coomes",
      "orcid": "0000-0002-8261-2582"
    },
    {
      "affs": [
        0
      ],
      "name": "Srinivasan Keshav",
      "orcid": "0000-0002-6549-0464"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2nrq8d3sy5rth.bib",
  "cited_by": 5,
  "doi": "10.1007/s11263-026-02923-y",
  "fulltext_url": null,
  "id": "2nrq8d3sy5rth",
  "issns": [
    "0920-5691",
    "1573-1405"
  ],
  "landing_url": "https://doi.org/10.1007/s11263-026-02923-y",
  "language": "en",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1107|Remote Sensing and LiDAR Applications"
    ]
  ],
  "openalex": "W4415088032",
  "pdf_url": "https://link.springer.com/content/pdf/10.1007/s11263-026-02923-y.pdf",
  "pmcid": "PMC13356082",
  "pmid": "42438738",
  "published": "2026-07-01",
  "publisher": "Springer Science+Business Media",
  "ris": "https://research.draconitic.com/paper/2nrq8d3sy5rth.ris",
  "sources": [
    {
      "first_seen": "2026-11-07T13:20:51Z",
      "native_id": "W4415088032",
      "source": "openalex",
      "url": "https://doi.org/10.1007/s11263-026-02923-y"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "openalex:1107|Remote Sensing and LiDAR Applications",
      "subfield": "ecology"
    }
  ],
  "title": "Scaling Up Forest Vision with Synthetic Data",
  "title_text": "Scaling Up Forest Vision with Synthetic Data",
  "type": "peer-reviewed",
  "updated_at": "2026-11-10T13:21:07Z",
  "url": "https://research.draconitic.com/paper/2nrq8d3sy5rth",
  "venue": "International Journal of Computer Vision",
  "versions": []
}