TreeON: Reconstructing 3D Tree Point Clouds from Orthophotos and Heightmaps

Information

• Publication Type: Journal Paper with Conference Talk
• Workgroup(s)/Project(s):
  • Climate-sensitive Adaptive Planning for Shaping Resilient Cities
  • Instant Visualization and Interaction for Large Point Clouds
• Date: 2026
• Journal: Computer Graphics Forum
• Open Access: yes
• Article Number: e70366
• ISSN: 1467-8659
• DOI: 10.1111/cgf.70366
• Pages: 14
• Publisher: WILEY
• Keywords: Computing methodologies, Point-based models, Reconstruction, Neural Networks

Abstract

We present TreeON, a novel neural-based framework for reconstructing detailed 3D tree point clouds from sparse top-down geodata, using only a single orthophoto and its corresponding Digital Surface Model (DSM). Our method introduces a new training supervision strategy that combines both geometric supervision and a differentiable shadow and silhouette loss to learn point cloud representations of trees without requiring species labels, procedural rules, detailed terrestrial reconstruction data, or ground laser scan data. To address the lack of ground truth data, we generate a synthetic dataset of point clouds from procedurally modeled trees and train our network on it. Quantitative and qualitative experiments demonstrate better reconstruction quality and coverage compared to existing methods, as well as strong generalization to real-world data, leading to visually appealing and structurally plausible tree point cloud representations that can be integrated into interactive digital 3D maps. The codebase, synthetic dataset, and pretrained model are publicly available at https://angelikigram.github.io/treeON/.

Additional Files and Images

Weblinks

• https://angelikigram.github.io/treeON/
• Entry in reposiTUm (TU Wien Publication Database)
• DOI: 10.1111/cgf.70366

BibTeX

@article{grammatikaki-2026-treeon,
  title =      "TreeON: Reconstructing 3D Tree Point Clouds from Orthophotos
               and Heightmaps",
  author =     "Angeliki Grammatikaki and Johannes Eschner and Pedro
               Hermosilla and Oscar Argudo and Manuela Waldner",
  year =       "2026",
  abstract =   "We present TreeON, a novel neural-based framework for
               reconstructing detailed 3D tree point clouds from sparse
               top-down geodata, using only a single orthophoto and its
               corresponding Digital Surface Model (DSM). Our method
               introduces a new training supervision strategy that combines
               both geometric supervision and a differentiable shadow and
               silhouette loss to learn point cloud representations of
               trees without requiring species labels, procedural rules,
               detailed terrestrial reconstruction data, or ground laser
               scan data. To address the lack of ground truth data, we
               generate a synthetic dataset of point clouds from
               procedurally modeled trees and train our network on it.
               Quantitative and qualitative experiments demonstrate better
               reconstruction quality and coverage compared to existing
               methods, as well as strong generalization to real-world
               data, leading to visually appealing and structurally
               plausible tree point cloud representations that can be
               integrated into interactive digital 3D maps. The codebase,
               synthetic dataset, and pretrained model are publicly
               available at https://angelikigram.github.io/treeON/.",
  journal =    "Computer Graphics Forum",
  articleno =  "e70366",
  issn =       "1467-8659",
  doi =        "10.1111/cgf.70366",
  pages =      "14",
  publisher =  "WILEY",
  keywords =   "Computing methodologies, Point-based models, Reconstruction,
               Neural Networks",
  URL =        "https://www.cg.tuwien.ac.at/research/publications/2026/grammatikaki-2026-treeon/",
}