{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T09:08:20Z","timestamp":1778663300658,"version":"3.51.4"},"reference-count":77,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T00:00:00Z","timestamp":1778630400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T00:00:00Z","timestamp":1778630400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001821","name":"Vienna Science and Technology Fund","doi-asserted-by":"publisher","award":["PID2021\u2010122136OB\u2010C21"],"award-info":[{"award-number":["PID2021\u2010122136OB\u2010C21"]}],"id":[{"id":"10.13039\/501100001821","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011033","name":"Agencia Estatal de Investigaci\u00f3n","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011033","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008530","name":"European Regional Development Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computer Graphics Forum"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    We present TreeON, a novel neural\u2010based framework for reconstructing detailed 3D tree point clouds from sparse top\u2010down 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\u2010world 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\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/angelikigram.github.io\/treeON\/\">https:\/\/angelikigram.github.io\/treeON\/<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1111\/cgf.70366","type":"journal-article","created":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T08:11:33Z","timestamp":1778659893000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TreeON: Reconstructing 3D Tree Point Clouds from Orthophotos and Heightmaps"],"prefix":"10.1111","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5779-2182","authenticated-orcid":false,"given":"Angeliki","family":"Grammatikaki","sequence":"first","affiliation":[{"name":"TU Wien, Institute of Visual Computing and Human\u2010Centered Technology  Vienna Austria"},{"name":"VRVis GmbH  Vienna Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6784-8503","authenticated-orcid":false,"given":"Johannes","family":"Eschner","sequence":"additional","affiliation":[{"name":"TU Wien, Institute of Visual Computing and Human\u2010Centered Technology  Vienna Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3586-4741","authenticated-orcid":false,"given":"Pedro","family":"Hermosilla","sequence":"additional","affiliation":[{"name":"TU Wien, Institute of Visual Computing and Human\u2010Centered Technology  Vienna Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3943-1839","authenticated-orcid":false,"given":"Oscar","family":"Argudo","sequence":"additional","affiliation":[{"name":"Universitat Polit\u00e8cnica de Catalunya, Department of Computer Science  Barcelona Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1387-5132","authenticated-orcid":false,"given":"Manuela","family":"Waldner","sequence":"additional","affiliation":[{"name":"TU Wien, Institute of Visual Computing and Human\u2010Centered Technology  Vienna Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2026,5,13]]},"reference":[{"key":"e_1_2_9_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2016.03.005"},{"key":"e_1_2_9_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2017.11.004"},{"key":"e_1_2_9_4_2","unstructured":"Achlioptas Panos Diamanti Olga Mitliagkas Ioannis andGuibas Leonidas.Learning Representations and Generative Models for 3D Point Clouds.20187."},{"key":"e_1_2_9_5_2","unstructured":"Alonso Pedro Li Tianrui andLi Chongshou.Less is More: Efficient Point Cloud Reconstruction via Multi-Head Decoders.20257."},{"key":"e_1_2_9_6_2","unstructured":"basemap.at.basemap.at.https:\/\/basemap.at\/. Accessed: 2025-11-03.20256."},{"issue":"5","key":"e_1_2_9_7_2","first-page":"279","article-title":"Urban 3D modelling using terrestrial laser scanners","volume":"36","author":"Bostr\u00f6m G.","year":"2006","journal-title":"International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences"},{"key":"e_1_2_9_8_2","unstructured":"Ba Jimmy Lei Kiros Jamie Ryan andHinton Geoffrey E.Layer Normalization.20165."},{"key":"e_1_2_9_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2461952"},{"key":"e_1_2_9_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/1278780.1278807"},{"key":"e_1_2_9_11_2","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1249\/1\/012008"},{"key":"e_1_2_9_12_2","unstructured":"Chen Zhaoxi Tang Jiaxiang Dong Yuhao et al.3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion.20253 10."},{"key":"e_1_2_9_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00571"},{"key":"e_1_2_9_14_2","doi-asserted-by":"publisher","DOI":"10.3390\/rs11182074"},{"key":"e_1_2_9_15_2","volume-title":"Austrian Forest Report 2023: We Take Care of the Forest","author":"Federal Ministry of Agriculture, Forestry, Regions and Water Management","year":"2023"},{"key":"e_1_2_9_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2016.08.013"},{"key":"e_1_2_9_17_2","unstructured":"Fan Haoqiang Su Hao andGuibas Leonidas J.\u201cA point set generation network for 3D object reconstruction from a single image\u201d.CVPR.20177."},{"key":"e_1_2_9_18_2","doi-asserted-by":"crossref","unstructured":"Grammatikaki Angeliki Eschner Johannes Ledermann Florian et al. \u201cHow to represent landmark trees in digital 3D maps? An automated workflow and user study\u201d.Cartography and Geographic Information Science0.0 (2025) 1\u201318. doi:10.1080\/15230406.2025.24895432 3 6 11.","DOI":"10.1080\/15230406.2025.2489543"},{"key":"e_1_2_9_19_2","unstructured":"Groueix Thibault Fisher Matthew Kim Vladimir G. et al.AtlasNet: A Papier-M\u00e2ch\u00e9 Approach to Learning 3D Surface Generation.201810."},{"key":"e_1_2_9_20_2","unstructured":"Grammatikaki Angeliki.Landmark trees in Austria. Version 1.0.0. TU Wien Mar.2024. DOI:10.48436\/nsj20-6ka247 9."},{"key":"e_1_2_9_21_2","doi-asserted-by":"publisher","DOI":"10.3390\/rs16030524"},{"key":"e_1_2_9_22_2","unstructured":"Gu Jiatao Trevithick Alex Lin Kai-En et al.NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion.20233."},{"key":"e_1_2_9_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2017.04.004"},{"key":"e_1_2_9_24_2","doi-asserted-by":"publisher","DOI":"10.3390\/rs16203836"},{"key":"e_1_2_9_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2007.02.029"},{"key":"e_1_2_9_26_2","unstructured":"Huang Hongyu Tian Guoji andChen Chongcheng.Evaluating the point cloud of individual trees generated from images based on Neural Radiance fields (NeRF) method.20233."},{"key":"e_1_2_9_27_2","unstructured":"Hong Yicong Zhang Kai Gu Jiuxiang et al.LRM: Large Reconstruction Model for Single Image to 3D.202410."},{"key":"e_1_2_9_28_2","doi-asserted-by":"crossref","unstructured":"He Kaiming Zhang Xiangyu Ren Shaoqing andSun Jian. \u201cDeep Residual Learning for Image Recognition\u201d.2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).2016 770\u2013778. DOI:10.1109\/CVPR.2016.904 5.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_9_29_2","unstructured":"IGN.LiDAR HD G\u00e9oservices.https:\/\/geoservices.ign.fr\/lidarhd. Institut national de l'information g\u00e9ographique et foresti\u00e8re (IGN) France.20257."},{"key":"e_1_2_9_30_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2019.100986"},{"key":"e_1_2_9_31_2","unstructured":"Ioffe SergeyandSzegedy Christian.Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift.20154."},{"key":"e_1_2_9_32_2","doi-asserted-by":"crossref","unstructured":"J\u00e6ger Peter Nilsson Niels andPalamas George. \u201cCan't see the Forest for the Trees: Perceiving Realism of Procedural Generated Trees in First-Person Games\u201d.EAI Endorsed Transactions on Creative Technologies(Mar.2021). DOI:10.4108\/eai.16-3-2021.1690292.","DOI":"10.4108\/eai.16-3-2021.169029"},{"key":"e_1_2_9_33_2","article-title":"New Weighting Functions for the Modified CIELAB Colour-Difference Formulae","volume":"9","author":"Kim Dong-Ho","year":"1997","journal-title":"Textile Coloration and Finishing"},{"key":"e_1_2_9_34_2","unstructured":"Kong Xin Liu Shikun Lyu Xiaoyang et al.EscherNet: A Generative Model for Scalable View Synthesis.20243."},{"key":"e_1_2_9_35_2","doi-asserted-by":"crossref","unstructured":"Llull Cristi\u00e1n Baloian Nelson Bustos Benjamin et al. \u201cEvaluation of 3D Reconstruction for Cultural Heritage Applications\u201d.2023 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW).2023 1634\u20131643. DOI:10.1109\/ICCVW60793.2023.001797.","DOI":"10.1109\/ICCVW60793.2023.00179"},{"key":"e_1_2_9_36_2","doi-asserted-by":"publisher","DOI":"10.1002\/col.1049"},{"key":"e_1_2_9_37_2","unstructured":"Lin Chen-Hsuan Gao Jun Tang Luming et al.Magic3D: High-Resolution Text-to-3D Content Creation.20233."},{"key":"e_1_2_9_38_2","unstructured":"Luo ShitongandHu Wei.Diffusion Probabilistic Models for 3D Point Cloud Generation.202110."},{"key":"e_1_2_9_39_2","unstructured":"Lee Jae Joong Li Bosheng Beery Sara et al.Tree-D Fusion: Simulation-Ready Tree Dataset from Single Images with Diffusion Priors.20243."},{"key":"e_1_2_9_40_2","doi-asserted-by":"crossref","unstructured":"Li Yuan Liu Zhihao Benes Bedrich et al. \u201cSVDTree: Semantic Voxel Diffusion for Single Image Tree Reconstruction\u201d.2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).2024 4692\u20134702. DOI:10.1109\/CVPR52733.2024.004493.","DOI":"10.1109\/CVPR52733.2024.00449"},{"key":"e_1_2_9_41_2","doi-asserted-by":"crossref","unstructured":"Liu Shichen Li Tianye Chen Weikai andLi Hao. \u201cSoft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning\u201d.Proceedings of the IEEE\/CVF International Conference on Computer Vision.2019 7708\u201377176.","DOI":"10.1109\/ICCV.2019.00780"},{"key":"e_1_2_9_42_2","unstructured":"Maas Andrew L.\u201cRectifier Nonlinearities Improve Neural Network Acoustic Models\u201d.20134."},{"key":"e_1_2_9_43_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11680-4_31"},{"key":"e_1_2_9_44_2","doi-asserted-by":"publisher","DOI":"10.1364\/josaa.36.000789"},{"key":"e_1_2_9_45_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-60243-6_12"},{"key":"e_1_2_9_46_2","unstructured":"Mescheder Lars Oechsle Michael Niemeyer Michael et al. \u201cOccupancy networks: Learning 3D reconstruction in function space\u201d.CVPR.20196 7."},{"key":"e_1_2_9_47_2","unstructured":"Offene Daten \u00d6sterreichs.Offene Daten \u00d6sterreichs.https:\/\/www.data.gv.at. Accessed: 2025-11-03.20257."},{"key":"e_1_2_9_48_2","doi-asserted-by":"crossref","unstructured":"Pan Junyi Han Xiaoguang Chen Weikai et al. \u201cDeep Mesh Reconstruction from Single RGB Images via Topology Modification Networks\u201d.Proceedings of the IEEE International Conference on Computer Vision.2019 9964\u2013997310.","DOI":"10.1109\/ICCV.2019.01006"},{"key":"e_1_2_9_49_2","unstructured":"Poole Ben Jain Ajay Barron Jonathan T. andMildenhall Ben.DreamFusion: Text-to-3D using 2D Diffusion.20223."},{"key":"e_1_2_9_50_2","unstructured":"Peng Songyou Niemeyer Michael Mescheder Lars et al.Convolutional Occupancy Networks.20206."},{"key":"e_1_2_9_51_2","unstructured":"Qian Yue Hou Junhui Kwong Sam andHe Ying.PUGeo-Net: A Geometry-centric Network for 3D Point Cloud Upsampling.202010."},{"key":"e_1_2_9_52_2","doi-asserted-by":"publisher","DOI":"10.1080\/15481603.2023.2171706"},{"key":"e_1_2_9_53_2","unstructured":"Qi Charles R. Su Hao Mo Kaichun andGuibas Leonidas J.PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation.20174."},{"key":"e_1_2_9_54_2","doi-asserted-by":"crossref","unstructured":"Rong Yi Zhou Haoran Xia Kang et al. \u201cRepKPU: Point Cloud Upsampling with Kernel Point Representation and Deformation\u201d.2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).2024 21050\u201321060. doi:10.1109\/CVPR52733.2024.0198910.","DOI":"10.1109\/CVPR52733.2024.01989"},{"key":"e_1_2_9_55_2","unstructured":"Shi Ruoxi Chen Hansheng Zhang Zhuoyang et al.Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model.20233 10."},{"key":"e_1_2_9_56_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.envsci.2005.08.002"},{"issue":"56","key":"e_1_2_9_57_2","first-page":"1929","article-title":"Dropout: A Simple Way to Prevent Neural Networks from Overfitting","volume":"15","author":"Srivastava Nitish","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_9_58_2","doi-asserted-by":"publisher","DOI":"10.1007\/11941439_114"},{"key":"e_1_2_9_59_2","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12282"},{"key":"e_1_2_9_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/38.920627"},{"key":"e_1_2_9_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1141964"},{"key":"e_1_2_9_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3721250.3743024"},{"key":"e_1_2_9_63_2","unstructured":"The Grove 3D.The Grove 3D.https:\/\/www.thegrove3d.com\/. Accessed: 2025-03-13.20253."},{"key":"e_1_2_9_64_2","unstructured":"Tancik Matthew Srinivasan Pratul P. Mildenhall Ben et al.Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains.20205."},{"key":"e_1_2_9_65_2","doi-asserted-by":"publisher","DOI":"10.1145\/1276377.1276486"},{"key":"e_1_2_9_66_2","unstructured":"Wang Zhengyi Lu Cheng Wang Yikai et al.Prolific-Dreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation.20233."},{"key":"e_1_2_9_67_2","unstructured":"Wang Guoqing Wang Zhongdao Tang Pin et al.OccGen: Generative Multi-modal 3D Occupancy Prediction for Autonomous Driving.20245."},{"key":"e_1_2_9_68_2","unstructured":"Wen Beichen Xie Haozhe Chen Zhaoxi et al.3D Scene Generation: A Survey.20253."},{"key":"e_1_2_9_69_2","doi-asserted-by":"publisher","DOI":"10.1145\/1289603.1289610"},{"key":"e_1_2_9_70_2","unstructured":"Xiang Jianfeng Lv Zelong Xu Sicheng et al.Structured 3D Latents for Scalable and Versatile 3D Generation.20253 10."},{"key":"e_1_2_9_71_2","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12744"},{"key":"e_1_2_9_72_2","unstructured":"Yu Tao Feng Runseng Feng Ruoyu et al.Inpaint Anything: Segment Anything Meets Image Inpainting.2023. doi:10.48550\/arXiv.2304.067904."},{"key":"e_1_2_9_73_2","doi-asserted-by":"publisher","DOI":"10.3390\/rs13173428"},{"key":"e_1_2_9_74_2","unstructured":"Yang Yinhui Wang Rui andHuo Yuchi.Rule-based Procedural Tree Modeling Approach.20222."},{"key":"e_1_2_9_75_2","unstructured":"Zhang Richard Isola Phillip Efros Alexei A et al. \u201cThe Unreasonable Effectiveness of Deep Features as a Perceptual Metric\u201d.CVPR.20182 5."},{"key":"e_1_2_9_76_2","unstructured":"Zhou Xiaochen Li Bosheng Benes Bedrich et al.DeepTree: Modeling Trees with Situated Latents.20233."},{"key":"e_1_2_9_77_2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2025.3558312"},{"key":"e_1_2_9_78_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103551"}],"container-title":["Computer Graphics Forum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70366","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/cgf.70366","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70366","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T08:12:30Z","timestamp":1778659950000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/cgf.70366"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,13]]},"references-count":77,"alternative-id":["10.1111\/cgf.70366"],"URL":"https:\/\/doi.org\/10.1111\/cgf.70366","archive":["Portico"],"relation":{},"ISSN":["0167-7055","1467-8659"],"issn-type":[{"value":"0167-7055","type":"print"},{"value":"1467-8659","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,13]]},"assertion":[{"value":"2026-05-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70366"}}