{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T09:21:20Z","timestamp":1778145680409,"version":"3.51.4"},"reference-count":46,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2019,9,23]],"date-time":"2019-09-23T00:00:00Z","timestamp":1569196800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>In this study, a deep learning (DL)-based approach is proposed for the detection and reconstruction of buildings from a single aerial image. The pre-required knowledge to reconstruct the 3D shapes of buildings, including the height data as well as the linear elements of individual roofs, is derived from the RGB image using an optimized multi-scale convolutional\u2013deconvolutional network (MSCDN). The proposed network is composed of two feature extraction levels to first predict the coarse features, and then automatically refine them. The predicted features include the normalized digital surface models (nDSMs) and linear elements of roofs in three classes of eave, ridge, and hip lines. Then, the prismatic models of buildings are generated by analyzing the eave lines. The parametric models of individual roofs are also reconstructed using the predicted ridge and hip lines. The experiments show that, even in the presence of noises in height values, the proposed method performs well on 3D reconstruction of buildings with different shapes and complexities. The average root mean square error (RMSE) and normalized median absolute deviation (NMAD) metrics are about 3.43 m and 1.13 m, respectively for the predicted nDSM. Moreover, the quality of the extracted linear elements is about 91.31% and 83.69% for the Potsdam and Zeebrugge test data, respectively. Unlike the state-of-the-art methods, the proposed approach does not need any additional or auxiliary data and employs a single image to reconstruct the 3D models of buildings with the competitive precision of about 1.2 m and 0.8 m for the horizontal and vertical RMSEs over the Potsdam data and about 3.9 m and 2.4 m over the Zeebrugge test data.<\/jats:p>","DOI":"10.3390\/rs11192219","type":"journal-article","created":{"date-parts":[[2019,9,23]],"date-time":"2019-09-23T11:02:00Z","timestamp":1569236520000},"page":"2219","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":88,"title":["2D Image-To-3D Model: Knowledge-Based 3D Building Reconstruction (3DBR) Using Single Aerial Images and Convolutional Neural Networks (CNNs)"],"prefix":"10.3390","volume":"11","author":[{"given":"Fatemeh","family":"Alidoost","sequence":"first","affiliation":[{"name":"School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran, Tehran 1439957131, Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8014-624X","authenticated-orcid":false,"given":"Hossein","family":"Arefi","sequence":"additional","affiliation":[{"name":"School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran, Tehran 1439957131, Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Federico","family":"Tombari","sequence":"additional","affiliation":[{"name":"Chair for Computer Aided Medical Procedures &amp; Augmented Reality, Faculty of Computer Science, Technical University of Munich, Boltzmannstr. 3, 85748 Garching b. Munich, Germany"},{"name":"Google Inc., 8002 Zurich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2019,9,23]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Kolbe, T.H., Gr\u00f6ger, G., and Pl\u00fcmer, L. (2005, January 21\u201323). CityGML\u2014Interoperable Access to 3D City Models. Proceedings of the Int. Symposium on Geo-information for Disaster Management, Delft, The Netherlands.","DOI":"10.1007\/3-540-27468-5_63"},{"key":"ref_2","unstructured":"Tarsha-Kurdi, F., Landes, T., Grussenmeyer, P., and Koehl, M. (2006, January 19\u201321). Model-Driven and Data-Driven Approaches Using Lidar Data: Analysis and Comparison. Proceedings of the International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, Munich, Germany."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1109\/JSTARS.2017.2781132","article-title":"LiDAR Point Clouds to 3D Urban Models: A Review","volume":"11","author":"Wang","year":"2018","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"125","DOI":"10.14358\/PERS.77.2.125","article-title":"3D Building Model Reconstruction from Multi-view Aerial Imagery and Lidar Data","volume":"77","author":"Cheng","year":"2011","journal-title":"Photogramm. Eng. Remote Sens."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1016\/j.isprsjprs.2011.02.007","article-title":"Building roof modeling from airborne laser scanning data based on level set approach","volume":"66","author":"Kim","year":"2011","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xu, H., Cheng, L., Li, M., and Wang, Y. (2016). Three-Dimensional Reconstruction of Building Roofs from Airborne LiDAR Data Based on a Layer Connection and Smoothness Strategy. Remote Sens., 8.","DOI":"10.3390\/rs8050415"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Yan, Y., Gao, F., Deng, S., and Su, N. (2017). A Hierarchical Building Segmentation in Digital Surface Models for 3D Reconstruction. Sensors, 17.","DOI":"10.3390\/s17020222"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2033","DOI":"10.1109\/TIP.2014.2307475","article-title":"Images as Occlusions of Textures: A Framework for Segmentation","volume":"23","author":"Mccann","year":"2014","journal-title":"IEEE Trans. Image Process."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Awrangjeb, M., Ali, S., and Gilani, N. (2018). An Effective Data-Driven Method for 3-D Building Roof Reconstruction and Robust Change Detection. Remote Sens., 10.","DOI":"10.3390\/rs10101512"},{"key":"ref_10","first-page":"1","article-title":"Structural Approach for Building Reconstruction from a Single DSM","volume":"6","author":"Lafarge","year":"2007","journal-title":"J. Latex Cl. Files"},{"key":"ref_11","unstructured":"Huang, H., Brenner, C., Sester, M., and Hannover, D. (2004, January 1\u20134). 3D Building Roof Reconstruction from Point Clouds via Generative Models Categories and Subject Descriptors. Proceedings of the 19th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, Chicago, IL, USA."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"8107","DOI":"10.3390\/rs6098107","article-title":"3D Building Roof Modeling by Optimizing Primitive\u2019s Parameters Using Constraints from LiDAR Data and Aerial Imagery","volume":"6","author":"Zhang","year":"2014","journal-title":"Remote Sens."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1541","DOI":"10.1109\/LGRS.2015.2412535","article-title":"Model-driven Reconstruction of 3D Buildings Using LiDAR Data","volume":"12","author":"Zheng","year":"2015","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Weng, Q., and Zheng, Y. (2017). A Hybrid Approach for Three-Dimensional Building Reconstruction in Indianapolis from LiDAR Data. Remote Sens., 9.","DOI":"10.3390\/rs9040310"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"6054","DOI":"10.1109\/TGRS.2017.2719738","article-title":"Learning Aerial Image Segmentation from Online Maps","volume":"55","author":"Kaiser","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2325","DOI":"10.1109\/LGRS.2017.2763738","article-title":"Deep Fully Convolutional Networks for the Detection of Informal Settlements in VHR Images","volume":"14","author":"Persello","year":"2017","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Wen, Q., Jiang, K., Wang, W., Liu, Q., Guo, Q., Li, L., and Wang, P. (2019). Automatic building extraction from google earth images under complex backgrounds based on deep instance segmentation network. Sensors, 19.","DOI":"10.3390\/s19020333"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Srivastava, S., Volpi, M., and Tuia, D. (2017, January 23\u201328). Joint Height Estimation and Semantic Labeling of Monocular Aerial Images with CNNs. Proceedings of the 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Fort Worth, TX, USA.","DOI":"10.1109\/IGARSS.2017.8128167"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"794","DOI":"10.1109\/LGRS.2018.2806945","article-title":"IMG2DSM: Height Simulation from Single Imagery Using Conditional Generative Adversarial Net","volume":"5","author":"Ghamisi","year":"2018","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_20","unstructured":"Mou, L., Member, S., Zhu, X.X., and Member, S. (2018). IM2HEIGHT: Height Estimation from Single Monocular Imagery via Fully Residual Convolutional-Deconvolutional Network. arXiv, 1\u201313."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1016\/j.isprsjprs.2019.01.013","article-title":"Height estimation from single aerial images using a deep convolutional encoder-decoder network","volume":"149","author":"Amirkolaee","year":"2019","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Bittner, K., D\u2019Angelo, P., K\u00f6rner, M., and Reinartz, P. (2018). DSM-to-LoD2: Spaceborne Stereo Digital Surface Model Refinement. Remote Sens., 10.","DOI":"10.3390\/rs10121926"},{"key":"ref_23","unstructured":"Axelsson, P.E. (2000, January 16\u201322). DEM generation from laser scanner data using adaptive TIN models. Proceedings of the International Archives of the Photogrammetry and Remote Sensing, Amsterdam, The Netherlands."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","volume":"39","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Laina, I., Rupprecht, C., Belagiannis, V., Tombari, F., and Navab, N. (2016, January 25\u201328). Deeper Depth Prediction with Fully Convolutional Residual Networks. Proceedings of the IEEE International Conference on 3D Vision (3DV), Stanford, CA, USA.","DOI":"10.1109\/3DV.2016.32"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Eigen, D., and Fergus, R. (2015, January 7\u201313). Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture. Proceedings of the International Conference on Computer Vision (ICCV), Washington, DC, USA.","DOI":"10.1109\/ICCV.2015.304"},{"key":"ref_27","unstructured":"Kaiming, H., Xiangyu, Z., Shaoqing, R., and Sun, J. (July, January 26). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1214\/aoms\/1177729586","article-title":"A Stochastic Approximation Method","volume":"22","author":"Robbins","year":"2007","journal-title":"Ann. Math. Stat."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"462","DOI":"10.1214\/aoms\/1177729392","article-title":"Stochastic Estimation of the Maximum of a Regression Function","volume":"23","author":"Kiefer","year":"1952","journal-title":"Ann. Math. Stat."},{"key":"ref_30","unstructured":"Kingma, D.P., and Ba, J.L. (2015, January 7\u20139). Adam: A Method for Stochastic Optimization. Proceedings of the the 3rd International Conference on Learning Representations (ICLR), San Diego, CA, USA."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1681","DOI":"10.3390\/rs5041681","article-title":"Building Reconstruction Using DSM and Orthorectified Images","volume":"5","author":"Arefi","year":"2013","journal-title":"Remote Sens."},{"key":"ref_32","unstructured":"(2019, September 15). ISPRS 2D Semantic Labeling Contest-Potsdam. Available online: http:\/\/www2.isprs.org\/commissions\/comm3\/wg4\/2d-sem-label-potsdam.html."},{"key":"ref_33","unstructured":"(2019, September 15). 2015 IEEE GRSS Data Fusion Contest. Available online: http:\/\/www.grss-ieee.org\/community\/technical-committees\/data-fusion."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Shepard, D. (1968, January 27\u201329). A two-dimensional interpolation function for irregularly-spaced data. Proceedings of the the 1968 ACM National Conference, New York, NY, USA.","DOI":"10.1145\/800186.810616"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"824","DOI":"10.1109\/TPAMI.2008.132","article-title":"Make3D: Learning 3D Scene Structure from a Single Still Image","volume":"12","author":"Saxena","year":"2009","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_36","first-page":"2366","article-title":"Depth Map Prediction from a Single Image using a Multi-Scale Deep Network","volume":"2","author":"Eigen","year":"2014","journal-title":"Int. Conf. Neural Inf. Process. Syst."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Zhao, S., Fu, H., Gong, M., and Tao, D. (2019, January 16\u201320). Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.01002"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Liu, F., Shen, C., and Lin, G. (2015, January 7\u201312). Deep Convolutional Neural Fields for Depth Estimation from a Single Image. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7299152"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Goldman, M., Hassner, T., and Avidan, S. (2019, January 16\u201320). Learn Stereo, Infer Mono: Siamese Networks for Self-Supervised, Monocular, Depth Estimation. Proceedings of the Computer Vision and Pattern Recognition Workshops (CVPRW), Long Beach, CA, USA.","DOI":"10.1109\/CVPRW.2019.00348"},{"key":"ref_40","unstructured":"Li, B., Shen, C., Dai, Y., Van Den Hengel, A., and He, M. (2015, January 7\u201312). Depth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs. Proceedings of the Conf. Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"4676","DOI":"10.1109\/TIP.2018.2832296","article-title":"Learning depth from single images with deep neural network embedding focal length","volume":"27","author":"He","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Li, Z., and Snavely, N. (2018, January 18\u201322). MegaDepth: Learning Single-View Depth Prediction from Internet Photos. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00218"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"McGlone, J.C., and Shufelt, J.A. (1994, January 21\u201323). Projective and object space geometry for monocular building extraction. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition CVPR-94, Seattle, WA, USA.","DOI":"10.1109\/CVPR.1994.323810"},{"key":"ref_44","unstructured":"McKeown, D.M., Bulwinkle, T., Cochran, S., Harvey, W., McGlone, C., and Shufelt, J.A. (2000, January 16\u201322). Performance evaluation for automatic feature extraction. Proceedings of the International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Amsterdam, The Netherlands."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1016\/j.inffus.2004.06.004","article-title":"Using the Dempster-Shafer method for the fusion of LIDAR data and multi-spectral images for building detection","volume":"6","author":"Rottensteiner","year":"2005","journal-title":"Inf. Fusion"},{"key":"ref_46","unstructured":"ISPRS (2019, September 15). ISPRS Test Project on Urban Classification and 3D Building Reconstruction. Available online: http:\/\/www2.isprs.org\/commissions\/comm3\/wg4\/results\/a3_recon.html."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/11\/19\/2219\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T13:23:15Z","timestamp":1760188995000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/11\/19\/2219"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9,23]]},"references-count":46,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2019,10]]}},"alternative-id":["rs11192219"],"URL":"https:\/\/doi.org\/10.3390\/rs11192219","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,9,23]]}}}