{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T18:02:58Z","timestamp":1770832978516,"version":"3.50.1"},"reference-count":54,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the National Natural Science of China","award":["41961065"],"award-info":[{"award-number":["41961065"]}]},{"name":"the Guangxi Innovative Development Grand Program","award":["Guike AD19254002, GuikeAA18118038, and GuikeAA18242048"],"award-info":[{"award-number":["Guike AD19254002, GuikeAA18118038, and GuikeAA18242048"]}]},{"name":"Guangxi Natural Science Foundation for Innovation Research Team","award":["2019GXNSFGA245001"],"award-info":[{"award-number":["2019GXNSFGA245001"]}]},{"name":"Guilin Research and Development Plan Program","award":["201902102"],"award-info":[{"award-number":["201902102"]}]},{"name":"the National Key Research and Development Program of China","award":["2016YFB0502501"],"award-info":[{"award-number":["2016YFB0502501"]}]},{"name":"Guangxi Key Laboratory of Spatial Information and Geomatics","award":["19-185-10-12"],"award-info":[{"award-number":["19-185-10-12"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>The digital elevation model (DEM) acquired through photogrammetry or LiDAR usually exposes voids due to phenomena such as instrumentation artifact, ground occlusion, etc. For this reason, this paper proposes a multiattention generative adversarial network model to fill the voids. In this model, a multiscale feature fusion generation network is proposed to initially fill the voids, and then a multiattention filling network is proposed to recover the detailed features of the terrain surrounding the void area, and the channel-spatial cropping attention mechanism module is proposed as an enhancement of the network. Spectral normalization is added to each convolution layer in the discriminator network. Finally, the training of the model by a combined loss function, including reconstruction loss and adversarial loss, is optimized. Three groups of experiments with four different types of terrains, hillsides, valleys, ridges and hills, are conducted for validation of the proposed model. The experimental results show that (1) the structural similarity surrounding terrestrial voids in the three types of terrains (i.e., hillside, valley, and ridge) can reach 80\u201390%, which implies that the DEM accuracy can be improved by at least 10% relative to the traditional interpolation methods (i.e., Kriging, IDW, and Spline), and can reach 57.4%, while other deep learning models (i.e., CE, GL and CR) only reach 43.2%, 17.1% and 11.4% in the hilly areas, respectively. Therefore, it can be concluded that the structural similarity surrounding the terrestrial voids filled using the model proposed in this paper can reach 60\u201390% upon the types of terrain, such as hillside, valley, ridge, and hill.<\/jats:p>","DOI":"10.3390\/rs14051206","type":"journal-article","created":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T21:25:14Z","timestamp":1646169914000},"page":"1206","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":47,"title":["Voids Filling of DEM with Multiattention Generative Adversarial Network Model"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8295-0496","authenticated-orcid":false,"given":"Guoqing","family":"Zhou","sequence":"first","affiliation":[{"name":"Guangxi Key Laboratory of Spatial Information and Geomatics, Guilin University of Technology, Guilin 541004, China"},{"name":"College of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541004, China"}]},{"given":"Bo","family":"Song","sequence":"additional","affiliation":[{"name":"Guangxi Key Laboratory of Spatial Information and Geomatics, Guilin University of Technology, Guilin 541004, China"},{"name":"College of Earth Sciences, Guilin University of Technology, Guilin 541004, China"}]},{"given":"Peng","family":"Liang","sequence":"additional","affiliation":[{"name":"Guangxi Key Laboratory of Spatial Information and Geomatics, Guilin University of Technology, Guilin 541004, China"},{"name":"College of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541004, China"}]},{"given":"Jiasheng","family":"Xu","sequence":"additional","affiliation":[{"name":"Guangxi Key Laboratory of Spatial Information and Geomatics, Guilin University of Technology, Guilin 541004, China"},{"name":"College of Earth Sciences, Guilin University of Technology, Guilin 541004, China"}]},{"given":"Tao","family":"Yue","sequence":"additional","affiliation":[{"name":"Guangxi Key Laboratory of Spatial Information and Geomatics, Guilin University of Technology, Guilin 541004, China"},{"name":"College of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541004, China"}]}],"member":"1968","published-online":{"date-parts":[[2022,3,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Han, H., Zeng, Q., and Jiao, J. (2021). Quality Assessment of TanDEM-X DEMs, SRTM and ASTER GDEM on Selected Chinese Sites. Remote Sens., 13.","DOI":"10.3390\/rs13071304"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Zhou, G. (2021). Urban High-Resolution Remote Sensing Algorithms and Modeling, CRC Press, Tylor& Francis Group.","DOI":"10.1201\/9781003082439"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/j.isprsjprs.2019.11.015","article-title":"TanDEM-X DEM: Comparative performance review employing LIDAR data and DSMs","volume":"160","author":"Div","year":"2020","journal-title":"ISPRS J. Photogramm."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Liu, Z., Han, L., Yang, Z., Cao, H., Guo, F., Guo, J., and Ji, Y. (2021). Evaluating the Vertical Accuracy of DEM Generated from ZiYuan-3 Stereo Images in Understanding the Tectonic Morphology of the Qianhe Basin, China. Remote Sens., 13.","DOI":"10.3390\/rs13061203"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1586","DOI":"10.1109\/TGRS.2015.2483641","article-title":"An Integrated Active Contour Approach to Shoreline Mapping Using HSI and DEM","volume":"54","author":"Sukcharoenpong","year":"2016","journal-title":"IEEE T. Geosci. Remote."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1016\/j.energy.2015.03.094","article-title":"Evaluation of the wave energy conditions along the coastal waters of Beibu Gulf, China","volume":"85","author":"Zhou","year":"2015","journal-title":"Energy"},{"key":"ref_7","first-page":"1","article-title":"Monitoring of Historical Glacier Recession in Yulong Mountain by the Integration of Multisource Remote Sensing Data","volume":"11","author":"Yue","year":"2018","journal-title":"IEEE J.-Stars"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1534","DOI":"10.1109\/TGRS.2020.3023135","article-title":"Selection of Optimal Building Facade Texture Images From UAV-Based Multiple Oblique Image Flows","volume":"59","author":"Zhou","year":"2021","journal-title":"IEEE T. Geosci. Remote."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"683","DOI":"10.1080\/01431161.2019.1646939","article-title":"Impacts of Urban land surface temperature on tract landscape pattern, physical and social variables","volume":"41","author":"Zhou","year":"2020","journal-title":"Int. J. Remote Sens."},{"key":"ref_10","unstructured":"Maune, D.F., and Nayegandhi, A. (2019). Digital Elevation Model Technologies and Applications: The DEM Users Manual, ASPRS."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1016\/j.cageo.2003.07.005","article-title":"Analysis of errors of derived slope and aspect related to DEM data properties","volume":"30","author":"Zhou","year":"2004","journal-title":"Comput. Geosci. UK"},{"key":"ref_12","first-page":"400","article-title":"Coastal 3-D Morphological Change Analysis Using LiDAR Series Data: A Case Study of Assateague Island National Seashore","volume":"25","author":"Zhou","year":"2009","journal-title":"J. Coastal Res."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1016\/j.rse.2017.12.037","article-title":"Artefact detection in global digital elevation models (DEMs): The Maximum Slope Approach and its application for complete screening of the SRTM v4. 1 and MERIT DEMs","volume":"207","author":"Hirt","year":"2018","journal-title":"Remote Sens. Environ."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1016\/j.isprsjprs.2018.09.009","article-title":"DEM refinement by low vegetation removal based on the combination of full waveform data and progressive TIN densification","volume":"146","author":"Ma","year":"2018","journal-title":"ISPRS J. Photogramm."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1941","DOI":"10.1109\/TGRS.2019.2951178","article-title":"Estimation of Variance and Spatial Correlation Width for Fine-Scale Measurement Error in Digital Elevation Model","volume":"58","author":"Uss","year":"2020","journal-title":"IEEE T. Geosci. Remote"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Shepard, D. (1968, January 27\u201329). A two-dimensional interpolation function for irregularly-spaced data. Proceedings of the 1968 23rd ACM National Conference, New York, NY, USA.","DOI":"10.1145\/800186.810616"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"983","DOI":"10.1080\/13658810601169899","article-title":"An evaluation of void-filling interpolation methods for SRTM data","volume":"21","author":"Reuter","year":"2007","journal-title":"Int. J. Geogr. Inf. Sci."},{"key":"ref_18","first-page":"213","article-title":"Filling SRTM voids: The delta surface fill method","volume":"72","author":"Grohman","year":"2006","journal-title":"Photogramm. Eng. Remote Sens."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1016\/j.isprsjprs.2007.05.004","article-title":"Filling the voids in the SRTM elevation model\u2014A TIN-based delta surface approach","volume":"62","author":"Luedeling","year":"2007","journal-title":"ISPRS J. Photogramm."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"646","DOI":"10.1002\/esp.1293","article-title":"Field mapping and digital elevation modelling of submerged and unsubmerged hydraulic jump regions in a bedrock step\u2013pool channel","volume":"31","author":"Pasternack","year":"2006","journal-title":"Earth Surf. Proc. Land."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1016\/j.cagd.2012.12.005","article-title":"Polynomial splines over locally refined box-partitions","volume":"30","author":"Dokken","year":"2013","journal-title":"Comput. Aided Geom. Des."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1016\/j.cag.2015.03.006","article-title":"Locally refined spline surfaces for representation of terrain data","volume":"49","author":"Skytt","year":"2015","journal-title":"Comput. Graph."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1016\/j.geomorph.2009.06.024","article-title":"Influence of survey strategy and interpolation model on DEM quality","volume":"112","author":"Heritage","year":"2009","journal-title":"Geomorphology"},{"key":"ref_24","first-page":"133","article-title":"A comparative analysis of different DEM interpolation methods","volume":"16","author":"Arun","year":"2013","journal-title":"Egypt. J. Remote Sens. Space Sci."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1080\/01431160601075509","article-title":"Filling voids of SRTM with Landsat sensor imagery in rugged terrain","volume":"28","author":"Ling","year":"2007","journal-title":"Int. J. Remote Sens."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Hogan, J., and Smith, W.A. (2010, January 13\u201318). Refinement of digital elevation models from shadowing cues. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, USA.","DOI":"10.1109\/CVPR.2010.5540083"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2815","DOI":"10.1080\/01431161.2011.621465","article-title":"A high-accuracy method for filling voids and its verification","volume":"33","author":"Yue","year":"2012","journal-title":"Int. J. Remote Sens."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"819","DOI":"10.1016\/j.jclepro.2014.08.080","article-title":"A high-accuracy method for filling voids on remotely sensed XCO2 surfaces and its verification","volume":"103","author":"Yue","year":"2015","journal-title":"J. Clean. Prod."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/j.isprsjprs.2016.11.002","article-title":"High-quality seamless DEM generation blending SRTM-1, ASTER GDEM v2 and ICESat\/GLAS observations","volume":"123","author":"Yue","year":"2017","journal-title":"ISPRS J. Photogramm."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Dong, G., Chen, F., and Ren, P. (2018, January 22\u201327). Filling SRTM void data via conditional adversarial networks. Proceedings of the IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Valencia, Spain.","DOI":"10.1109\/IGARSS.2018.8518992"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"6333","DOI":"10.1109\/TGRS.2013.2296232","article-title":"Extracting Ground-Level DEM From SRTM DEM in Forest Environments Based on Mathematical Morphology","volume":"52","author":"Liu","year":"2014","journal-title":"IEEE T. Geosci. Remote"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., and Efros, A.A. (2016, January 27\u201330). Context Encoders: Feature Learning by Inpainting. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref_33","first-page":"1","article-title":"Hierarchical spatial features learning with deep CNNs for very high-resolution remote sensing image classification","volume":"39","author":"Guangyun","year":"2018","journal-title":"Int. J. Remote Sens."},{"key":"ref_34","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014). Generative Adversarial Networks. arXiv, Available online: https:\/\/arxiv.org\/abs\/1406.2661."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1145\/3072959.3073659","article-title":"Globally and locally consistent image completion","volume":"36","author":"Iizuka","year":"2017","journal-title":"ACM Trans. Graph."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Liu, G., Reda, F.A., Shih, K.J., Wang, T.C., Tao, A., and Catanzaro, B. (2018, January 8\u201314). Image Inpainting for Irregular Holes Using Partial Convolutions. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01252-6_6"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yue, L., and Liu, X. (2019). Void Filling of Digital Elevation Models with a Terrain Texture Learning Model Based on Generative Adversarial Networks. Remote Sens., 11.","DOI":"10.3390\/rs11232829"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"111602","DOI":"10.1016\/j.rse.2019.111602","article-title":"A shadow constrained conditional generative adversarial net for SRTM data restoration","volume":"237","author":"Dong","year":"2020","journal-title":"Remote Sens. Environ."},{"key":"ref_39","unstructured":"Hui, Z., Li, J., Wang, X., and Gao, X. (2020). Image fine-grained inpainting. arXiv, Available online: https:\/\/arxiv.org\/abs\/2002.02609."},{"key":"ref_40","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., and Kavukcuoglu, K. (2015). Spatial Transformer Networks. arXiv, Available online: https:\/\/arxiv.org\/abs\/1506.02025."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., and Sun, G. (2018, January 18\u201322). Squeeze-and-excitation networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Yu, J., Lin, Z., Yang, J., Shen, X., Lu, X., and Huang, T.S. (2018, January 18\u201322). Generative image inpainting with contextual attention. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00577"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Wang, N., Li, J., Zhang, L., and Du, B. (2019, January 10\u201316). MUSICAL: Multi-Scale Image Contextual Attention Learning for Inpainting. Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI), Macao, China.","DOI":"10.24963\/ijcai.2019\/520"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1645","DOI":"10.1109\/LGRS.2019.2902222","article-title":"Void filling of digital elevation models with deep generative models","volume":"16","author":"Gavriil","year":"2019","journal-title":"IEEE Geosci. Remote Sens."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Zhang, C., Shi, S., Ge, Y., Liu, H., and Cui, W. (2020). DEM Void Filling Based on Context Attention Generation Model. ISPRS Int. J. Geo-Inf., 9.","DOI":"10.3390\/ijgi9120734"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"735","DOI":"10.1080\/13658816.2019.1599122","article-title":"Spatial interpolation using conditional generative adversarial neural networks","volume":"34","author":"Zhu","year":"2020","journal-title":"Int. J. Geogr. Inf. Sci."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"112818","DOI":"10.1016\/j.rse.2021.112818","article-title":"Integrating topographic knowledge into deep learning for the void-filling of digital elevation models","volume":"269","author":"Li","year":"2022","journal-title":"Remote Sens. Environ."},{"key":"ref_48","unstructured":"Yu, J., Lin, Z., Yang, J., Shen, X., Lu, X., and Huang, T.S. (November, January 27). Free-form image inpainting with gated convolution. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Seoul, Korea."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Mehta, S., Rastegari, M., Caspi, A., Shapiro, L., and Hajishirzi, H. (2018, January 8\u201314). Espnet: Efficient spatial pyramid of dilated convolutions for semantic segmentation. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01249-6_34"},{"key":"ref_50","unstructured":"Miyato, T., Kataoka, T., Koyama, M., and Yoshida, Y. (2018). Spectral normalization for generative adversarial networks. arXiv, Available online: https:\/\/arxiv.org\/abs\/1802.05957."},{"key":"ref_51","unstructured":"Arjovsky, M., Chintala, S., and Bottou, L. (2017). Wasserstein GAN. arXiv, Available online: https:\/\/arxiv.org\/abs\/1701.07875."},{"key":"ref_52","unstructured":"Kingma, D.P., and Ba, J. (2017). Adam: A method for stochastic optimization. arXiv, Available online: https:\/\/arxiv.org\/abs\/1412.6980."},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Jiang, B., Chen, G., Wang, J., Ma, H., Wang, L., Wang, Y., and Chen, X. (2021). Deep Dehazing Network for Remote Sensing Image with Non-Uniform Haze. Remote Sens., 13.","DOI":"10.3390\/rs13214443"},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: From error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/5\/1206\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:30:02Z","timestamp":1760135402000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/5\/1206"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,1]]},"references-count":54,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2022,3]]}},"alternative-id":["rs14051206"],"URL":"https:\/\/doi.org\/10.3390\/rs14051206","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,1]]}}}