{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T11:06:39Z","timestamp":1769079999974,"version":"3.49.0"},"reference-count":50,"publisher":"MDPI AG","issue":"22","license":[{"start":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T00:00:00Z","timestamp":1699488000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42171331"],"award-info":[{"award-number":["42171331"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"2115 Talent Development Program of China Agricultural University","award":["42171331"],"award-info":[{"award-number":["42171331"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Estimating the complete 3D points of crop plants from incomplete points is vital for phenotyping and smart agriculture management. Compared with the completion of regular man-made objects such as airplanes, chairs, and desks, the completion of corn plant points is more difficult for thin, curled, and irregular corn leaves. This study focuses on MSGRNet+OA, which is based on GRNet, to complete a 3D point cloud of thin corn plants. The developed MSGRNet+OA was accompanied by gridding, multi-scale 3DCNN, gridding reverse, cubic feature sampling, and offset-attention. In this paper, we propose the introduction of a 3D grid as an intermediate representation to regularize the unorganized point cloud, use multi-scale predictive fusion to utilize global information at different scales, and model the geometric features by adding offset-attention to compute the point position offsets. These techniques enable the network to exhibit good adaptability and robustness in dealing with irregular and varying point cloud structures. The accuracy assessment results show that the accuracy of completion using MSGRNet+OA is superlative, with a CD (\u00d710\u22124) of 1.258 and an F-Score@1% of 0.843. MSGRNet+OA is the most effective when compared with other networks (PCN, shape inversion, the original GRNet, SeedFormer, and PMP-Net++), and it improves the accuracy of the CD (\u00d710\u22124)\/F-Score@1% with \u221215.882\/0.404, \u221215.96\/0.450, \u22120.181\/0.018, \u22121.852\/0.274, and \u22121.471\/0.203, respectively. These results reveal that the developed MSGRNet+OA can be used to complete a 3D point cloud of thin corn leaves for phenotyping.<\/jats:p>","DOI":"10.3390\/rs15225289","type":"journal-article","created":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T03:42:40Z","timestamp":1699501360000},"page":"5289","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Completing 3D Point Clouds of Thin Corn Leaves for Phenotyping Using 3D Gridding Convolutional Neural Networks"],"prefix":"10.3390","volume":"15","author":[{"given":"Ying","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Land Science and Technology, China Agricultural University, Beijing 100083, China"},{"name":"Key Laboratory of Remote Sensing for Agri-Hazards, Ministry of Agriculture, Beijing 100083, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8726-5858","authenticated-orcid":false,"given":"Wei","family":"Su","sequence":"additional","affiliation":[{"name":"College of Land Science and Technology, China Agricultural University, Beijing 100083, China"},{"name":"Key Laboratory of Remote Sensing for Agri-Hazards, Ministry of Agriculture, Beijing 100083, China"}]},{"given":"Wancheng","family":"Tao","sequence":"additional","affiliation":[{"name":"College of Land Science and Technology, China Agricultural University, Beijing 100083, China"},{"name":"Key Laboratory of Remote Sensing for Agri-Hazards, Ministry of Agriculture, Beijing 100083, China"}]},{"given":"Ziqian","family":"Li","sequence":"additional","affiliation":[{"name":"College of Land Science and Technology, China Agricultural University, Beijing 100083, China"},{"name":"Key Laboratory of Remote Sensing for Agri-Hazards, Ministry of Agriculture, Beijing 100083, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2677-4210","authenticated-orcid":false,"given":"Xianda","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Land Science and Technology, China Agricultural University, Beijing 100083, China"},{"name":"Key Laboratory of Remote Sensing for Agri-Hazards, Ministry of Agriculture, Beijing 100083, China"}]},{"given":"Ziyue","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Land Science and Technology, China Agricultural University, Beijing 100083, China"},{"name":"Key Laboratory of Remote Sensing for Agri-Hazards, Ministry of Agriculture, Beijing 100083, China"}]},{"given":"Caisen","family":"Xiong","sequence":"additional","affiliation":[{"name":"College of Land Science and Technology, China Agricultural University, Beijing 100083, China"},{"name":"Key Laboratory of Remote Sensing for Agri-Hazards, Ministry of Agriculture, Beijing 100083, China"}]}],"member":"1968","published-online":{"date-parts":[[2023,11,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"532","DOI":"10.1016\/j.rse.2005.01.010","article-title":"Geographic variability in lidar predictions of forest stand structure in the Pacific Northwest","volume":"95","author":"Lefsky","year":"2005","journal-title":"Remote Sens. Environ."},{"key":"ref_2","unstructured":"Hoffmeister, D., Curdt, C., Tilly, N., and Bendig, J. (2010, January 18\u201319). 3D Terrestrial Laser Scanning for Field Crop Modelling. Proceedings of the ISPRS WG VII\/5 Workshop on Remote Sensing Methods for Change Detection and Process Modelling, Cologne, Germany."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1007\/s11427-017-9056-0","article-title":"Crop 3D\u2014A LiDAR based platform for 3D high-throughput crop phenotyping","volume":"61","author":"Guo","year":"2018","journal-title":"Sci. China Life Sci."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1016\/j.tplants.2011.09.005","article-title":"Phenomics\u2014Technologies to relieve the phenotyping bottleneck","volume":"16","author":"Furbank","year":"2011","journal-title":"Trends Plant Sci."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1016\/j.isprsjprs.2016.01.006","article-title":"Terrestrial laser scanning in forest inventories","volume":"115","author":"Liang","year":"2016","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1023\/A:1008112528134","article-title":"Combination of Edge Element and Optical Flow Estimates for 3D-Model-Based Vehicle Tracking in Traffic Image Sequences","volume":"35","author":"Haag","year":"1999","journal-title":"Int. J. Comput. Vis."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Rother, D., and Sapiro, G. (October, January 29). Seeing 3D objects in a single 2D image. Proceedings of the 2009 IEEE 12th International Conference on Computer Vision (ICCV), Kyoto, Japan.","DOI":"10.1109\/ICCV.2009.5459405"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1016\/0004-3702(77)90006-6","article-title":"Description and recognition of curved objects","volume":"8","author":"Nevatia","year":"1977","journal-title":"Artif. Intell."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1016\/0004-3702(86)90052-4","article-title":"Perceptual organization and the representation of natural form","volume":"28","author":"Pentland","year":"1986","journal-title":"Artif. Intell."},{"key":"ref_10","first-page":"1","article-title":"Single-view reconstruction via joint analysis of image and shape collections","volume":"34","author":"Huang","year":"2015","journal-title":"ACM Trans. Graph."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1688","DOI":"10.1104\/pp.114.248971","article-title":"Automated recovery of three-dimensional models of plant shoots from multiple color images","volume":"166","author":"Pound","year":"2014","journal-title":"Plant Physiol."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Kar, A., Tulsiani, S., Carreira, J., and Malik, J. (2015). Category-Specific Object Reconstruction from a Single Image. arXiv.","DOI":"10.1109\/CVPR.2015.7298807"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Landy, M., and Movshon, J.A. (1991). Computational Models of Visual Processing, MIT Press.","DOI":"10.7551\/mitpress\/2002.001.0001"},{"key":"ref_14","unstructured":"Bakshi, S., and Yang, Y. (1994, January 13\u201316). Shape from shading for non-Lambertian surfaces. Proceedings of the International Conference on Image Processing, Austin, TX, USA."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"690","DOI":"10.1109\/34.784284","article-title":"Shape-from-shading: A survey","volume":"21","author":"Zhang","year":"1999","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1167\/12.9.281","article-title":"The perception of shape from shading for Lambertian surfaces and range images","volume":"12","author":"Todd","year":"2012","journal-title":"J. Vis."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1105","DOI":"10.1364\/JOSA.57.001105","article-title":"Theory for Off-Specular Reflection from Roughened Surfaces*","volume":"57","author":"Torrance","year":"1967","journal-title":"J. Opt. Soc. Am. (JOSA)"},{"key":"ref_18","unstructured":"Guan, L., Franco, J., and Pollefeys, M. (2007, January 17\u201322). 3D occlusion inference from silhouette cues. Proceedings of the 2007 IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, MN, USA."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"161","DOI":"10.5566\/ias.1078","article-title":"Shape from Texture Using Locally Scaled Point Processes","volume":"34","author":"Didden","year":"2015","journal-title":"Image Anal. Stereol."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Criminisi, A., and Zisserman, A. (2000, January 11\u201314). Shape from texture: Homogeneity revisited. Proceedings of the British Machine Vision Conference (BMVC), Bristol, UK.","DOI":"10.5244\/C.14.9"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Verbin, D., and Zickler, T. (2020, January 16\u201318). Toward a universal model for shape from texture. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00050"},{"key":"ref_22","first-page":"1","article-title":"Multi-View Stereo: A Tutorial","volume":"9","author":"Furukawa","year":"2015","journal-title":"Now Found. Trends"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1109\/34.481545","article-title":"3D Shape Reconstruction by Using Vanishing Points","volume":"18","author":"Parodi","year":"1996","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1016\/j.isprsjprs.2019.10.011","article-title":"Deep learning for conifer\/deciduous classification of airborne LiDAR 3D point clouds representing individual trees","volume":"158","author":"Hamraz","year":"2019","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"2820","DOI":"10.1109\/TPAMI.2018.2868195","article-title":"Dense 3D Object Reconstruction from a Single Depth View","volume":"41","author":"Bo","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_26","unstructured":"Wu, J., Zhang, C., Xue, T., Freeman, W.T., and Tenenbaum, J.B. (2016, January 27\u201330). Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Gadelha, M., Maji, S., and Wang, R. (2016, January 27\u201330). 3D Shape Induction from 2D Views of Multiple Objects. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/3DV.2017.00053"},{"key":"ref_28","unstructured":"Wu, Z., Song, S., Khosla, A., Yu, F., Zhang, L., Tang, X., and Xiao, J. (2015, January 7\u201312). 3D ShapeNets: A Deep Representation for Volumet-ric Shapes. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA."},{"key":"ref_29","unstructured":"Wu, J., Wang, Y., Xue, T., Sun, X., Freeman, B., and Tenenbaum, J. (2017, January 4\u20139). MarrNet: 3D Shape Reconstruction via 2.5D Sketches. Proceedings of the International Conference on Neural Information Processing, Long Beach, CA, USA."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Riegler, G., Ulusoy, A.O., and Geiger, A. (2016, January 27\u201330). OctNet: Learning Deep 3D Representations at High Resolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.701"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Tatarchenko, M., Richter, S.R., Ranftl, R., Li, Z., Koltun, V., and Brox, T. (2019, January 15\u201320). What Do Single-view 3D Reconstruction Networks Learn?. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00352"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Yuan, W., Khot, T., Held, D., Mertz, C., and Hebert, M. (2018, January 5\u20138). PCN: Point Completion Network. Proceedings of the International Conference on 3D Vision (3DV), Verona, Italy.","DOI":"10.1109\/3DV.2018.00088"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Tchapmi, L.P., Kosaraju, V., Rezatofighi, H., Reid, I., and Savarese, S. (2019, January 15\u201320). TopNet: Structural Point Cloud Decoder. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00047"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Mescheder, L., Oechsle, M., and Niemeyer, M. (2019, January 15\u201320). Occupancy Networks: Learning 3D Reconstruction in Function Space. Proceedings of the Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00459"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Wang, N., Zhang, Y., and Li, Z. (2018, January 8\u201314). Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images. Proceedings of the European Conference on Compuyer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01252-6_4"},{"key":"ref_36","first-page":"2919","article-title":"VoxSegNet: Volumetric CNNs for Semantic Part Segmentation of 3D Shapes","volume":"26","author":"Zongji","year":"2019","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Xie, H., Yao, H., and Zhou, S. (2020, January 23\u201328). GRNet: Gridding Residual Network for Dense Point Cloud Completion. Proceedings of the European Conference on Computer Vision (ECCV 2020), Glasgow, UK.","DOI":"10.1007\/978-3-030-58545-7_21"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"852","DOI":"10.1109\/TPAMI.2022.3159003","article-title":"PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-step Point Moving Paths","volume":"45","author":"Wen","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Zhou, H., Cao, Y., Chu, W., Zhu, J., Lu, T., Tai, Y., and Wang, C. (2022, January 23\u201327). SeedFormer Patch Seeds Based Point Cloud Com-pletion with Upsample Transformer. Proceedings of the European Conference on Computer Vision (ECCV), Tel Aviv, Israel.","DOI":"10.1007\/978-3-031-20062-5_24"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Li, S., Gao, P., Tan, X., and Wei, M. (2023, January 18\u201322). ProxyFormer: Proxy Alignment Assisted Point Cloud Completion with Missing Part Sensitive Transformer. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.00913"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"10120","DOI":"10.1109\/LRA.2022.3193239","article-title":"Contrastive 3D Shape Completion and Reconstruction for Agricultural Robots Using RGB-D Frames","volume":"7","author":"Magistri","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_42","unstructured":"Dai, A., Qi, C.R., and Nie\u00dfner, M. (July, January 21). Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A. (2016, January 12\u201317). Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning. Proceedings of the AAAI Conference on Artificial Intelligence, Phoenix, AZ, USA.","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref_44","unstructured":"Wu, D., Wang, Y., and Xia, S. (2020, January 30). Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets. Proceedings of the International Conference on Learning Representations (ICLR), Addis Ababa, Ethiopia."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Zunair, H., and Hamza, A.B. (2021). Sharp U-Net: Depthwise convolutional network for biomedical image segmentation. Comput. Biol. Med., 136.","DOI":"10.1016\/j.compbiomed.2021.104699"},{"key":"ref_46","first-page":"412","article-title":"A Model of Saliency-Based Visual Attention for Rapid Scene Analysis","volume":"7","author":"Vinay","year":"2019","journal-title":"Int. J. Recent Technol. Eng. (IJRTE)"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1007\/s41095-021-0229-5","article-title":"PCT: Point cloud transformer","volume":"7","author":"Guo","year":"2021","journal-title":"Comput. Vis. Media"},{"key":"ref_48","unstructured":"Fan, H., Su, H., and Guibas, L.J. (July, January 26). A Point Set Generation Network for 3D Object Reconstruction from a Single Image. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA."},{"key":"ref_49","unstructured":"Diederik, P., and Kingma, J.B. (2014, January 14\u201316). Adam: A Method for Stochastic Optimization. Proceedings of the International Conference for Learning Representations, San Diego, CA, USA."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Zhang, J., Chen, X., and Cai, Z. (2021, January 20\u201325). Unsupervised 3D Shape Completion through GAN Inversion. Proceedings of the Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00181"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/22\/5289\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:19:45Z","timestamp":1760131185000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/22\/5289"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,9]]},"references-count":50,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2023,11]]}},"alternative-id":["rs15225289"],"URL":"https:\/\/doi.org\/10.3390\/rs15225289","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,9]]}}}