{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T21:40:56Z","timestamp":1764020456885,"version":"build-2065373602"},"reference-count":49,"publisher":"Institution of Engineering and Technology (IET)","issue":"8","license":[{"start":{"date-parts":[[2021,3,3]],"date-time":"2021-03-03T00:00:00Z","timestamp":1614729600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52075404"],"award-info":[{"award-number":["52075404"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Image Processing"],"published-print":{"date-parts":[[2021,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Studying representation learning and generative modelling has been at the core of the 3D learning domain. By leveraging the generative adversarial networks and convolutional neural networks for point\u2010cloud representations, we propose a novel framework, which can directly generate 3D objects represented by point clouds. The novelties of the proposed method are threefold. First, the generative adversarial networks are applied to 3D object generation in the point\u2010cloud space, where the model learns object representation from point clouds independently. In this work, we propose a 3D spatial transformer network, and integrate it into a generation model, whose ability for extracting and reconstructing features for 3D objects can be improved. Second, a point\u2010wise approach is developed to reduce the computational complexity of the proposed network. Third, an evaluation system is proposed to measure the performance of our model by employing various categories and methods, and the error, considered as the difference between synthesized objects and raw objects are quantitatively compared, is less than 2.8%. Extensive experiments on benchmark dataset show that this method has a strong ability to generate 3D objects in the point\u2010cloud space, and the synthesized objects have slight differences with man\u2010made 3D objects.<\/jats:p>","DOI":"10.1049\/ipr2.12146","type":"journal-article","created":{"date-parts":[[2021,3,4]],"date-time":"2021-03-04T00:23:02Z","timestamp":1614817382000},"page":"1745-1758","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Constructing an efficient and adaptive learning model for 3D object generation"],"prefix":"10.1049","volume":"15","author":[{"given":"Jiwei","family":"Hu","sequence":"first","affiliation":[{"name":"School of Information Engineering Wuhan University of Technology  Wuhan China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5917-2294","authenticated-orcid":false,"given":"Wupeng","family":"Deng","sequence":"additional","affiliation":[{"name":"School of Information Engineering Wuhan University of Technology  Wuhan China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information Engineering Wuhan University of Technology  Wuhan China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kin\u2010Man","family":"Lam","sequence":"additional","affiliation":[{"name":"Department of Electronic and Information Engineering The Hong Kong Polytechnic University  Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ping","family":"Lou","sequence":"additional","affiliation":[{"name":"School of Information Engineering Wuhan University of Technology  Wuhan China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"265","published-online":{"date-parts":[[2021,3,3]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.04.017"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1049\/iet-ipr.2019.1152"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1049\/iet-ipr.2019.0532"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1049\/iet-ipr.2016.0630"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.11.029"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.04.010"},{"key":"e_1_2_8_8_1","doi-asserted-by":"crossref","unstructured":"Charles Q. et\u00a0al.:PointNet: Deep learning on point sets for 3D classification and segmentation. In:Proceedings of CVPR Honolulu HI pp.77\u201385(2017)","DOI":"10.1109\/CVPR.2017.16"},{"key":"e_1_2_8_9_1","unstructured":"Charles Q. et\u00a0al.:PointNet++: Deep hierarchical feature learning on point sets in a metric space. In:Proceedings of NIPS Long Beach CA pp.5100\u20135109(2017)"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2672198"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2374357"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2018.09.051"},{"key":"e_1_2_8_13_1","unstructured":"Wu Z. et\u00a0al.:3D ShapeNets: A deep representation for volumetric shapes. In:Proceedings of CVPR Boston MA pp.1912\u20131920(2015)"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2947245"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.04.006"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2992554"},{"key":"e_1_2_8_17_1","unstructured":"Romain L. et\u00a0al.:Information constraints on auto\u2010encoding variational Bayes. In:Proceedings of NIPS Montreal Canada pp.6114\u20136125(2018)"},{"key":"e_1_2_8_18_1","unstructured":"Goodfellow L. et\u00a0al.:Generative adversarial nets. In:Proceedings of NIPS Montreal Canada pp.2672\u20132680(2014)"},{"key":"e_1_2_8_19_1","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"Radford A.","year":"2016","journal-title":"arXiv: 1511.06434"},{"key":"e_1_2_8_20_1","doi-asserted-by":"crossref","unstructured":"Girdhar R. et\u00a0al.:Leaning a predictable and generative vector representation for objects. In:Proceedings of ECCV Amsterdam Netherlands pp.484\u2013499(2016)","DOI":"10.1007\/978-3-319-46466-4_29"},{"key":"e_1_2_8_21_1","doi-asserted-by":"crossref","unstructured":"Su H. et\u00a0al.:Render for cnn: Viewpoint estimation in images using CNNS trained with rendered 3D model view. In:Proceedings of ICCV Santiago Chile pp.2686\u20132694(2015)","DOI":"10.1109\/ICCV.2015.308"},{"key":"e_1_2_8_22_1","unstructured":"Wu J. Zhang C. Xue T. et\u00a0al.:Learning a probabilistic latent space of object shapes via 3D generative\u2010adversarial modeling. In:Proceedings of NIPS Barcelona Spain pp.82\u201390(2016)"},{"key":"e_1_2_8_23_1","doi-asserted-by":"crossref","unstructured":"Yang B. et\u00a0al.:3D object reconstruction from a single depth view with adversarial learning.Proceedings of ICCVW Venice Italy pp.679\u2013688(2017)","DOI":"10.1109\/ICCVW.2017.86"},{"key":"e_1_2_8_24_1","unstructured":"Jaderberg M. et\u00a0al.:Spatial transformer networks. In:Proceedings of NIPS Montreal Canada pp.2017\u20132025(2015)"},{"key":"e_1_2_8_25_1","doi-asserted-by":"crossref","unstructured":"Maturana D. Scherer S.:Voxnet: A 3d convolutional neural network for real\u2010time object recognition. In:Proceedings of IROS Hamburg Germany pp.922\u2013928(2015)","DOI":"10.1109\/IROS.2015.7353481"},{"key":"e_1_2_8_26_1","doi-asserted-by":"crossref","unstructured":"Minto L. Zanuttigh P. Pagnutti G.:Deep learning for 3D shape classification based on volumetric density and surface approximation clues. In:Proceedings of VISIGRAPP Funchal Madeira Portugal pp.337\u2013324(2018)","DOI":"10.5220\/0006619103170324"},{"key":"e_1_2_8_27_1","unstructured":"Li Y. et\u00a0al.:Fpnn: Field probing neural networks for 3D data. In:Proceedings of NIPS Barcelona Spain pp.307\u2013315(2016)"},{"key":"e_1_2_8_28_1","doi-asserted-by":"crossref","unstructured":"Qi C.R. Su H. Niebner M. et\u00a0al.:Volumetric and multi\u2010view CNNS for object classification on 3D data. In:Proceedings of CVPR Las Vegas NV pp.5648\u20135656(2016)","DOI":"10.1109\/CVPR.2016.609"},{"key":"e_1_2_8_29_1","doi-asserted-by":"crossref","unstructured":"Su H. Maji S. Kalogerakis E. et\u00a0al.:Multi\u2010view convolutional neural networks for 3D shape recognition. In:Proceedings of ICCV Santiago Chile pp.945\u2013953(2015)","DOI":"10.1109\/ICCV.2015.114"},{"key":"e_1_2_8_30_1","doi-asserted-by":"publisher","DOI":"10.1049\/iet-ipr.2017.1076"},{"key":"e_1_2_8_31_1","doi-asserted-by":"crossref","unstructured":"Yu T. Meng J. Yuan J.:Multi\u2010view harmonized bilinear network for 3D object recognition. In:Proceedings of CVPR Salt Lake City UT pp.186\u2013194(2018)","DOI":"10.1109\/CVPR.2018.00027"},{"key":"e_1_2_8_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185551"},{"key":"e_1_2_8_33_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12694"},{"key":"e_1_2_8_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.05.031"},{"key":"e_1_2_8_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.03.002"},{"key":"e_1_2_8_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2015.2480802"},{"key":"e_1_2_8_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.05.010"},{"key":"e_1_2_8_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2017.12.001"},{"key":"e_1_2_8_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2916689"},{"key":"e_1_2_8_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2016.2546307"},{"key":"e_1_2_8_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2016.2517076"},{"key":"e_1_2_8_42_1","unstructured":"Ishaan G. et\u00a0al.:Improved training of wasserstein GANs. In:Proceedings of NIPS Long Beach CA pp.5768\u20135778(2017)"},{"key":"e_1_2_8_43_1","unstructured":"Youssef M. Tom S. Vaibhava G.:McGAN: Mean and covariance feature matching GAN. In:Proceedings of ICML Sydney Australia pp.3885\u20133899(2017)"},{"key":"e_1_2_8_44_1","unstructured":"Panos A. et\u00a0al.:Learning representations and generative models for 3D point clouds. In:Proceedings of ICML Stockholm Sweden pp.67\u201385(2018)"},{"key":"e_1_2_8_45_1","doi-asserted-by":"crossref","unstructured":"Yang Y. et\u00a0al.:FoldingNet: Point cloud auto\u2010encoder via deep grid deformation. In:Proceedings of CVPR Salt Lake City UT pp.206\u2013215(2018)","DOI":"10.1109\/CVPR.2018.00029"},{"key":"e_1_2_8_46_1","unstructured":"Li C. et\u00a0al.:Point cloud GAN. In:Proceedings of ICLR New Orleans LA(2019)"},{"key":"e_1_2_8_47_1","doi-asserted-by":"crossref","unstructured":"Sarmad M. Lee H.J. Kim Y.M.:RL\u2010GAN\u2010Net: a reinforcement learning agent controlled GAN network for real\u2010time point cloud shape completion. arXiv: 1904.12304 (2019)","DOI":"10.1109\/CVPR.2019.00605"},{"key":"e_1_2_8_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.10.013"},{"key":"e_1_2_8_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.04.006"},{"key":"e_1_2_8_50_1","doi-asserted-by":"crossref","unstructured":"Sharma A. Grau O. Fritz M.:VConv\u2010dae: Deep volumetric shape learning without object labels. In:Proceedings of the ECCV Amsterdam Netherlands pp.236\u2013250(2016)","DOI":"10.1007\/978-3-319-49409-8_20"}],"container-title":["IET Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.12146","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/ipr2.12146","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.12146","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T06:16:51Z","timestamp":1761632211000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/ipr2.12146"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,3]]},"references-count":49,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2021,6]]}},"alternative-id":["10.1049\/ipr2.12146"],"URL":"https:\/\/doi.org\/10.1049\/ipr2.12146","archive":["Portico"],"relation":{},"ISSN":["1751-9659","1751-9667"],"issn-type":[{"type":"print","value":"1751-9659"},{"type":"electronic","value":"1751-9667"}],"subject":[],"published":{"date-parts":[[2021,3,3]]},"assertion":[{"value":"2020-12-07","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-02-10","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-03-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}