{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T06:52:53Z","timestamp":1777704773965,"version":"3.51.4"},"reference-count":43,"publisher":"SAGE Publications","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IFS"],"published-print":{"date-parts":[[2023,11,4]]},"abstract":"<jats:p>Point cloud upsampling can improve the resolutions of point clouds and maintain the forms of point clouds, which has attracted more and more attention in recent years. However, upsampling networks sometimes generate point clouds with unclear contours and deficient topological structures, i.e., the problem of insufficient form fidelity of upsampled point clouds. This paper focuses on the above problem. Firstly, we manage to find the points located at contours or sparse positions of point clouds, i.e., the form describers, and make them multiply correctly. To this end, 3 statistics of points, i.e., local coordinate difference, local normal difference and describing index, are designed to estimate the form describers of the point clouds and rectify the feature aggregation of them with reliable neighboring features. Secondly, we divide points into disjoint levels according to the above statistics and apply K nearest neighbors algorithm to the points of different levels respectively to build an accurate graph. Finally, cascaded networks and graph information are fused and added to the feature aggregation so that the network can learn the topology of objects deeply, enhancing the perception of model toward graph information. Our upsampling model PU-FPG is obtained by combining these 3 parts with upsampling networks. We conduct abundant experiments on PU1K dataset and Semantic3D dataset, comparing the upsampling effects of PU-FPG and previous works in multiple metrics. Compared with the baseline model, the Chamfer distance, the Hausdorff distance and the point-to-surface distance of PU-FPG are reduced by 0.159\u00a0\u00d7\u00a010-3, 2.892\u00a0\u00d7\u00a010-3 and 0.852\u00a0\u00d7\u00a010-3, respectively. This shows that PU-FPG can improve the form fidelity and raise the quality of upsampled point clouds effectively. Our code is publicly available at https:\/\/github.com\/SATURN2021\/PU-FPG.<\/jats:p>","DOI":"10.3233\/jifs-232490","type":"journal-article","created":{"date-parts":[[2023,9,8]],"date-time":"2023-09-08T10:39:41Z","timestamp":1694169581000},"page":"8595-8612","source":"Crossref","is-referenced-by-count":2,"title":["PU-FPG: Point cloud upsampling via form preserving graph convolutional networks"],"prefix":"10.1177","volume":"45","author":[{"given":"Haochen","family":"Wang","sequence":"first","affiliation":[{"name":"School of Science, Beijing University of Civil Engineering and Architecture, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changlun","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Science, Beijing University of Civil Engineering and Architecture, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuang","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Science, Beijing University of Civil Engineering and Architecture, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hengyou","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Science, Beijing University of Civil Engineering and Architecture, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"He","sequence":"additional","affiliation":[{"name":"School of Science, Beijing University of Civil Engineering and Architecture, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haibing","family":"Mu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Communication and Information System, Beijing Jiaotong University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"key":"10.3233\/JIFS-232490_ref1","doi-asserted-by":"crossref","unstructured":"Hoppe H. , DeRose T. , Duchamp T. , McDonald J. and Stuetzle W. , Surface reconstruction from unorganized points, in: Proceedings of the 19th annual conference on computer graphics and interactive techniques (1992). https:\/\/doi.org\/10.1145\/133994.134011","DOI":"10.1145\/133994.134011"},{"key":"10.3233\/JIFS-232490_ref2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2487228.2487237","article-title":"Screened Poisson Surface Reconstruction","volume":"32","author":"Kazhdan","year":"2013","journal-title":"ACM Transactions on Graphics (ToG)"},{"key":"10.3233\/JIFS-232490_ref3","doi-asserted-by":"crossref","unstructured":"Newcombe R.A. , Izadi S. , Hilliges O. , Molyneaux D. , Kim D. , Davison A.J. , Kohi P. , Shotton J. , Hodges S. and Fitzgibbon A. , Kinectfusion: Real-time dense surface mapping and tracking, in: 2011 10th IEEE International Symposium on Mixed and Augmented Reality (2011).","DOI":"10.1109\/ISMAR.2011.6092378"},{"key":"10.3233\/JIFS-232490_ref4","doi-asserted-by":"crossref","unstructured":"Riegler G. , Ulusoy A.O. , Bischof H. and Geiger A. , Octnetfusion: Learning depth fusion from data, in: 2017 IEEE International Conference on 3D Vision (3DV) (2017).","DOI":"10.1109\/3DV.2017.00017"},{"key":"10.3233\/JIFS-232490_ref5","doi-asserted-by":"crossref","unstructured":"Lang A.H. , Vora S. , Caesar H. , Zhou L. , Yang J. and Beijbom O. , Pointpillars: Fast en-coders for object detection from point clouds, in: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (2019).","DOI":"10.1109\/CVPR.2019.01298"},{"key":"10.3233\/JIFS-232490_ref6","doi-asserted-by":"crossref","unstructured":"Wang Y. , Chao W.L. , Garg D. , Hariharan B. , Campbell M. and Weinberger K.Q. , Pseudolidar from visual depth estimation: Bridging the gap in 3d object detection for autonomous driving, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019).","DOI":"10.1109\/CVPR.2019.00864"},{"key":"10.3233\/JIFS-232490_ref7","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1109\/TVCG.2003.1175093","article-title":"Computing and rendering point set surfaces","volume":"9","author":"Alexa","year":"2003","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"key":"10.3233\/JIFS-232490_ref8","doi-asserted-by":"crossref","first-page":"22-es","DOI":"10.1145\/1276377.1276405","article-title":"Parameterization-free projection for geometry reconstruction","volume":"26","author":"Lipman","year":"2007","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"10.3233\/JIFS-232490_ref9","first-page":"1","article-title":"Edge-aware point set resampling","volume":"32","author":"Huang","year":"2013","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"10.3233\/JIFS-232490_ref10","first-page":"1","article-title":"Deep points consolidation","volume":"34","author":"Wu","year":"2015","journal-title":"ACM Transactions on Graphics (ToG)"},{"key":"10.3233\/JIFS-232490_ref11","unstructured":"Qi C.R. , Su H. , Mo K. and Guibas L.J. , PointNet: Deep learning on point sets for 3D classification and segmentation, in: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (2017)."},{"key":"10.3233\/JIFS-232490_ref12","first-page":"5099","article-title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","volume":"30","author":"Qi","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.3233\/JIFS-232490_ref13","doi-asserted-by":"crossref","unstructured":"Yu L. , Li X. , Fu C.W. , Cohen-Or D. and Heng P.A. , Pu-net: Point cloud upsampling network, in: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (2018).","DOI":"10.1109\/CVPR.2018.00295"},{"key":"10.3233\/JIFS-232490_ref14","doi-asserted-by":"crossref","unstructured":"Yifan W. , Wu S. , Huang H. , Cohen-Or D. and Sorkine-Hornung O. , Patch-based progressive 3d point set upsampling, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019).","DOI":"10.1109\/CVPR.2019.00611"},{"key":"10.3233\/JIFS-232490_ref15","doi-asserted-by":"crossref","unstructured":"Li R. , Li X. , Fu C.W. , Cohen-Or D. and Heng P.A. , Pu-gan: a point cloud upsampling adversarial network, in: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV) (2019).","DOI":"10.1109\/ICCV.2019.00730"},{"key":"10.3233\/JIFS-232490_ref16","doi-asserted-by":"crossref","unstructured":"Qian Y. , Hou J. , Kwong S. and He Y. , Pugeo-net: A geometry-centric network for 3d point cloud upsampling, in: European conference on computer vision (ECCV) (2020). https:\/\/doi.org\/10.1007\/978-3-030-58529-7_44","DOI":"10.1007\/978-3-030-58529-7_44"},{"key":"10.3233\/JIFS-232490_ref17","doi-asserted-by":"crossref","unstructured":"Qian G. , Abualshour A. , Li G. , Thabet A. and Ghanem B. , Pu-gcn: Point cloud up-sampling using graph convolutional networks, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021).","DOI":"10.1109\/CVPR46437.2021.01151"},{"key":"10.3233\/JIFS-232490_ref18","doi-asserted-by":"crossref","first-page":"2191","DOI":"10.1145\/3503161.3547777","article-title":"PC2-PU: Patch Correlation and Point Cor-relation for Effective Point Cloud Upsampling","author":"Long","year":"2022","journal-title":"Proceedings of the 30th ACM International Conference on Multimedia"},{"key":"10.3233\/JIFS-232490_ref19","doi-asserted-by":"crossref","unstructured":"Yu L. , Li X. , Fu C.W. , Cohen-Or D. and Heng P.A. , Ec-net: An Edge-Aware Point Set Consolidation Network, in: Proceedings of the European conference on computer vision (ECCV) (2018).","DOI":"10.1007\/978-3-030-01234-2_24"},{"key":"10.3233\/JIFS-232490_ref20","doi-asserted-by":"crossref","first-page":"3206","DOI":"10.1109\/TVCG.2021.3058311","article-title":"Meta-PU: An arbitrary-scale upsampling network for point cloud","volume":"28","author":"Ye","year":"2022","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"key":"10.3233\/JIFS-232490_ref21","doi-asserted-by":"crossref","unstructured":"Li R. , Li X. , Heng P.A. and Fu C.W. , Point cloud upsampling via disentangled refinement, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021).","DOI":"10.1109\/CVPR46437.2021.00041"},{"key":"10.3233\/JIFS-232490_ref22","doi-asserted-by":"crossref","first-page":"8354","DOI":"10.1109\/TIP.2021.3115385","article-title":"Deep magnification-flexible upsampling over 3d point clouds","volume":"30","author":"Qian","year":"2021","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.3233\/JIFS-232490_ref23","doi-asserted-by":"crossref","unstructured":"Feng W. , Li J. , Cai H. , Luo X. and Zhang J. , Neural Points: Point Cloud Representation with Neural Fields for Arbitrary Upsampling, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022).","DOI":"10.1109\/CVPR52688.2022.01808"},{"key":"10.3233\/JIFS-232490_ref24","doi-asserted-by":"crossref","unstructured":"Du H. , Yan X. , Wang J. , Xie D. and Pu S. , Point cloud up-sampling via cascaded refinement network, in: Proceedings of the Asian Conference on Computer Vision (ACCV) (2022).","DOI":"10.1007\/978-3-031-26319-4_7"},{"key":"10.3233\/JIFS-232490_ref25","doi-asserted-by":"crossref","first-page":"7389","DOI":"10.1109\/TIP.2022.3222918","article-title":"PUFA-GAN: A Frequency-Aware Generative Adversarial Network for 3D Point Cloud Upsampling","volume":"31","author":"Liu","year":"2022","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.3233\/JIFS-232490_ref26","unstructured":"Heimann V. , Spruck A. and Kaup A. , Joint Geometry and Attribute Upsampling of Point Clouds Using Frequency-Selective Models with Overlapped Support (2023). arXiv, arXiv:2301.11630."},{"key":"10.3233\/JIFS-232490_ref27","doi-asserted-by":"crossref","first-page":"989","DOI":"10.1145\/3343031.3350960","article-title":"L2g auto-encoder: Understanding point clouds by local-to-global recon-struction with hierarchical self-attention","author":"Liu","year":"2019","journal-title":"Proceedings of the 27th ACM International Conference on Multimedia"},{"key":"10.3233\/JIFS-232490_ref28","doi-asserted-by":"crossref","first-page":"4213","DOI":"10.1109\/TIP.2022.3182266","article-title":"Spu-net: Self-supervised point cloud upsampling by coarse-to-fine reconstruction with self-projection optimization","volume":"31","author":"Liu","year":"2022","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.3233\/JIFS-232490_ref29","first-page":"412","article-title":"Graphvae: Towards generation of small graphs using variational autoencoders","author":"Simonovsky","year":"2018","journal-title":"ICANN 2018:27th International Conference on Artificial Neural Networks"},{"key":"10.3233\/JIFS-232490_ref30","unstructured":"De Cao N. and Kipf T. , MolGAN: An implicit generative model for small molecular graphs, arXiv, arXiv:1805.11973, (2018)."},{"key":"10.3233\/JIFS-232490_ref31","unstructured":"Bruna J. , Zaremba W. , Szlam A. and LeCun Y. , Spectral networks and locally connected networks on graphs, arXiv, arXiv:1312.6203 (2013)."},{"key":"10.3233\/JIFS-232490_ref32","unstructured":"Defferrard M. , Bresson X. and Vandergheynst P. , Convolutional neural networks on graphs with fast localized spectral filtering, Advances in Neural Information Processing Systems 29 (2016)."},{"key":"10.3233\/JIFS-232490_ref33","unstructured":"Kipf T.N. and Welling M. , Semi-supervised classification with graph convolutional networks, arXiv, arXiv:1609.02907 (2016)."},{"key":"10.3233\/JIFS-232490_ref34","unstructured":"Tong Z. , Liang Y. , Sun C. , Rosenblum D.S. and Lim A. , Directed graph convolutional network, arXiv, arXiv:2004.13970 (2020)."},{"key":"10.3233\/JIFS-232490_ref35","unstructured":"Hamilton W. , Ying Z. and Leskovec J. , Inductive representation learning on large graphs, Advances in Neural Information Processing Systems 30 (2017)."},{"key":"10.3233\/JIFS-232490_ref36","first-page":"1","article-title":"Dynamic graph cnn for learning on point clouds","volume":"38","author":"Wang","year":"2019","journal-title":"Acm Transactions on Graphics (tog)"},{"key":"10.3233\/JIFS-232490_ref37","unstructured":"Li G. , Mueller M. et al., Deepgcns: Making gcns go as deep as cnns, IEEE Transactions on Pattern Analysis and Machine Intelligence (2021)."},{"key":"10.3233\/JIFS-232490_ref38","doi-asserted-by":"crossref","unstructured":"Thomas H. , Qi C.R. , Deschaud J.E. , Marcotegui B. , Gou-lette F. and Guibas L.J. , Kpconv: Flexible and deformable con-volution for point clouds, in: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2019).","DOI":"10.1109\/ICCV.2019.00651"},{"key":"10.3233\/JIFS-232490_ref39","doi-asserted-by":"crossref","unstructured":"Li G. , M\u00fcller M. , Thabet A. and Ghanem B. , Deepgcns: Can gcns go as deep as cnns? in: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2019).","DOI":"10.1109\/ICCV.2019.00936"},{"key":"10.3233\/JIFS-232490_ref40","first-page":"6279","article-title":"A Graph-CNN for 3D Point Cloud Classification","author":"Zhang","year":"2018","journal-title":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"},{"key":"10.3233\/JIFS-232490_ref41","unstructured":"Wu H. , Zhang J. and Huang K. , Point Cloud Super Resolution with Adversarial Residual Graph Networks, arXiv, arXiv:1908.02111 (2019)."},{"key":"10.3233\/JIFS-232490_ref42","doi-asserted-by":"crossref","unstructured":"Hackel T. , Savinov N. , Ladicky L. , Wegner J.D. , Schindler K. and Pollefeys M. , Semantic3d.net: A new large-scale point cloud classification benchmark, arXiv, arXiv:1704.03847 (2017).","DOI":"10.5194\/isprs-annals-IV-1-W1-91-2017"},{"key":"10.3233\/JIFS-232490_ref43","unstructured":"Chang A.X. , Funkhouser T. et al., Shapenet: An information-rich 3d model repository, arXiv, arXiv:1512.03012 (2015)."}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JIFS-232490","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:41:58Z","timestamp":1777455718000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JIFS-232490"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,4]]},"references-count":43,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.3233\/jifs-232490","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,4]]}}}