{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T02:57:29Z","timestamp":1760151449834,"version":"build-2065373602"},"reference-count":53,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2022,3,25]],"date-time":"2022-03-25T00:00:00Z","timestamp":1648166400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF-2021R1I1A1A01048455"],"award-info":[{"award-number":["NRF-2021R1I1A1A01048455"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Unlike 2-dimensional (2D) images, direct 3-dimensional (3D) point cloud processing using deep neural network architectures is challenging, mainly due to the lack of explicit neighbor relationships. Many researchers attempt to remedy this by performing an additional voxelization preprocessing step. However, this adds additional computational overhead and introduces quantization error issues, limiting an accurate estimate of the underlying structure of objects that appear in the scene. To this end, in this article, we propose a deep network that can directly consume raw unstructured point clouds to perform object classification and part segmentation. In particular, a Deep Feature Transformation Network (DFT-Net) has been proposed, consisting of a cascading combination of edge convolutions and a feature transformation layer that captures the local geometric features by preserving neighborhood relationships among the points. The proposed network builds a graph in which the edges are dynamically and independently calculated on each layer. To achieve object classification and part segmentation, we ensure point order invariance while conducting network training simultaneously\u2014the evaluation of the proposed network has been carried out on two standard benchmark datasets for object classification and part segmentation. The results were comparable to or better than existing state-of-the-art methodologies. The overall score obtained using the proposed DFT-Net is significantly improved compared to the state-of-the-art methods with the ModelNet40 dataset for object categorization.<\/jats:p>","DOI":"10.3390\/s22072512","type":"journal-article","created":{"date-parts":[[2022,3,27]],"date-time":"2022-03-27T21:31:25Z","timestamp":1648416685000},"page":"2512","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["DFT-Net: Deep Feature Transformation Based Network for Object Categorization and Part Segmentation in 3-Dimensional Point Clouds"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5813-304X","authenticated-orcid":false,"given":"Mehak","family":"Sheikh","sequence":"first","affiliation":[{"name":"Department of Computer Science, National University of Modern Languages, NUML, Rawalpindi 46000, Pakistan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8151-0413","authenticated-orcid":false,"given":"Muhammad Adeel","family":"Asghar","sequence":"additional","affiliation":[{"name":"Department of Computer Science, National University of Modern Languages, NUML, Rawalpindi 46000, Pakistan"}]},{"given":"Ruqia","family":"Bibi","sequence":"additional","affiliation":[{"name":"Department of Software Engineering, National University of Modern Languages, NUML, Rawalpindi 46000, Pakistan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5035-9375","authenticated-orcid":false,"given":"Muhammad Noman","family":"Malik","sequence":"additional","affiliation":[{"name":"Department of Computer Science, National University of Modern Languages, NUML, Rawalpindi 46000, Pakistan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8050-8431","authenticated-orcid":false,"given":"Mohammad","family":"Shorfuzzaman","sequence":"additional","affiliation":[{"name":"Department of Computer Science, College of Computers and Information Technology, Taif University, P.O. Box 11099, Taif 21944, Saudi Arabia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2284-0479","authenticated-orcid":false,"given":"Raja Majid","family":"Mehmood","sequence":"additional","affiliation":[{"name":"Information and Communication Technology Department, School of Electrical and Computer Engineering, Xiamen University Malaysia, Sepang 43900, Malaysia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6081-0852","authenticated-orcid":false,"given":"Sun-Hee","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Brain & Cognitive Engineering, Korea University, Anam-dong, Seongbuk-ku, Seoul 02841, Korea"}]}],"member":"1968","published-online":{"date-parts":[[2022,3,25]]},"reference":[{"key":"ref_1","first-page":"405","article-title":"The interpretation of structure from motion","volume":"203","author":"Ullman","year":"1979","journal-title":"Proc. R. S. Lond. Ser. B Biol. Sci."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1016\/j.geomorph.2012.08.021","article-title":"\u2018Structure-from-motion\u2019 photogrammetry: A low-cost, effective tool for geoscience applications","volume":"179","author":"Westoby","year":"2012","journal-title":"Geomorphology"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1038\/nphoton.2010.148","article-title":"Lidar: Mapping the world in 3d","volume":"4","author":"Schwarz","year":"2010","journal-title":"Nat. Photonics"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1292","DOI":"10.1109\/TGRS.2015.2477429","article-title":"Automatic detection and reconstruction of 2-d\/3-d building shapes from spaceborne tomosar point clouds","volume":"54","author":"Shahzad","year":"2015","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"752","DOI":"10.1109\/TGRS.2014.2327391","article-title":"Robust reconstruction of building facades for large areas using spaceborne tomosar point clouds","volume":"53","author":"Shahzad","year":"2014","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1016\/j.isprsjprs.2015.01.011","article-title":"Octree-based region growing for point cloud segmentation","volume":"104","author":"Vo","year":"2015","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_7","unstructured":"Pauly, M., Gross, M., and Kobbelt, L.P. (November, January 27). Efficient simplification of point-sampled surfaces. Proceedings of the Conference on Visualization\u201902, Boston, MA, USA."},{"key":"ref_8","first-page":"248","article-title":"Segmentation of point clouds using smoothness constraint","volume":"36","author":"Rabbani","year":"2006","journal-title":"Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1111\/j.1467-8659.2007.01016.x","article-title":"Efficient ransac for point-cloud shape detection","volume":"26","author":"Schnabel","year":"2007","journal-title":"Comput. Graph. Forum"},{"key":"ref_10","unstructured":"Tarsha-Kurdi, F., Landes, T., and Grussenmeyer, P. (2007, January 12\u201314). Hough-transform and extended ransac algorithms for automatic detection of 3d building roof planes from lidar data. Proceedings of the ISPRS Workshop on Laser Scanning 2007 and SilviLaser 2007, Espoo, Finland."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zhang, R., Candra, S.A., Vetter, K., and Zakhor, A. (2015, January 26\u201330). Sensor fusion for semantic segmentation of urban scenes. Proceedings of the 2015 IEEE International Conference on Robotics and Automation (ICRA), Seattle, WA, USA.","DOI":"10.1109\/ICRA.2015.7139439"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Wolf, D., Prankl, J., and Vincze, M. (2015, January 26\u201330). Fast semantic segmentation of 3d point clouds using a dense crf with learned parameters. Proceedings of the 2015 IEEE International Conference on Robotics and Automation (ICRA), Seattle, WA, USA.","DOI":"10.1109\/ICRA.2015.7139875"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Maturana, D., and Scherer, S. (October, January 28). Voxnet: A 3d convolutional neural network for real-time object recognition. Proceedings of the 2015 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Hamburg, Germany.","DOI":"10.1109\/IROS.2015.7353481"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Tchapmi, L., Choy, C., Armeni, I., Gwak, J., and Savarese, S. (2017, January 10\u201312). Segcloud: Semantic segmentation of 3d point clouds. Proceedings of the 2017 International Conference on 3D Vision (3DV), Qingdao, China.","DOI":"10.1109\/3DV.2017.00067"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Sitzmann, V., Thies, J., Heide, F., Nie\u00dfner, M., Wetzstein, G., and Zollhofer, M. (2019, January 15\u201319). Deepvoxels: Learning persistent 3d feature embeddings. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00254"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Shin, D., Fowlkes, C.C., and Hoiem, D. (2018, January 18\u201323). Pixels, voxels, and views: A study of shape representations for single view 3d object shape prediction. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00323"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Moon, G., Chang, J.Y., and Lee, K.M. (2018, January 18\u201323). V2v-posenet: Voxel-to-voxel prediction network for accurate 3d hand and human pose estimation from a single depth map. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00533"},{"key":"ref_18","unstructured":"Qi, C.R., Su, H., Mo, K., and Guibas, L.J. (2017, January 21\u201326). Pointnet: Deep learning on point sets for 3d classification and segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA."},{"key":"ref_19","unstructured":"Qi, C.R., Yi, L., Su, H., and Guibas, L.J. (2017). Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Advances in Neural Information Processing Systems, NIPS."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Shen, Y., Feng, C., Yang, Y., and Tian, D. (2018, January 18\u201322). Mining point cloud local structures by kernel correlation and graph pooling. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00478"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Hua, B.S., Tran, M.K., and Yeung, S.K. (2018, January 18\u201322). Pointwise convolutional neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00109"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"68892","DOI":"10.1109\/ACCESS.2019.2918862","article-title":"Dprnet: Deep 3d point based residual network for semantic segmentation and classification of 3d point clouds","volume":"7","author":"Arshad","year":"2019","journal-title":"IEEE Access"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Wang, Y., Sun, Y., Liu, Z., Sarma, S.E., Bronstein, M.M., and Solomon, J.M. (2018). Dynamic graph cnn for learning on point clouds. arXiv.","DOI":"10.1145\/3326362"},{"key":"ref_24","unstructured":"Wu, Z., Song, S., Khosla, A., Yu, F., Zhang, L., Tang, X., and Xiao, J. (2015, January 7\u201312). 3 shapenets: A deep representation for volumetric shapes. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Zhou, Y., and Tuzel, O. (2018, January 18\u201322). Voxelnet: End-to-end learning for point cloud based 3d object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Yang, B., Luo, W., and Urtasun, R. (2018, January 18\u201322). Pixor: Real-time 3d object detection from point clouds. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00798"},{"key":"ref_27","unstructured":"Hegde, V., and Zadeh, R. (2016). Fusionnet: 3D object classification using multiple data representations. arXiv."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1109\/TPAMI.2014.2316828","article-title":"3d object recognition in cluttered scenes with local surface features: A survey","volume":"36","author":"Guo","year":"2014","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Garcia-Garcia, A., Gomez-Donoso, F., Garcia-Rodriguez, J., Orts-Escolano, S., Cazorla, M., and Azorin-Lopez, J. (2016, January 24\u201329). Pointnet: A 3d convolutional neural network for real-time object class recognition. Proceedings of the 2016 International Joint Conference on Neural Networks (IJCNN), Vancouver, BC, Canada.","DOI":"10.1109\/IJCNN.2016.7727386"},{"key":"ref_30","unstructured":"Li, Y., Bu, R., Sun, M., Wu, W., Di, X., and Chen, B. (2018). Pointcnn: Convolution on \u03c7-Transformed Points. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Sheshappanavar, S.V., Singh, V.V., and Kambhamettu, C. (2021, January 11\u201317). PatchAugment: Local Neighborhood Augmentation in Point Cloud Classification. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, BC, Canada.","DOI":"10.1109\/ICCVW54120.2021.00240"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Zhang, J., Chen, L., Ouyang, B., Liu, B., Zhu, J., Chen, Y., Meng, Y., and Wu, D. (2021). PointCutMix: Regularization Strategy for Point Cloud Classification. arXiv.","DOI":"10.1016\/j.neucom.2022.07.049"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Qiu, S., Anwar, S., and Barnes, N. (2021). Geometric back-projection network for point cloud classification. IEEE Trans. Multimed.","DOI":"10.1109\/WACV48630.2021.00386"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Yang, Y., Feng, C., Shen, Y., and Tian, D. (2018, January 18\u201322). Foldingnet: Point cloud auto-encoder via deep grid deformation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00029"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Duan, Y., Zheng, Y., Lu, J., Zhou, J., and Tian, Q. (2019, January 16\u201320). Structural relational reasoning of point clouds. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00104"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Yang, J., Zhang, Q., Ni, B., Li, L., Liu, J., Zhou, M., and Tian, Q. (2019, January 16\u201320). Modeling point clouds with self-attention and gumbel subset sampling. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00344"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Su, H., Nie\u00dfner, M., Dai, A., Yan, M., and Guibas, L.J. (2016, January 27\u201330). Volumetric and multi-view cnns for object classification on 3d data. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.609"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Simonovsky, M., and Komodakis, N. (2017, January 21\u201326). Dynamic edgeconditioned filters in convolutional neural networks on graphs. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.11"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Esteves, C., Allen-Blanchette, C., Makadia, A., and Daniilidis, K. (2018, January 8\u201314). Learning so (3) equivariant representations with spherical cnns. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01261-8_4"},{"key":"ref_40","unstructured":"Lei, H., Akhtar, N., and Mian, A. (2018). Spherical convolutional neural network for 3d point clouds. arXiv."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Klokov, R., and Lempitsky, V. (2017, January 22\u201329). Escape from cells: Deep kd-networks for the recognition of 3d point cloud models. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.99"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Gadelha, M., Wang, R., and Maji, S. (2018, January 8\u201314). Multiresolution tree networks for 3d point cloud processing. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01234-2_7"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Zeng, W., and Gevers, T. (2018, January 8\u201314). 3dcontextnet: Kd tree guided hierarchical learning of point clouds using local and global contextual cues. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-11015-4_24"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Lin, C.H., Kong, C., and Lucey, S. (2018, January 2\u20137). Learning efficient point cloud generation for dense 3d object reconstruction. Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.","DOI":"10.1609\/aaai.v32i1.12278"},{"key":"ref_45","unstructured":"Zhi, S., Liu, Y., Li, X., and Guo, Y. (2017, January 23\u201324). Lightnet: A lightweight 3d convolutional neural network for real-time 3d object recognition. Proceedings of the Eurographics Workshop on 3D Object Retrieval, Lyon, France."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Monti, F., Boscaini, D., Masci, J., Rodola, E., Svoboda, J., and Bronstein, M.M. (2017, January 21\u201326). Geometric deep learning on graphs and manifolds using mixture model cnns. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.576"},{"key":"ref_47","unstructured":"Li, Y., Pirk, S., Su, H., Qi, C.R., and Guibas, L.J. (2016). Fpnn: Field probing neural networks for 3d data. Advances in Neural Information Processing Systems, NIPS."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Yi, L., Su, H., Guo, X., and Guibas, L.J. (2017, January 21\u201326). Syncspeccnn: Synchronized spectral cnn for 3d shape segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.697"},{"key":"ref_49","unstructured":"Shen, Y., Feng, C., Yang, Y., and Tian, D. (2017). Neighbors do help: Deeply exploiting local structures of point clouds. arXiv."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Rethage, D., Wald, J., Sturm, J., Navab, N., and Tombari, F. (2018, January 8\u201314). Fully-convolutional point networks for large-scale point clouds. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01225-0_37"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Huang, Q., Wang, W., and Neumann, U. (2018, January 18\u201323). Recurrent slice networks for 3d segmentation of point clouds. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00278"},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Wang, X., Liu, S., Shen, X., Shen, C., and Jia, J. (2019, January 15\u201320). Associatively segmenting instances and semantics in point clouds. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00422"},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Gomez-Donoso, F., Escalona, F., and Cazorla, M. (2020). Par3dnet: Using 3dcnns for object recognition on tridimensional partial views. Appl. Sci., 10.","DOI":"10.3390\/app10103409"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/7\/2512\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:43:01Z","timestamp":1760136181000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/7\/2512"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,25]]},"references-count":53,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2022,4]]}},"alternative-id":["s22072512"],"URL":"https:\/\/doi.org\/10.3390\/s22072512","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2022,3,25]]}}}