{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T01:57:51Z","timestamp":1778551071232,"version":"3.51.4"},"reference-count":71,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T00:00:00Z","timestamp":1769385600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"2024 Shanghai Municipal Government Special Fund for Promoting High-Quality Industrial Development\u2014Leading Industry Innovation and Development Project","award":["2024-GZL-RGZN-01039"],"award-info":[{"award-number":["2024-GZL-RGZN-01039"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Existing 3D point cloud enhancement methods typically rely on artificially designed geometric transformations or local blending strategies, which are prone to introducing illogical deformations, struggle to preserve global structure, and exhibit insufficient adaptability to diverse degradation patterns. To address these limitations, this paper proposes SFD-ADNet\u2014an adaptive deformation framework based on a dual spatial\u2013frequency domain. It achieves 3D point cloud augmentation by explicitly learning deformation parameters rather than applying predefined perturbations. By jointly modeling spatial structural dependencies and spectral features, SFD-ADNet generates augmented samples that are both structurally aware and task-relevant. In the spatial domain, a hierarchical sequence encoder coupled with a bidirectional Mamba-based deformation predictor captures long-range geometric dependencies and local structural variations, enabling adaptive position-aware deformation control. In the frequency domain, a multi-scale dual-channel mechanism based on adaptive Chebyshev polynomials separates low-frequency structural components from high-frequency details, allowing the model to suppress noise-sensitive distortions while preserving the global geometric skeleton. The two deformation predictions dynamically fuse to balance structural fidelity and sample diversity. Extensive experiments conducted on ModelNet40-C and ScanObjectNN-C involved synthetic CAD models and real-world scanned point clouds under diverse perturbation conditions. SFD-ADNet, as a universal augmentation module, reduces the mCE metrics of PointNet++ and different backbone networks by over 20%. Experiments demonstrate that SFD-ADNet achieves state-of-the-art robustness while preserving critical geometric structures. Furthermore, models enhanced by SFD-ADNet demonstrate consistently improved robustness against diverse point cloud attacks, validating the efficacy of adaptive space-frequency deformation in robust point cloud learning.<\/jats:p>","DOI":"10.3390\/jimaging12020058","type":"journal-article","created":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T09:05:27Z","timestamp":1769504727000},"page":"58","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["SFD-ADNet: Spatial\u2013Frequency Dual-Domain Adaptive Deformation for Point Cloud Data Augmentation"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6234-9028","authenticated-orcid":false,"given":"Jiacheng","family":"Bao","sequence":"first","affiliation":[{"name":"College of Publishing, University of Shanghai for Science and Technology, Shanghai 200093, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingjun","family":"Kong","sequence":"additional","affiliation":[{"name":"Printing and Packaging Engineering Department, Shanghai Publishing and Printing College, Shanghai 200093, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8549-4710","authenticated-orcid":false,"given":"Wenju","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Publishing, University of Shanghai for Science and Technology, Shanghai 200093, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,26]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"144274","DOI":"10.1109\/ACCESS.2023.3345000","article-title":"Adversarial Attacks and Defenses on 3D Point Cloud Classification: A Survey","volume":"11","author":"Naderi","year":"2023","journal-title":"IEEE Access"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1007","DOI":"10.1007\/s00371-024-03380-9","article-title":"Point clouds feature frequency domain analysis based on multilayer perceptron","volume":"41","author":"Zhang","year":"2024","journal-title":"Vis. Comput."},{"key":"ref_3","unstructured":"Lu, W., Wang, J., Yu, H., Huang, L., Zhang, X., Chen, Y., and Xie, X. (2022). FIXED: Frustratingly Easy Domain Generalization with Mixup. arXiv."},{"key":"ref_4","unstructured":"Xiao, A., Huang, J., Guan, D., Cui, K., Lu, S., and Shao, L. (2022). PolarMix: A General Data Augmentation Technique for LiDAR Point Clouds. arXiv."},{"key":"ref_5","first-page":"845","article-title":"A Random Fusion of Mix3D and PolarMix to Improve Semantic Segmentation Performance in 3D Lidar Point Cloud","volume":"140","author":"Liu","year":"2024","journal-title":"CMES Comput. Model. Eng. Sci."},{"key":"ref_6","unstructured":"Sebek, P., Pokorn\u00fd, \u0160., Vacek, P., and Svoboda, T. (2022). Real3D-Aug: Point Cloud Augmentation by Placing Real Objects with Occlusion Handling for 3D Detection and Segmentation. arXiv."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Sheshappanavar, S.V., Veerendraveer, V., and Kambhamettu, C. (2021, January 11\u201317). PatchAugment: Local Neighborhood Augmentation in Point Cloud Classification. Proceedings of the 2021 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW), Virtual.","DOI":"10.1109\/ICCVW54120.2021.00240"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"103769","DOI":"10.1016\/j.jvcir.2023.103769","article-title":"IPC-Net: Incomplete point cloud classification network based on data augmentation and similarity measurement","volume":"91","author":"He","year":"2023","journal-title":"J. Vis. Commun. Image Represent."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Vu, T.A., Sarkar, S., Zhang, Z.Y., Hua, B.S., and Yeung, S.K. (2024, January 18\u201321). Test-Time Augmentation for 3D Point Cloud Classification and Segmentation. Proceedings of the International Conference in 3D Vision (3DV), Davos, Switzerland.","DOI":"10.1109\/3DV62453.2024.00153"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"104557","DOI":"10.1016\/j.imavis.2022.104557","article-title":"3D-VDNet: Exploiting the vertical distribution characteristics of point clouds for 3D object detection and augmentation","volume":"127","author":"Xiao","year":"2022","journal-title":"Image Vis. Comput."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Charles, R.Q., Su, H., Kaichun, M., and Guibas, L.J. (2017, January 21\u201326). PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.16"},{"key":"ref_12","unstructured":"Ruizhongtai Qi, C., Yi, L., Su, H., and Guibas, L. (2017). PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space. arXiv."},{"key":"ref_13","unstructured":"Li, Y., Bu, R., Sun, M., Wu, W., Di, X., and Chen, B. (2018, January 2\u20138). PointCNN: Convolution On X-Transformed Points. Proceedings of the Neural Information Processing Systems, Montr\u00e9al, QC, Canada."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Thomas, H., Qi, C., Deschaud, J.-E., Marcotegui, B., Goulette, F., and Guibas, L.J. (November, January 27). KPConv: Flexible and Deformable Convolution for Point Clouds. Proceedings of the 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.","DOI":"10.1109\/ICCV.2019.00651"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Lin, Y., Yan, Z., Huang, H., Du, D., Liu, L., Cui, S., and Han, X. (2020, January 16\u201318). FPConv: Learning Local Flattening for Point Convolution. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Virtual.","DOI":"10.1109\/CVPR42600.2020.00435"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"3100","DOI":"10.1007\/s11263-022-01682-w","article-title":"RegGeoNet: Learning Regular Representations for Large-Scale 3D Point Clouds","volume":"130","author":"Zhang","year":"2022","journal-title":"Int. J. Comput. Vis."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"9726","DOI":"10.1109\/TPAMI.2023.3244828","article-title":"Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis","volume":"45","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3197517.3201301","article-title":"Point convolutional neural networks by extension operators","volume":"37","author":"Atzmon","year":"2018","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Deng, X., Zhang, W., Ding, Q., and Zhang, X. (2022, January 18\u201322). PointVector: A Vector Representation In Point Cloud Analysis. Proceedings of the 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.00912"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Landrieu, L., and Simonovsky, M. (2017, January 18\u201322). Large-Scale Point Cloud Semantic Segmentation with Superpoint Graphs. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00479"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Ran, H., Liu, J., and Wang, C. (2022, January 19\u201324). Surface Representation for Point Clouds. Proceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01837"},{"key":"ref_22","first-page":"1","article-title":"Dynamic Graph CNN for Learning on Point Clouds","volume":"38","author":"Wang","year":"2018","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jiang, L., Fu, C.-W., and Jia, J. (2019, January 16\u201320). PointWeb: Enhancing Local Neighborhood Features for Point Cloud Processing. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00571"},{"key":"ref_24","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2017, January 4\u20139). Attention is All you Need. Proceedings of the Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"134826","DOI":"10.1109\/ACCESS.2021.3116304","article-title":"Point Transformer","volume":"9","author":"Engel","year":"2020","journal-title":"IEEE Access"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Park, C., Jeong, Y., Cho, M., and Park, J. (2021, January 19\u201324). Fast Point Transformer. Proceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01644"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Lai, X., Liu, J., Jiang, L., Wang, L., Zhao, H., Liu, S., Qi, X., and Jia, J. (2022, January 19\u201324). Stratified Transformer for 3D Point Cloud Segmentation. Proceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00831"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Yu, X., Tang, L., Rao, Y., Huang, T., Zhou, J., and Lu, J. (2022, January 18\u201324). Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling. Proceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Pang, Y., Wang, W., Tay, F.E.H., Liu, W., Tian, Y., and Yuan, L. (2022). Masked Autoencoders for Point Cloud Self-supervised Learning. arXiv.","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Liu, H., Cai, M., and Lee, Y.J. (2022, January 23\u201327). Masked Discrimination for Self-Supervised Learning on Point Clouds. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel.","DOI":"10.1007\/978-3-031-20086-1_38"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Wang, H., Liu, Q., Yue, X., Lasenby, J., and Kusner, M.J. (2021, January 11\u201317). Unsupervised Point Cloud Pre-training via Occlusion Completion. Proceedings of the 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), Virtual.","DOI":"10.1109\/ICCV48922.2021.00964"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Afham, M., Dissanayake, I., Dissanayake, D., Dharmasiri, A., Thilakarathna, K., and Rodrigo, R. (2022, January 19\u201324). CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding. Proceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00967"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"6900","DOI":"10.1109\/TVCG.2023.3345353","article-title":"PointVST: Self-Supervised Pre-Training for 3D Point Clouds via View-Specific Point-to-Image Translation","volume":"30","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"ref_34","unstructured":"Dong, R., Qi, Z., Zhang, L., Zhang, J., Sun, J.Y., Ge, Z., Yi, L., and Ma, K. (2022). Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?. arXiv."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Xue, L., Yu, N., Zhang, S., Li, J., Mart\u00edn-Mart\u00edn, R., Wu, J., Xiong, C., Xu, R., Niebles, J.C., and Savarese, S. (2024, January 17\u201321). ULIP-2: Towards Scalable Multimodal Pre-Training for 3D Understanding. Proceedings of the 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.02558"},{"key":"ref_36","unstructured":"Qi, Z., Dong, R., Zhang, S., Geng, H., Han, C., Ge, Z., Yi, L., and Ma, K. (October, January 29). ShapeLLM: Universal 3D Object Understanding for Embodied Interaction. Proceedings of the European Conference on Computer Vision, Milan, Italy."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"65","DOI":"10.70003\/160792642025012601006","article-title":"Class-Balanced PolarMix for Data Augmentation of 3D LIDAR Point Clouds Semantic Segmentation","volume":"26","author":"Liu","year":"2025","journal-title":"J. Internet Technol."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Chen, T.Y., and Ying, X.H. (2025). FPSMix: Data augmentation strategy for point cloud classification. Front. Comput. Sci., 19.","DOI":"10.1007\/s11704-023-3455-4"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Hasecke, F., Alsfasser, M., and Kummert, A. (2022, January 5\u20139). What Can be Seen is What You Get: Structure Aware Point Cloud Augmentation. Proceedings of the 2022 IEEE Intelligent Vehicles Symposium (IV), Aachen, Germany.","DOI":"10.1109\/IV51971.2022.9827116"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"3316","DOI":"10.1109\/TIV.2023.3348805","article-title":"Leveraging Smooth Deformation Augmentation for LiDAR Point Cloud Semantic Segmentation","volume":"9","author":"Qiu","year":"2024","journal-title":"IEEE Trans. Intell. Veh."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"21344","DOI":"10.1038\/s41598-024-72264-8","article-title":"PCAlign: A general data augmentation framework for point clouds","volume":"14","author":"Zhang","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Yang, L., and Xiang, Z. (2024). RISurConv: Rotation Invariant Surface Attention-Augmented Convolutions for 3D Point Cloud Classification and Segmentation. arXiv.","DOI":"10.1007\/978-3-031-73390-1_6"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Deng, J., Chan, G., Zhong, H., and Lu, C.X. (2024, January 13\u201317). Robust 3D Object Detection from LiDAR-Radar Point Clouds via Cross-Modal Feature Augmentation. Proceedings of the 2024 IEEE International Conference on Robotics and Automation (ICRA), Yokohama, Japan.","DOI":"10.1109\/ICRA57147.2024.10610775"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1007\/978-981-96-0963-5_4","article-title":"Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-supervised Learning","volume":"Volume 15478","author":"Ren","year":"2024","journal-title":"Computer Vision\u2014ACCV 2024: 17th Asian Conference on Computer Vision, Proceedings; Lecture Notes in Computer Science"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-981-96-0969-7_1","article-title":"DA 2: Degree-Accumulated Data Augmentation on Point Clouds with Curriculum Dynamic Threshold Selection","volume":"Volume 15480","author":"Tai","year":"2024","journal-title":"Computer Vision\u2014ACCV 2024: 17th Asian Conference on Computer Vision, Proceedings; Lecture Notes in Computer Science"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Wang, J., Ding, L., Xu, T., Dong, S., Xu, X., Bai, L., and Li, J. (2023, January 2\u20136). Sample-adaptive Augmentation for Point Cloud Recognition Against Real-world Corruptions. Proceedings of the 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France.","DOI":"10.1109\/ICCV51070.2023.01318"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Wang, W., Liu, X., and Mou, X. (2021). Data Augmentation and Spectral Structure Features for Limited Samples Hyperspectral Classification. Remote Sens., 13.","DOI":"10.3390\/rs13040547"},{"key":"ref_48","first-page":"501","article-title":"A Spectrally Improved Point Cloud Classification Method for Multispectral LiDAR","volume":"XLIII-B3-2020","author":"Chen","year":"2020","journal-title":"ISPRS Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Feng, W., Quan, Y., Ye, G., and Dauphin, G. (2024). Dynamic Spatial\u2013Spectral Feature Optimization-Based Point Cloud Classification. Remote Sens., 16.","DOI":"10.3390\/rs16030575"},{"key":"ref_50","unstructured":"Wen, C., Long, J., Yu, B., and Tao, D. (2023). PointWavelet: Learning in Spectral Domain for 3D Point Cloud Analysis. arXiv."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Liu, D., Liu, S., Chen, C., Jiang, Z., and Xu, C. (2022, January 17\u201322). PFMixer: Point Cloud Frequency Mixing. Proceedings of the IGARSS 2022\u20142022 IEEE International Geoscience and Remote Sensing Symposium, Kuala Lumpur, Malaysia.","DOI":"10.1109\/IGARSS46834.2022.9883613"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1109\/JAS.2023.123432","article-title":"Point Cloud Classification Using Content-Based Transformer via Clustering in Feature Space","volume":"11","author":"Liu","year":"2024","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"124023","DOI":"10.1016\/j.eswa.2024.124023","article-title":"Context-Based Local-Global Fusion Network for 3d Point Cloud Classification and Segmentation","volume":"251","author":"Wu","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_54","unstructured":"Han, X., Tang, Y., Wang, Z., and Li, X. (November, January 28). Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model. Proceedings of the 32nd ACM International Conference on Multimedia, Melbourne, Australia."},{"key":"ref_55","unstructured":"Jang, E., Gu, S.S., and Poole, B. (2016). Categorical Reparameterization with Gumbel-Softmax. arXiv."},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., and Sun, G. (2018, January 18\u201323). Squeeze-and-Excitation Networks. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref_57","unstructured":"Ren, J., Pan, L., and Liu, Z. (2022, January 17\u201323). Benchmarking and Analyzing Point Cloud Classification under Corruptions. Proceedings of the International Conference on Machine Learning, Baltimore, MD, USA."},{"key":"ref_58","doi-asserted-by":"crossref","unstructured":"Kim, S.H., Lee, S., Hwang, D., Lee, J., Hwang, S.J., and Kim, H.J. (2021, January 11\u201317). Point Cloud Augmentation with Weighted Local Transformations. Proceedings of the 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), Virtual.","DOI":"10.1109\/ICCV48922.2021.00059"},{"key":"ref_59","doi-asserted-by":"crossref","unstructured":"Lee, D., Lee, J., Lee, J., Lee, H., Lee, M., Woo, S., and Lee, S. (2021, January 19\u201325). Regularization Strategy for Point Cloud via Rigidly Mixed Sample. Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Virtual.","DOI":"10.1109\/CVPR46437.2021.01564"},{"key":"ref_60","doi-asserted-by":"crossref","unstructured":"Liu, Y., Fan, B., Xiang, S., and Pan, C. (2019, January 16\u201320). Relation-Shape Convolutional Neural Network for Point Cloud Analysis. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00910"},{"key":"ref_61","unstructured":"Goyal, A., Law, H., Liu, B., Newell, A., and Deng, J. (2021, January 18\u201324). Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline. Proceedings of the International Conference on Machine Learning, Virtual."},{"key":"ref_62","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhang, J., Zhou, Z., Xu, M., Qi, X., and Qiao, Y. (2020). Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud. arXiv.","DOI":"10.1609\/aaai.v35i4.16414"},{"key":"ref_63","doi-asserted-by":"crossref","unstructured":"Xiang, T., Zhang, C., Song, Y., Yu, J., and Cai, W. (2021, January 11\u201317). Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis. Proceedings of the 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), Virtual.","DOI":"10.1109\/ICCV48922.2021.00095"},{"key":"ref_64","doi-asserted-by":"crossref","unstructured":"Xu, M., Ding, R., Zhao, H., and Qi, X. (2021, January 19\u201325). PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds. Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Virtual.","DOI":"10.1109\/CVPR46437.2021.00319"},{"key":"ref_65","doi-asserted-by":"crossref","unstructured":"Li, J., Huang, B., and Pan, L. (2024). SMCNet: State-Space Model for Enhanced Corruption Robustness in 3D Classification. Sensors, 24.","DOI":"10.3390\/s24237861"},{"key":"ref_66","unstructured":"Qian, G., Li, Y., Peng, H., Mai, J., Hammoud, H., Elhoseiny, M., and Ghanem, B. (2022). PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies. arXiv."},{"key":"ref_67","doi-asserted-by":"crossref","unstructured":"Meraz, M., Ansari, M.A., Javed, M., and Chakraborty, P. (2024). Point-GR: Graph Residual Point Cloud Network for 3D Object Classification and Segmentation. arXiv.","DOI":"10.1007\/978-3-031-87663-9_2"},{"key":"ref_68","doi-asserted-by":"crossref","unstructured":"Zhou, W., Wang, Q., Jin, W., Shi, X.J., Wang, D., Hao, X., and Yu, Y. (2023). GTNet: Graph Transformer Network for 3D Point Cloud Classification and Semantic Segmentation. arXiv.","DOI":"10.2139\/ssrn.4839921"},{"key":"ref_69","unstructured":"Yang, J., Zhang, Q., Fang, R., Ni, B., Liu, J., and Tian, Q. (2019). Adversarial Attack and Defense on Point Sets. arXiv."},{"key":"ref_70","doi-asserted-by":"crossref","unstructured":"Zhou, H., Chen, D., Liao, J., Chen, K., Dong, X., Liu, K., Zhang, W., Hua, G., and Yu, N. (2020, January 16\u201318). LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud Based Deep Networks. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Virtual.","DOI":"10.1109\/CVPR42600.2020.01037"},{"key":"ref_71","unstructured":"Wu, Z., Duan, Y., Wang, H., Fan, Q., and Guibas, L.J. (2020). IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restoration. arXiv."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/2\/58\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T09:45:23Z","timestamp":1769507123000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/2\/58"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,26]]},"references-count":71,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["jimaging12020058"],"URL":"https:\/\/doi.org\/10.3390\/jimaging12020058","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,26]]}}}