{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T05:54:14Z","timestamp":1770184454188,"version":"3.49.0"},"reference-count":51,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T00:00:00Z","timestamp":1770076800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"JST BOOST, Japan","award":["JPMJBS2402"],"award-info":[{"award-number":["JPMJBS2402"]}]},{"name":"JSPS KAKENHI","award":["JP21K14130"],"award-info":[{"award-number":["JP21K14130"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Self-supervised contrastive learning has demonstrated remarkable effectiveness in learning visual representations without labeled data, yet its application to 3D local feature learning from point clouds remains underexplored. Existing methods predominantly focus on complete object shapes, neglecting the critical challenge of recognizing partial observations commonly encountered in real-world 3D perception. We propose a momentum contrastive learning framework specifically designed to learn discriminative local features from randomly sampled point cloud regions. By adapting the MoCo architecture with PointNet++ as the feature backbone, our method treats local parts of point cloud as fundamental contrastive learning units, combined with carefully designed augmentation strategies including random dropout and translation. Experiments on ShapeNet demonstrate that our approach effectively learns transferable local features and the empirical observation that approximately 30% object local part represents a practical threshold for effective learning when simulating real-world occlusion scenarios, and achieves comparable downstream classification accuracy while reducing training time by 16%.<\/jats:p>","DOI":"10.3390\/s26031007","type":"journal-article","created":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T16:46:28Z","timestamp":1770137188000},"page":"1007","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["3D Local Feature Learning and Analysis on Point Cloud Parts via Momentum Contrast"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2402-0075","authenticated-orcid":false,"given":"Xuanmeng","family":"Sha","sequence":"first","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Osaka, Suita, Osaka 565-0871, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4595-8816","authenticated-orcid":false,"given":"Tomohiro","family":"Mashita","sequence":"additional","affiliation":[{"name":"Department of Engineering Informatics, Osaka Electro-Communication University, Neyagawa, Osaka 572-8530, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3332-4426","authenticated-orcid":false,"given":"Naoya","family":"Chiba","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Osaka, Suita, Osaka 565-0871, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3174-6588","authenticated-orcid":false,"given":"Liyun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Graduate School of Frontier Sciences, The University of Tokyo, Kashiwa-shi, Chiba 277-8561, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,3]]},"reference":[{"key":"ref_1","unstructured":"Qi, C.R., Litany, O., He, K., and Guibas, L.J. (November, January 27). Deep hough voting for 3d object detection in point clouds. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Shi, S., Wang, X., and Li, H. (2019, January 15\u201320). Pointrcnn: 3d object proposal generation and detection from point cloud. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00086"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Yang, Z., Sun, Y., Liu, S., and Jia, J. (2020, January 13\u201319). 3dssd: Point-based 3d single stage object detector. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Hu, Q., Xu, G., Ma, Y., Wan, J., and Guo, Y. (2022, January 18\u201324). Not all points are equal: Learning highly efficient point-based detectors for 3d lidar point clouds. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01838"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Lang, A.H., Vora, S., Caesar, H., Zhou, L., Yang, J., and Beijbom, O. (2019, January 15\u201320). Pointpillars: Fast encoders for object detection from point clouds. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Shi, G., Li, R., and Ma, C. (2022). Pillarnet: High-performance pillar-based 3d object detection. arXiv.","DOI":"10.1007\/978-3-031-20080-9_3"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Shi, S., Guo, C., Jiang, L., Wang, Z., Shi, J., Wang, X., and Li, H. (2020, January 13\u201319). Pv-rcnn: Point-voxel feature set abstraction for 3d object detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1007\/s11263-022-01710-9","article-title":"Pv-rcnn++: Point-voxel feature set abstraction with local vector representation for 3d object detection","volume":"131","author":"Shi","year":"2023","journal-title":"Int. J. Comput. Vis."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Yan, Y., Mao, Y., and Li, B. (2018). Second: Sparsely embedded convolutional detection. Sensors, 18.","DOI":"10.3390\/s18103337"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"57566","DOI":"10.1109\/ACCESS.2020.2982196","article-title":"A review on deep learning approaches for 3d data representations in retrieval and classifications","volume":"8","author":"Gezawa","year":"2020","journal-title":"IEEE Access"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Ghadiyaram, D., Tran, D., and Mahajan, D. (2019, January 16\u201320). Large-scale weakly-supervised pre-training for video action recognition. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.01232"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Kolesnikov, A., Beyer, L., Zhai, X., Puigcerver, J., Yung, J., Gelly, S., and Houlsby, N. (2020, January 23\u201328). Big transfer (bit): General visual representation learning. Proceedings of the Computer Vision\u2014ECCV 2020: 16th European Conference, Glasgow, UK. Part V 16.","DOI":"10.1007\/978-3-030-58558-7_29"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Mahajan, D., Girshick, R., Ramanathan, V., He, K., Paluri, M., Li, Y., Bharambe, A., and Maaten, L.V.D. (2018, January 8\u201314). Exploring the limits of weakly supervised pretraining. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Sun, C., Shrivastava, A., Singh, S., and Gupta, A. (2017, January 22\u201329). Revisiting unreasonable effectiveness of data in deep learning era. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.97"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Turk, G., and Levoy, M. (1994, January 24\u201329). Zippered polygon meshes from range images. Proceedings of the 21st Annual Conference on Computer Graphics and Interactive Techniques, Orlando, FL, USA.","DOI":"10.1145\/192161.192241"},{"key":"ref_16","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref_17","unstructured":"Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv."},{"key":"ref_18","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Yu, S.X., and Lin, D. (2018, January 18\u201322). Unsupervised feature learning via non-parametric instance discrimination. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref_20","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume":"33","author":"Caron","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_21","unstructured":"Chen, T., Kornblith, S., Norouzi, M., and Hinton, G. (2020, January 12\u201318). A simple framework for contrastive learning of visual representations. Proceedings of the International Conference on Machine Learning, Vienna, Austria."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"121354","DOI":"10.1016\/j.eswa.2023.121354","article-title":"Self-supervised learning for point cloud data: A survey","volume":"237","author":"Zeng","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Hou, J., Graham, B., Nie\u00dfner, M., and Xie, S. (2021, January 19\u201325). Exploring data-efficient 3d scene understanding with contrastive scene contexts. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01533"},{"key":"ref_24","unstructured":"Veli\u010dkovi\u0107, P., Fedus, W., Hamilton, W.L., Li\u00f2, P., Bengio, Y., and Hjelm, R.D. (2018). Deep graph infomax. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Xie, S., Gu, J., Guo, D., Qi, C.R., Guibas, L., and Litany, O. (2020, January 23\u201328). Pointcontrast: Unsupervised pre-training for 3d point cloud understanding. Proceedings of the Computer Vision\u2014ECCV 2020: 16th European Conference, Glasgow, UK. Part III 16.","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Girdhar, R., Joulin, A., and Misra, I. (2021, January 11\u201317). Self-supervised pretraining of 3d features on any point-cloud. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, Canada.","DOI":"10.1109\/ICCV48922.2021.01009"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"596","DOI":"10.1109\/LRA.2020.3048658","article-title":"Point set voting for partial point cloud analysis","volume":"6","author":"Zhang","year":"2021","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Jiang, J., Zhao, L., Lu, X., Hu, W., Razzak, I., and Wang, M. (2024, January 20\u201327). Dhgcn: Dynamic hop graph convolution network for self-supervised point cloud learning. Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence and Fourteenth Symposium on Educational Advances in Artificial Intelligence, Vancouver, BC, Canada.","DOI":"10.1609\/aaai.v38i11.29185"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"130365","DOI":"10.1016\/j.neucom.2025.130365","article-title":"Laa: Local awareness attention for point cloud self-supervised representation learning","volume":"640","author":"Yu","year":"2025","journal-title":"Neurocomputing"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Pang, Y., Wang, W., Tay, F.E., Liu, W., Tian, Y., and Yuan, L. (2022, January 23\u201327). Masked autoencoders for point cloud self-supervised learning. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel.","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Ren, B., Mei, G., Paudel, D.P., Wang, W., Li, Y., Liu, M., Cucchiara, R., Gool, L.V., and Sebe, N. (2024, January 8\u201312). Bringing masked autoencoders explicit contrastive properties for point cloud self-supervised learning. Proceedings of the Asian Conference on Computer Vision, Hanoi, Vietnam.","DOI":"10.1007\/978-981-96-0963-5_4"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., and Girshick, R. (2020, January 13\u201319). Momentum contrast for unsupervised visual representation learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref_33","unstructured":"Chang, A.X., Funkhouser, T., Guibas, L., Hanrahan, P., Huang, Q., Li, Z., Savarese, S., Savva, M., Song, S., and Su, H. (2015). ShapeNet: An Information-Rich 3D Model Repository. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2980179.2980238","article-title":"A scalable active framework for region annotation in 3d shape collections","volume":"35","author":"Yi","year":"2016","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"ref_35","first-page":"8","article-title":"Video segmentation by non-local consensus voting","volume":"2","author":"Faktor","year":"2014","journal-title":"BMVC"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Croitoru, I., Bogolin, S.-V., and Leordeanu, M. (2017, January 22\u201329). Unsupervised learning from video to detect foreground objects in single images. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.465"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., and Zisserman, A. (2017, January 22\u201329). Look, listen and learn. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Agrawal, P., Carreira, J., and Malik, J. (2015, January 7\u201313). Learning to see by moving. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.13"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Jayaraman, D., and Grauman, K. (2015, January 7\u201313). Learning image representations tied to ego-motion. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.166"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Zhang, L., Ratsamee, P., Wang, B., Luo, Z., Uranishi, Y., Higashida, M., and Takemura, H. (2023, January 3\u20137). Panoptic-aware image-to-image translation. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA.","DOI":"10.1109\/WACV56688.2023.00034"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"938","DOI":"10.1109\/TCSVT.2023.3288547","article-title":"Panoptic-level image-to-image translation for object recognition and visual odometry enhancement","volume":"34","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_42","unstructured":"Sha, X., Zhang, L., Mashita, T., Chiba, N., and Uranishi, Y. (2025). 3dfacepolicy: Audio-driven 3d facial animation based on action control. arXiv."},{"key":"ref_43","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, Honolulu, HI, USA."},{"key":"ref_44","unstructured":"Qi, C.R., Yi, L., Su, H., and Guibas, L.J. (2017, January 4\u20139). Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Proceedings of the NIPS\u201917: Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_45","unstructured":"Qian, G., Li, Y., Peng, H., Mai, J., Hammoud, H., Elhoseiny, M., and Ghanem, B. (2022, January 28). Pointnext: Revisiting pointnet++ with improved training and scaling strategies. Proceedings of the 36th International Conference on Neural Information Processing Systems, New Orleans, LA, USA."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Hu, Q., Yang, B., Xie, L., Rosa, S., Guo, Y., Wang, Z., Trigoni, N., and Markham, A. (2020, January 13\u201319). Randla-net: Efficient semantic segmentation of large-scale point clouds. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01112"},{"key":"ref_47","unstructured":"Ma, X., Qin, C., You, H., Ran, H., and Fu, Y. (2022). Rethinking network design and local geometry in point cloud: A simple residual mlp framework. arXiv."},{"key":"ref_48","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141, and Polosukhin, I. (2017, January 4\u20139). Attention is all you need. Proceedings of the NIPS\u201917: Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_49","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_50","unstructured":"Oord, A.v.d., Li, Y., and Vinyals, O. (2018). Representation learning with contrastive predictive coding. arXiv."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5\u20139). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany. Part III 18.","DOI":"10.1007\/978-3-319-24574-4_28"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/3\/1007\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T16:48:31Z","timestamp":1770137311000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/3\/1007"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,3]]},"references-count":51,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["s26031007"],"URL":"https:\/\/doi.org\/10.3390\/s26031007","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,3]]}}}