{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T05:05:41Z","timestamp":1784696741878,"version":"3.55.0"},"reference-count":33,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T00:00:00Z","timestamp":1784505600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Three-dimensional sensing technologies can rapidly acquire 3D point cloud data for object perception and scene understanding. However, point cloud-based object classification is still constrained by limited labeled data and high computational complexity. At present, feature extractors pretrained on large-scale 2D datasets have achieved strong performance in zero-shot 2D classification. Therefore, projecting 3D point clouds into 2D images and leveraging well-established 2D pretrained models for zero-shot point cloud classification has become an effective strategy. In this strategy, generating high-fidelity 2D projections is a critical challenge. To address this challenge, this paper proposes a zero-shot 3D object classification framework based on a multi-scale local geometric feature extraction module and depth-aware multi-view projection. Specifically, point clouds are first modeled as graph structures. Multi-scale radii are used to adjust the receptive field during feature extraction, thereby capturing both fine-grained and large-scale local geometric features. Multi-view 2D images are then generated through depth-wise feature accumulation. These images are fed into a frozen CLIP model for zero-shot classification. The proposed method preserves the structural characteristics of point clouds and reduces the domain gap between point clouds and 2D images. Experiments are conducted on the ModelNet10, ModelNet40, and ScanObjectNN datasets. The results show that the proposed method outperforms current mainstream zero-shot 3D point cloud classification methods. These results suggest that the proposed framework offers an effective solution for point cloud object classification in complex scenarios.<\/jats:p>","DOI":"10.3390\/s26144598","type":"journal-article","created":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T13:18:31Z","timestamp":1784553511000},"page":"4598","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Zero-Shot 3D Object Classification via Graph-Based Local Geometric Features and Depth-Aware Multi-View Projection"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8169-6212","authenticated-orcid":false,"given":"Wenchao","family":"He","sequence":"first","affiliation":[{"name":"Department of Electromechanical and Information Engineering, Changchun Humanities and Sciences College, Changchun 130117, China"},{"name":"College of Communication Engineering, Jilin University, Changchun 130015, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1513-9770","authenticated-orcid":false,"given":"Ying","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Electronic Science and Engineering, Jilin University, Changchun 130015, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0216-3307","authenticated-orcid":false,"given":"Hongxi","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Communication Engineering, Jilin University, Changchun 130015, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0846-4267","authenticated-orcid":false,"given":"Yiran","family":"Shi","sequence":"additional","affiliation":[{"name":"College of Communication Engineering, Jilin University, Changchun 130015, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,20]]},"reference":[{"key":"ref_1","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_2","doi-asserted-by":"crossref","unstructured":"Sedaghat, N., Zolfaghari, M., Amiri, E., and Brox, T. (2016). Orientation-boosted voxel nets for 3D object recognition. arXiv.","DOI":"10.5244\/C.31.97"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Riegler, G., Osman Ulusoy, A., and Geiger, A. (2017, January 21\u201326). Octnet: Learning deep 3d representations at high resolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.701"},{"key":"ref_4","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_5","first-page":"5105","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"Qi","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_6","unstructured":"Liu, X., Han, Z., Liu, Y.-S., and Zwicker, M. (February, January 27). Point2sequence: Learning the shape representation of 3d point clouds with an attention-based sequence to sequence network. Proceedings of the AAAI Conference on Artificial Intelligence, Honolulu, HI, USA."},{"key":"ref_7","unstructured":"Goyal, A., Law, H., Liu, B., Newell, A., and Deng, J. (March, January 26). Revisiting point cloud shape classification with a simple and effective baseline. Proceedings of the International Conference on Machine Learning, Shenzhen, China."},{"key":"ref_8","unstructured":"Thomas, H., Qi, C.R., 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 IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_9","unstructured":"Hamdi, A., Giancola, S., and Ghanem, B. (2021). Voint cloud: Multi-view point cloud representation for 3d understanding. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Su, H., Maji, S., Kalogerakis, E., and Learned-Miller, E. (2015, January 7\u201313). Multi-view convolutional neural networks for 3d shape recognition. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.114"},{"key":"ref_11","unstructured":"Jiang, J., Bao, D., Chen, Z., Zhao, X., and Gao, Y. (February, January 27). MLVCNN: Multi-loop-view convolutional neural network for 3D shape retrieval. Proceedings of the AAAI Conference on Artificial Intelligence, Honolulu, HI, USA."},{"key":"ref_12","first-page":"1","article-title":"Exploiting the PANORAMA Representation for Convolutional Neural Network Classification and Retrieval","volume":"7","author":"Sfikas","year":"2017","journal-title":"3DOR@ Eurographics"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"4381","DOI":"10.1109\/TPAMI.2024.3354961","article-title":"Point-to-pixel prompting for point cloud analysis with pre-trained image models","volume":"46","author":"Wang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_14","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., and Clark, J. (2021, January 18\u201324). Learning transferable visual models from natural language supervision. Proceedings of the International Conference on Machine Learning, Virtual."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Xue, L., Gao, M., Xing, C., Mart\u00edn-Mart\u00edn, R., Wu, J., Xiong, C., Xu, R., Niebles, J.C., and Savarese, S. (2023, January 18\u201322). Ulip: Learning a unified representation of language, images, and point clouds for 3d understanding. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"453","DOI":"10.1109\/TPAMI.2013.140","article-title":"Attribute-based classification for zero-shot visual object categorization","volume":"36","author":"Lampert","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Zhang, R., Guo, Z., Zhang, W., Li, K., Miao, X., Cui, B., Qiao, Y., Gao, P., and Li, H. (2022, January 18\u201324). Pointclip: Point cloud understanding by clip. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Zhu, X., Zhang, R., He, B., Guo, Z., Zeng, Z., Qin, Z., Zhang, S., and Gao, P. (2023, January 18\u201326). Pointclip v2: Prompting clip and gpt for powerful 3d open-world learning. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Paris, France.","DOI":"10.1109\/ICCV51070.2023.00249"},{"key":"ref_19","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_20","doi-asserted-by":"crossref","first-page":"8767","DOI":"10.1109\/TCSVT.2025.3551084","article-title":"MV-CLIP: Multi-view CLIP for zero-shot 3D shape recognition","volume":"35","author":"Song","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"131188","DOI":"10.1016\/j.neucom.2025.131188","article-title":"MVF-PointCLIP: Training-free multi-view fusion PointCLIP for zero-shot 3D classification","volume":"653","author":"Dai","year":"2025","journal-title":"Neurocomputing"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Shen, S., Zhu, Z., Fan, L., Zhang, H., and Wu, X. (2024, January 4\u20138). Diffclip: Leveraging stable diffusion for language grounded 3d classification. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA.","DOI":"10.1109\/WACV57701.2024.00356"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Lin, Z., Geng, S., Zhang, R., Gao, P., De Melo, G., Wang, X., Dai, J., Qiao, Y., and Li, H. (2022, January 23\u201327). Frozen clip models are efficient video learners. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel.","DOI":"10.1007\/978-3-031-19833-5_23"},{"key":"ref_24","first-page":"1","article-title":"Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing","volume":"55","author":"Liu","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Zhang, R., Hu, X., Li, B., Huang, S., Deng, H., Qiao, Y., Gao, P., and Li, H. (2023, January 18\u201322). Prompt, generate, then cache: Cascade of foundation models makes strong few-shot learners. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.01460"},{"key":"ref_26","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 IEEE\/CVF International Conference on Computer Vision, Virtual.","DOI":"10.1109\/ICCV48922.2021.00095"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Stuart, L.A.G., Morton, A., Stavness, I., and Pound, M.P. (2025, January 19\u201323). 3DGS-to-PC: 3D Gaussian Splatting to Dense Point Clouds. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Honolulu, HI, USA.","DOI":"10.1109\/ICCVW69036.2025.00395"},{"key":"ref_28","unstructured":"Wu, Z., Song, S., Khosla, A., Yu, F., Zhang, L., Tang, X., and Xiao, J. (2015, January 7\u201312). 3d shapenets: A deep representation for volumetric shapes. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA."},{"key":"ref_29","unstructured":"Uy, M.A., Pham, Q.-H., Hua, B.-S., Nguyen, T., and Yeung, S.-K. (November, January 27). Revisiting point cloud classification: A new benchmark dataset and classification model on real-world data. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_30","unstructured":"Zhang, C., Song, Y., Yao, L., and Cai, W. (February,  7\u201312). Shape-oriented convolution neural network for point cloud analysis. Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Huang, T., Dong, B., Yang, Y., Huang, X., Lau, R.W., Ouyang, W., and Zuo, W. (2023, January 18\u201326). Clip2point: Transfer clip to point cloud classification with image-depth pre-training. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Paris, France.","DOI":"10.1109\/ICCV51070.2023.02025"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Hegde, D., Valanarasu, J.M.J., and Patel, V. (2023, January 18\u201326). Clip goes 3d: Leveraging prompt tuning for language grounded 3d recognition. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Paris, France.","DOI":"10.1109\/ICCVW60793.2023.00217"},{"key":"ref_33","unstructured":"Qi, Z., Dong, R., Fan, G., Ge, Z., Zhang, X., Ma, K., and Yi, L. (2023, January 23\u201329). Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining. Proceedings of the 40th International Conference on Machine Learning, Honolulu, HI, USA."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/14\/4598\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T04:37:33Z","timestamp":1784695053000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/14\/4598"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,20]]},"references-count":33,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["s26144598"],"URL":"https:\/\/doi.org\/10.3390\/s26144598","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,20]]}}}