{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T17:02:59Z","timestamp":1784566979554,"version":"3.55.0"},"reference-count":79,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T00:00:00Z","timestamp":1779753600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T00:00:00Z","timestamp":1779753600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s11263-026-02884-2","type":"journal-article","created":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T17:48:26Z","timestamp":1779817706000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Point2Seq: Quantized Serialization Encoding for Object Point Cloud Pretraining"],"prefix":"10.1007","volume":"134","author":[{"given":"Xumin","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zuyan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6121-5529","authenticated-orcid":false,"given":"Jiwen","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,26]]},"reference":[{"issue":"4","key":"2884_CR1","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/MSP.2017.2693418","volume":"34","author":"MM Bronstein","year":"2017","unstructured":"Bronstein, M. M., Bruna, J., LeCun, Y., Szlam, A., & Vandergheynst, P. (2017). Geometric deep learning: going beyond euclidean data. IEEE Signal Processing Magazine, 34(4), 18\u201342.","journal-title":"IEEE Signal Processing Magazine"},{"key":"2884_CR2","first-page":"4436","volume":"30","author":"S Cheng","year":"2021","unstructured":"Cheng, S., Chen, X., He, X., Liu, Z., & Bai, X. (2021). Pra-net: Point relation-aware network for 3d point cloud analysis. TIP., 30, 4436\u20134448.","journal-title":"TIP."},{"key":"2884_CR3","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A. X., Savva, M., Halber, M., Funkhouser, T., & Nie\u00dfner, M. (2017). Scannet: Richly-annotated 3d reconstructions of indoor scenes. CVPR.","DOI":"10.1109\/CVPR.2017.261"},{"key":"2884_CR4","doi-asserted-by":"crossref","unstructured":"Deitke, M., Schwenk, D., Salvador, J., Weihs, L., Michel, O., VanderBilt, E., Schmidt, L., Ehsani, K., Kembhavi, A., & Farhadi, A. (2022) Objaverse: A universe of annotated 3d objects. arXiv:2212.08051","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"2884_CR5","doi-asserted-by":"crossref","unstructured":"Deitke, M., Liu, R., Wallingford, M., Ngo, H., Michel, O., Kusupati, A., Fan, A., Laforte, C., Voleti, V., Gadre, S. Y., VanderBilt, E., Kembhavi, A., Vondrick, C., Gkioxari, G., Ehsani, K., Schmidt, L., & Farhadi, A. (2023) Objaverse-xl: A universe of 10m+ 3d objects. arXiv:2307.05663","DOI":"10.52202\/075280-1554"},{"key":"2884_CR6","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L. J., Li, K., & Fei-Fei, L. (2009) Imagenet: A large-scale hierarchical image database. In: CVPR, Ieee","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2884_CR7","unstructured":"Dong, R., Qi, Z., Zhang, L., Zhang, J., Sun, J., Ge, Z., Yi, L., & Ma, K. (2022) Autoencoders as cross-modal teachers: Can pretrained 2d image transformers help 3d representation learning? In: ICLR"},{"key":"2884_CR8","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., & Gelly, S. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. ICLR."},{"key":"2884_CR9","doi-asserted-by":"crossref","unstructured":"Fan, H., Su, H., & Guibas, L. J. (2017). A point set generation network for 3d object reconstruction from a single image. CVPR.","DOI":"10.1109\/CVPR.2017.264"},{"key":"2884_CR10","unstructured":"Graham, B., & Van\u00a0der Maaten, L. (2017) Submanifold sparse convolutional networks. arXiv:1706.01307"},{"key":"2884_CR11","doi-asserted-by":"crossref","unstructured":"Graham, B., Engelcke, M., & Van Der\u00a0Maaten, L. (2018) 3d semantic segmentation with submanifold sparse convolutional networks. CVPR","DOI":"10.1109\/CVPR.2018.00961"},{"key":"2884_CR12","doi-asserted-by":"crossref","unstructured":"Groueix, T., Fisher, M., Kim, V. G., Russell, B. C., & A. M. (2018). Atlasnet: A papier-m\u00e2ch\u00e9 approach to learning 3d surface generation. CoRR.","DOI":"10.1109\/CVPR.2018.00030"},{"issue":"2","key":"2884_CR13","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1007\/s41095-021-0229-5","volume":"7","author":"MH Guo","year":"2021","unstructured":"Guo, M. H., Cai, J. X., Liu, Z. N., Mu, T. J., Martin, R. R., & Hu, S. M. (2021). Pct: Point cloud transformer. Computational Visual Media, 7(2), 187\u2013199.","journal-title":"Computational Visual Media"},{"key":"2884_CR14","doi-asserted-by":"crossref","unstructured":"Hamdi, A., Giancola, S., & Ghanem, B. (2021). Mvtn: Multi-view transformation network for 3d shape recognition. ICCV.","DOI":"10.1109\/ICCV48922.2021.00007"},{"key":"2884_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. CVPR.","DOI":"10.1109\/CVPR.2016.90"},{"key":"2884_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020). Momentum contrast for unsupervised visual representation learning. CVPR.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"2884_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., & Girshick, R. (2021). Masked autoencoders are scalable vision learners arXiv:2111.06377.","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"2884_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., & Girshick, R. (2022). Masked autoencoders are scalable vision learners. CVPR.","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"2884_CR19","doi-asserted-by":"crossref","unstructured":"Huang, Z., Yu, Y., Xu, J., Ni, F., & Le, X. (2020). Pf-net: Point fractal network for 3d point cloud completion. CVPR.","DOI":"10.1109\/CVPR42600.2020.00768"},{"key":"2884_CR20","unstructured":"Kenton, J., & Toutanova, L. K. (2019). Bert: Pre-training of deep bidirectional transformers for language understanding. NAACL."},{"key":"2884_CR21","unstructured":"Krizhevsky, A., & Hinton, G. (2009). Learning multiple layers of features from tiny images. csutorontoca"},{"issue":"2","key":"2884_CR22","first-page":"896","volume":"3","author":"DH Lee","year":"2013","unstructured":"Lee, D. H. (2013). Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. ICML Workshop. Atlanta, 3(2), 896.","journal-title":"ICML Workshop. Atlanta"},{"key":"2884_CR23","doi-asserted-by":"crossref","unstructured":"Liu, H., Cai, M., Lee, Y. J. (2022a) Masked discrimination for self-supervised learning on point clouds. ECCV","DOI":"10.1007\/978-3-031-20086-1_38"},{"key":"2884_CR24","doi-asserted-by":"crossref","unstructured":"Liu, M., Sheng, L., Yang, S., Shao, J., & Hu, S. M. (2020). Morphing and sampling network for dense point cloud completion. AAAI.","DOI":"10.1609\/aaai.v34i07.6827"},{"key":"2884_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021) Swin transformer: Hierarchical vision transformer using shifted windows. In: ICCV","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2884_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C. Y., Feichtenhofer, C., Darrell, T., & Xie, S. (2022b) A convnet for the 2020s. arXiv:2201.03545","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"2884_CR27","unstructured":"Ma, X., Qin, C., You, H., Ran, H., & Fu, Y. (2022). Rethinking network design and local geometry in point cloud: A simple residual mlp framework. ICLR."},{"key":"2884_CR28","doi-asserted-by":"crossref","unstructured":"Maturana, D., & Scherer, S. (2015). Voxnet: A 3d convolutional neural network for real-time object recognition. IROS, IEEE.","DOI":"10.1109\/IROS.2015.7353481"},{"key":"2884_CR29","doi-asserted-by":"crossref","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., & Ostrovski, G, et\u00a0al. (2015) Human-level control through deep reinforcement learning. nature","DOI":"10.1038\/nature14236"},{"key":"2884_CR30","doi-asserted-by":"crossref","unstructured":"Pan, L., Chen, X., Cai, Z., Zhang, J., Zhao, H., Yi, S., & Liu, Z. (2021). Variational relational point completion network. CVPR.","DOI":"10.1109\/CVPR46437.2021.00842"},{"key":"2884_CR31","doi-asserted-by":"crossref","unstructured":"Pang, Y., Wang, W., Tay, F., Liu, W., Tian, Y., & Yuan, L. (2022). Masked autoencoders for point cloud self-supervised learning. ECCV.","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"2884_CR32","doi-asserted-by":"crossref","unstructured":"Peebles, W., & Xie, S. (2023). Scalable diffusion models with transformers. ICCV.","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"2884_CR33","unstructured":"Qi, C. R., Su, H., Mo, K., & Guibas, L. J. (2017a) Pointnet: Deep learning on point sets for 3d classification and segmentation. In: CVPR"},{"key":"2884_CR34","unstructured":"Qi, C. R., Su, H., Mo, K., & Guibas, L. J. (2017b) Pointnet: Deep learning on point sets for 3d classification and segmentation. In: CVPR"},{"key":"2884_CR35","unstructured":"Qi, C. R., Yi, L., Su, H., & Guibas, L. J.(2017c) Pointnet++: Deep hierarchical feature learning on point sets in a metric space. NeurIPS"},{"key":"2884_CR36","unstructured":"Qi, Z., Dong, R., Fan, G., Ge, Z., Zhang, X., Ma, K., & Yi, L. (2023). Contrast with reconstruct: Contrastive 3d representation learning guided by generative pretraining. ICML."},{"key":"2884_CR37","doi-asserted-by":"crossref","unstructured":"Qian, G., Li, Y., Peng, H., Mai, J., Hammoud, H., Elhoseiny, M.,& Ghanem, B.(2022) Pointnext: Revisiting pointnet++ with improved training and scaling strategies. arXiv:2206.04670","DOI":"10.52202\/068431-1685"},{"key":"2884_CR38","unstructured":"Radford, A., Kim, J. W., Hallacy, C., Goh, R. A., Agarwal, G., Sastry, S., Askell, G., Mishkin, A., Clark, P., & J. (2021). Learning transferable visual models from natural language supervision. ICML."},{"key":"2884_CR39","doi-asserted-by":"crossref","unstructured":"Ran, H., Liu, J., & Wang, C. (2022). Surface representation for point clouds. CVPR.","DOI":"10.1109\/CVPR52688.2022.01837"},{"key":"2884_CR40","doi-asserted-by":"crossref","unstructured":"Rao, Y., Zhao, W., Tang, Y., Zhou, J., Lim, S. L., & Lu, J. (2022). Hornet: Efficient high-order spatial interactions with recursive gated convolutions arXiv:2207.14284.","DOI":"10.52202\/068431-0752"},{"key":"2884_CR41","doi-asserted-by":"crossref","unstructured":"Riegler, G., Osman Ulusoy, A., & Geiger, A. (2017). Octnet: Learning deep 3d representations at high resolutions. CVPR.","DOI":"10.1109\/CVPR.2017.701"},{"key":"2884_CR42","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. CVPR.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2884_CR43","doi-asserted-by":"crossref","unstructured":"Schuhmann, C., Beaumont, R., Vencu, R., Gordon, C., Wightman, R., Cherti, M., Coombes, T., Katta, A., Mullis, C., & Wortsman, M. (2022). Laion-5b: An open large-scale dataset for training next generation image-text models. NeurIPS.","DOI":"10.52202\/068431-1833"},{"key":"2884_CR44","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015). Going deeper with convolutions. CVPR.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"2884_CR45","unstructured":"Tan, M., & Le, Q. (2019) Efficientnet: Rethinking model scaling for convolutional neural networks. In: ICML, PMLR"},{"key":"2884_CR46","doi-asserted-by":"crossref","unstructured":"Tang, J., Gong, Z., Yi, R., Xie, Y., & Ma, L. (2022). Lake-net: Topology-aware point cloud completion by localizing aligned keypoints. CVPR.","DOI":"10.1109\/CVPR52688.2022.00177"},{"key":"2884_CR47","doi-asserted-by":"crossref","unstructured":"Tchapmi, L. P., Kosaraju, V., Rezatofighi, H., Reid, I. D., & Savarese, S. (2019). Topnet: Structural point cloud decoder. CVPR.","DOI":"10.1109\/CVPR.2019.00047"},{"key":"2884_CR48","doi-asserted-by":"crossref","unstructured":"Thomas, H., Qi, C. R., Deschaud, J. E., Marcotegui, B., Goulette, F.,& Guibas, L. J.(2019) Kpconv: Flexible and deformable convolution for point clouds. In: ICCV","DOI":"10.1109\/ICCV.2019.00651"},{"key":"2884_CR49","doi-asserted-by":"crossref","unstructured":"Uy, M. A., Pham, Q. H., Hua, B. S., Nguyen, T., & Yeung, S. K. (2019). Revisiting point cloud classification: A new benchmark dataset and classification model on real-world data. ICCV.","DOI":"10.1109\/ICCV.2019.00167"},{"key":"2884_CR50","unstructured":"Van Den Oord, A., & Vinyals, O. (2017). Neural discrete representation learning. NeurIPS, 30,"},{"key":"2884_CR51","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention is all you need. NeurIPS."},{"key":"2884_CR52","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1016\/j.cag.2018.07.011","volume":"76","author":"P Wang","year":"2018","unstructured":"Wang, P., Gan, Y., Shui, P., Yu, F., Zhang, Y., Chen, S., & Sun, Z. (2018). 3d shape segmentation via shape fully convolutional networks. Computers & Graphics, 76, 182\u2013192.","journal-title":"Computers & Graphics"},{"key":"2884_CR53","first-page":"1","volume":"36","author":"PS Wang","year":"2017","unstructured":"Wang, P. S., Liu, Y., Guo, Y. X., Sun, C. Y., & Tong, X. (2017). Cnns on octree data for 3d shape analysis. TOG, 36, 1\u201311.","journal-title":"TOG"},{"issue":"11","key":"2884_CR54","first-page":"8139","volume":"44","author":"X Wang","year":"2021","unstructured":"Wang, X., Ang, M. H., & Lee, G. H. (2021). Cascaded refinement network for point cloud completion with self-supervision. T-PA, 44(11), 8139\u20138150.","journal-title":"T-PA"},{"issue":"5","key":"2884_CR55","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3326362","volume":"38","author":"Y Wang","year":"2019","unstructured":"Wang, Y., Sun, Y., Liu, Z., Sarma, S. E., Bronstein, M. M., & Solomon, J. M. (2019). Dynamic graph cnn for learning on point clouds. TOG, 38(5), 1\u201312.","journal-title":"TOG"},{"issue":"5","key":"2884_CR56","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3326362","volume":"38","author":"Y Wang","year":"2019","unstructured":"Wang, Y., Sun, Y., Liu, Z., Sarma, S. E., Bronstein, M. M., & Solomon, J. M. (2019). Dynamic graph cnn for learning on point clouds. TOG, 38(5), 1\u201312.","journal-title":"TOG"},{"key":"2884_CR57","doi-asserted-by":"crossref","unstructured":"Wang, Z., Yu, X., Rao, Y., Zhou, J., & Lu, J. (2022). P2p: Tuning pre-trained image models for point cloud analysis with point-to-pixel prompting. NeurIPS.","DOI":"10.52202\/068431-1046"},{"key":"2884_CR58","doi-asserted-by":"crossref","unstructured":"Wang, Z., Yu, X., Rao, Y., Zhou, J., & Lu, J. (2023). Take-a-photo: 3d-to-2d generative pre-training of point cloud models. ICCV.","DOI":"10.1109\/ICCV51070.2023.00519"},{"key":"2884_CR59","doi-asserted-by":"crossref","unstructured":"Wang, Z., Rao, Y., Yu, X., Zhou, J., & Lu, J. (2024). Point-to-pixel prompting for point cloud analysis with pre-trained image models T-PAMI.","DOI":"10.1109\/TPAMI.2024.3354961"},{"key":"2884_CR60","doi-asserted-by":"crossref","unstructured":"Wu, X., Jiang, L., Wang, P. S., Liu, Z., Liu, X., Qiao, Y., & Zhao, H.(2024) Point transformer v3: Simpler, faster, stronger. In: CVPR","DOI":"10.1109\/CVPR52733.2024.00463"},{"key":"2884_CR61","unstructured":"Wu, Z., Song, S., Khosla, A., Yu, F., Zhang, L., Tang, X., & Xiao, J.(2015a) 3d shapenets: A deep representation for volumetric shapes. In: CVPR"},{"key":"2884_CR62","unstructured":"Wu, Z., Song, S., Khosla, A., Yu, F., Zhang, L., Tang, X., & Xiao, J. ((2015b) 3d shapenets: A deep representation for volumetric shapes. CVPR"},{"key":"2884_CR63","doi-asserted-by":"crossref","unstructured":"Xiang, J., Lv, Z., Xu, S., Deng, Y., Wang, R., Zhang, B., Chen, D., Tong, X., & Yang, J. (2024). Structured 3d latents for scalable and versatile 3d generation arXiv:2412.01506.","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"2884_CR64","doi-asserted-by":"crossref","unstructured":"Xiang, P., Wen, X., Liu, Y. S., Cao, Y. P., Wan, P., Zheng, W., & Han, Z.(2021) Snowflakenet: Point cloud completion by snowflake point deconvolution with skip-transformer. In: ICCV","DOI":"10.1109\/ICCV48922.2021.00545"},{"key":"2884_CR65","doi-asserted-by":"crossref","unstructured":"Xie, H., Yao, H., Zhou, S., Mao, J., Zhang, S., & Sun, W.(2020) Grnet: Gridding residual network for dense point cloud completion. In: Vedaldi A, Bischof H, Brox T, Frahm J (eds) ECCV","DOI":"10.1007\/978-3-030-58545-7_21"},{"key":"2884_CR66","doi-asserted-by":"crossref","unstructured":"Xue, L., Yu, N., Zhang, S., Panagopoulou, A., Li, J., Mart\u00edn-Mart\u00edn, R., Wu, J., Xiong, C., Xu, R., & Niebles, J. C. (2024). Ulip-2: Towards scalable multimodal pre-training for 3d understanding. CVPR.","DOI":"10.1109\/CVPR52733.2024.02558"},{"key":"2884_CR67","doi-asserted-by":"crossref","unstructured":"Yang, Y., Feng, C., Shen, Y., & Tian, D. (2018). Foldingnet: Point cloud auto-encoder via deep grid deformation. CVPR.","DOI":"10.1109\/CVPR.2018.00029"},{"key":"2884_CR68","unstructured":"Yang, Y. Q., Guo, Y. X., Xiong, J. Y., Liu, Y., Pan, H., Wang, P. S., Tong, X., Guo, B. (2023) Swin3d: A pretrained transformer backbone for 3d indoor scene understanding. arXiv:2304.06906"},{"key":"2884_CR69","doi-asserted-by":"crossref","unstructured":"Yi, L., Kim, V. G., Ceylan, D., Shen, I. C., Yan, M., Su, H., Lu, C., Huang, Q., Sheffer, A., & Guibas, L. (2016). A scalable active framework for region annotation in 3d shape collections. ToG.","DOI":"10.1145\/2980179.2980238"},{"key":"2884_CR70","doi-asserted-by":"crossref","unstructured":"Yu, X., Rao, Y., Wang, Z., Liu, Z., Lu, J., & Zhou, J. (2021). Pointr: Diverse point cloud completion with geometry-aware transformers. ICCV.","DOI":"10.1109\/ICCV48922.2021.01227"},{"key":"2884_CR71","doi-asserted-by":"crossref","unstructured":"Yu, X., Tang, L., Rao, Y., Huang, T., Zhou, J., & Lu, J. (2022). Point-bert: Pre-training 3d point cloud transformers with masked point modeling (pp. 19313\u201319322). CVPR.","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"2884_CR72","doi-asserted-by":"crossref","unstructured":"Yu, X., Rao, Y., Wang, Z., Lu, J., & Zhou, J. (2023). Adapointr: Diverse point cloud completion with adaptive geometry-aware transformers T-PAMI.","DOI":"10.1109\/TPAMI.2023.3309253"},{"key":"2884_CR73","doi-asserted-by":"crossref","unstructured":"Yuan, W., Khot, T., Held, D., Mertz, C., & Hebert, M. (2018) PCN: point completion network. In: 3DV","DOI":"10.1109\/3DV.2018.00088"},{"key":"2884_CR74","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., & Agrawala, M. (2023a) Adding conditional control to text-to-image diffusion models. In: ICCV","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"2884_CR75","doi-asserted-by":"crossref","unstructured":"Zhang, R., Guo, Z., Gao, P., Fang, R., Zhao, B., Wang, D., Qiao, Y., & Li, H. (2022). Point-m2ae: Multi-scale masked autoencoders for hierarchical point cloud pre-training arXiv:2205.14401.","DOI":"10.52202\/068431-1962"},{"key":"2884_CR76","doi-asserted-by":"crossref","unstructured":"Zhang, R., Wang, L., Qiao, Y., Gao, P., & Li, H.(2023b) Learning 3d representations from 2d pre-trained models via image-to-point masked autoencoders. In: CVPR","DOI":"10.1109\/CVPR52729.2023.02085"},{"key":"2884_CR77","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jiang, L., Jia, J., & Torr, P. H.Koltun V (2021) Point transformer. ICCV.","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"2884_CR78","doi-asserted-by":"crossref","unstructured":"Zhou, H., Cao, Y., Chu, W., Zhu, J., Lu, T., Tai, Y., & Wang, C.(2022) Seedformer: Patch seeds based point cloud completion with upsample transformer. In: ECCV, Springer","DOI":"10.1007\/978-3-031-20062-5_24"},{"key":"2884_CR79","doi-asserted-by":"crossref","unstructured":"Zhou, Y., & Tuzel, O. (2018). Voxelnet: End-to-end learning for point cloud based 3d object detection. CVPR.","DOI":"10.1109\/CVPR.2018.00472"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02884-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-02884-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02884-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T16:13:45Z","timestamp":1784564025000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-026-02884-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,26]]},"references-count":79,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["2884"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-02884-2","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,26]]},"assertion":[{"value":"16 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This article does not contain any studies with human participants or animals.","order":1,"name":"Ethics","label":"Ethical Approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest","order":2,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No human subjects involved in this research.","order":3,"name":"Ethics","label":"Consent to Participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No individual person\u2019s data will be published in this research.","order":4,"name":"Ethics","label":"Consent for Publication","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"288"}}