{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T19:07:07Z","timestamp":1788894427790,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":92,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370433","type":"print"},{"value":"9783032370440","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37044-0_12","type":"book-chapter","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:22:44Z","timestamp":1788891764000},"page":"206-225","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Volume Transformer: Revisiting Vanilla Transformers for\u00a03D Scene Understanding"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2239-8230","authenticated-orcid":false,"given":"Kadir","family":"Yilmaz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0822-0291","authenticated-orcid":false,"given":"Adrian","family":"Kruse","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4420-3576","authenticated-orcid":false,"given":"Tristan","family":"H\u00f6fer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0559-5341","authenticated-orcid":false,"given":"Daan","family":"de Geus","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4225-0051","authenticated-orcid":false,"given":"Bastian","family":"Leibe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"12_CR1","unstructured":"Abnar, S., Dehghani, M., Zuidema, W.: Transferring inductive biases through knowledge distillation. arXiv:2006.00555 arXiv preprint (2020)"},{"key":"12_CR2","unstructured":"Andersch, M., et al.: NVIDIA hopper architecture in-depth (2022). https:\/\/developer.nvidia.com\/blog\/nvidia-hopper-architecture-in-depth\/. NVIDIA Technical Blog. Accessed 23 Feb 2026"},{"key":"12_CR3","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer Normalization. arXiv:1607.06450 arXiv preprint (2016)"},{"key":"12_CR4","unstructured":"Baruch, G., et al.: ARKitScenes - a diverse real-world dataset for 3d indoor scene understanding using mobile RGB-D data. In: NeurIPS (2021)"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Behley, J., et al.: SemanticKITTI: a dataset for semantic scene understanding of lidar sequences. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00939"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Berman, M., Triki, A.R., Blaschko, M.B.: The Lov\u00e1sz-Softmax loss: a tractable surrogate for the optimization of the intersection-over-union measure in neural networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00464"},{"key":"12_CR7","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: NeurIPS (2020)"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: NUSCENES: a multimodal dataset for autonomous driving. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"12_CR9","unstructured":"Carion, N., et\u00a0al.: SAM 3: segment anything with concepts. arXiv preprint arXiv:2511.16719 (2025)"},{"key":"12_CR10","unstructured":"Chang, A.X., et al.: ShapeNet: an Information-Rich 3D Model Repository. arXiv:1512.03012 arXiv preprint (2015)"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Chen, X., Cao, Q., Zhong, Y., Zhang, J., Gao, S., Tao, D.: DearKD: data-efficient early knowledge distillation for vision transformers. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01174"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Cherti, M., et al.: Reproducible scaling laws for contrastive language-image learning. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Choy, C., Gwak, J., Savarese, S.: 4D Spatio-temporal convnets: minkowski convolutional neural networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00319"},{"key":"12_CR14","unstructured":"Cordonnier, J.B., Loukas, A., Jaggi, M.: On the relationship between self-attention and convolutional layers. In: ICLR (2020)"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: ScanNet: richly-annotated 3D reconstructions of indoor scenes. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"12_CR16","unstructured":"Dao, T.: FlashAttention-2: faster attention with better parallelism and work partitioning. In: ICLR (2024)"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Dao, T., Fu, D.Y., Ermon, S., Rudra, A., R\u00e9, C.: FlashAttention: fast and memory-efficient exact attention with IO-awareness. In: NeurIPS (2022)","DOI":"10.52202\/068431-1189"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"12_CR19","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"12_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105171","volume":"149","author":"Y Fang","year":"2024","unstructured":"Fang, Y., Sun, Q., Wang, X., Huang, T., Wang, X., Cao, Y.: EVA-02: a visual representation for neon genesis. Image Vis. Comput. 149, 105171 (2024)","journal-title":"Image Vis. Comput."},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Feng, T., Wang, W., Ma, F., Yang, Y.: LSK3DNet: towards effective and efficient 3D perception with large sparse kernels. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01413"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Graham, B., Engelcke, M., Van Der Maaten, L.: 3D semantic segmentation with submanifold sparse convolutional networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00961"},{"key":"12_CR23","unstructured":"Grattafiori, A., et al.: The Llama 3 Herd of Models. arXiv:2407.21783 arXiv preprint (2024)"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Guo, M.H., Cai, J.X., Liu, Z.N., Mu, T.J., Martin, R.R., Hu, S.M.: PCT: point cloud transformer. Computational Visual Media (2021)","DOI":"10.1007\/s41095-021-0229-5"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Guo, Y., Wang, H., Hu, Q., Liu, H., Liu, L., Bennamoun, M.: Deep learning for 3D point clouds: a survey. IEEE TPAMI (2020)","DOI":"10.1109\/TPAMI.2020.3005434"},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Henry, A., Dachapally, P.R., Pawar, S.S., Chen, Y.: Query-key normalization for transformers. In: Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 4246\u20134253 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.379"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Heo, B., Park, S., Han, D., Yun, S.: Rotary position embedding for vision transformer. In: ECCV (2024)","DOI":"10.1007\/978-3-031-72684-2_17"},{"key":"12_CR29","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv:1503.02531 arXiv preprint (2015)"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Huang, G., Sun, Y., Liu, Z., Sedra, D., Weinberger, K.Q.: Deep networks with stochastic depth. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Ji, G., Weder, S., Engelmann, F., Pollefeys, M., Blum, H.: ARKit LabelMaker: a new scale for indoor 3D scene understanding. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00415"},{"key":"12_CR32","unstructured":"Kaplan, J., et al.: Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)"},{"key":"12_CR33","unstructured":"Knaebel, K., Schult, J., Hermans, A., Leibe, B.: Point2Vec for self-supervised representation learning on point clouds. In: GCPR (2023)"},{"key":"12_CR34","doi-asserted-by":"crossref","unstructured":"Knaebel, K., et al.: DINO in the room: leveraging 2D foundation models for 3D segmentation. In: 3DV (2026)","DOI":"10.1109\/3DV69130.2026.00178"},{"key":"12_CR35","doi-asserted-by":"crossref","unstructured":"Kolodiazhnyi, M., Vorontsova, A., Konushin, A., Rukhovich, D.: OneFormer3D: one transformer for unified point cloud segmentation. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01979"},{"key":"12_CR36","doi-asserted-by":"crossref","unstructured":"Lai, X., Chen, Y., Lu, F., Liu, J., Jia, J.: Spherical transformer for LiDAR-Based 3D recognition. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01683"},{"key":"12_CR37","doi-asserted-by":"crossref","unstructured":"Lai, X., et al.: Stratified transformer for 3D point cloud segmentation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00831"},{"key":"12_CR38","doi-asserted-by":"crossref","unstructured":"Lai, X., Yuan, Y., Chu, R., Chen, Y., Hu, H., Jia, J.: Mask-attention-free transformer for 3D instance segmentation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00342"},{"key":"12_CR39","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2019)"},{"key":"12_CR40","doi-asserted-by":"crossref","unstructured":"Lu, J., Deng, J.: Relation3D: enhancing relation modeling for point cloud instance segmentation. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00831"},{"key":"12_CR41","doi-asserted-by":"crossref","unstructured":"Lu, J., Deng, J., Wang, C., He, J., Zhang, T.: Query refinement transformer for 3D instance segmentation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01697"},{"key":"12_CR42","doi-asserted-by":"crossref","unstructured":"Nekrasov, A., Schult, J., Litany, O., Leibe, B., Engelmann, F.: Mix3D: out-of-context data augmentation for 3D scenes. In: 3DV (2021)","DOI":"10.1109\/3DV53792.2021.00022"},{"key":"12_CR43","unstructured":"Oquab, M., Darcet, T., Moutakanni, T., Vo, H.V., Szafraniec, M., Khalidov, V.: DINOv2: learning robust visual features without supervision. TMLR (2024)"},{"key":"12_CR44","doi-asserted-by":"crossref","unstructured":"Pang, Y., Wang, W., Tay, F.E., Liu, W., Tian, Y., Yuan, L.: Masked autoencoders for point cloud self-supervised learning. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"12_CR45","unstructured":"Paszke, A., et al.: PyTorch: an imperative style, highperformance deep learning library. In: NeurIPS (2019)"},{"key":"12_CR46","doi-asserted-by":"crossref","unstructured":"Peng, B., et al.: OA-CNNs: omni-adaptive sparse CNNs for 3D semantic segmentation. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02013"},{"key":"12_CR47","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: CVPR (2017)"},{"key":"12_CR48","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: NeurIPS (2017)"},{"key":"12_CR49","doi-asserted-by":"crossref","unstructured":"Qian, G., et al.: PointNeXt: revisiting PointNet++ with improved training and scaling strategies. In: NeurIPS (2022)","DOI":"10.52202\/068431-1685"},{"key":"12_CR50","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"12_CR51","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: ICML (2023)"},{"key":"12_CR52","unstructured":"Raghu, M., Unterthiner, T., Kornblith, S., Zhang, C., Dosovitskiy, A.: Do vision transformers see like convolutional neural networks? In: NeurIPS (2021)"},{"key":"12_CR53","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"12_CR54","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: MICCAI (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"12_CR55","doi-asserted-by":"crossref","unstructured":"Rozenberszki, D., Litany, O., Dai, A.: Language-grounded indoor 3D semantic segmentation in the wild. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19827-4_8"},{"key":"12_CR56","doi-asserted-by":"crossref","unstructured":"Schuhmann, C., et\u00a0al.: LAION-5B: an open large-scale dataset for training next generation image-text models. In: NeurIPS (2022)","DOI":"10.52202\/068431-1833"},{"key":"12_CR57","unstructured":"Schuhmann, C., et al.: LAION-400M: open dataset of CLIP-Filtered 400 million image-text Pairs. arXiv:2111.02114 arXiv preprint (2021)"},{"key":"12_CR58","doi-asserted-by":"crossref","unstructured":"Schult, J., Engelmann, F., Hermans, A., Litany, O., Tang, S., Leibe, B.: Mask3D: mask transformer for 3D semantic instance segmentation. In: ICRA (2023)","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"12_CR59","doi-asserted-by":"crossref","unstructured":"Shah, J., Bikshandi, G., Zhang, Y., Thakkar, V., Ramani, P., Dao, T.: FlashAttention-3: fast and accurate attention with asynchrony and low-precision. In: NeurIPS (2024)","DOI":"10.52202\/079017-2193"},{"key":"12_CR60","doi-asserted-by":"crossref","unstructured":"Shin, S., Zhou, K., Vankadari, M., Markham, A., Trigoni, N.: Spherical mask: coarse-to-Fine 3D point cloud instance segmentation with spherical representation. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00389"},{"key":"12_CR61","unstructured":"Sim\u00e9oni, O., et al.: DINOv3. arXiv preprint arXiv:2508.10104 (2025)"},{"key":"12_CR62","doi-asserted-by":"crossref","unstructured":"Smith, L.N., Topin, N.: Super-convergence: very fast training of neural networks using large learning rates. In: Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications (2019)","DOI":"10.1117\/12.2520589"},{"key":"12_CR63","unstructured":"SpconvContributors: Spconv: Spatially Sparse Convolution Library (2022). https:\/\/github.com\/traveller59\/spconv"},{"key":"12_CR64","unstructured":"Steiner, A.P., Kolesnikov, A., Zhai, X., Wightman, R., Uszkoreit, J., Beyer, L.: How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers. TMLR (2022)"},{"key":"12_CR65","doi-asserted-by":"crossref","unstructured":"Su, J., Ahmed, M., Lu, Y., Pan, S., Bo, W., Liu, Y.: RoFormer: enhanced transformer with rotary position embedding. Neurocomputing (2024)","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"12_CR66","doi-asserted-by":"crossref","unstructured":"Sun, J., Qing, C., Tan, J., Xu, X.: Superpoint transformer for 3D scene instance segmentation. In: AAAI (2023)","DOI":"10.1609\/aaai.v37i2.25335"},{"key":"12_CR67","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: Scalability in perception for autonomous driving: waymo open dataset. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"12_CR68","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"12_CR69","doi-asserted-by":"crossref","unstructured":"Tang, H., et al.: Searching efficient 3D architectures with sparse point-voxel convolution. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58604-1_41"},{"key":"12_CR70","doi-asserted-by":"crossref","unstructured":"Tang, H., et al.: Searching efficient 3D architectures with sparse point-voxel convolution. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58604-1_41"},{"key":"12_CR71","unstructured":"Team, G., et\u00a0al.: Gemma 3 Technical Report. arXiv preprint arXiv:2503.19786 (2025)"},{"key":"12_CR72","doi-asserted-by":"crossref","unstructured":"Thomas, H., Qi, C.R., Deschaud, J.E., Marcotegui, B., Goulette, F., Guibas, L.J.: KPConv: flexible and deformable convolution for point clouds. In: CVPR (2019)","DOI":"10.1109\/ICCV.2019.00651"},{"key":"12_CR73","doi-asserted-by":"crossref","unstructured":"Thomas, H., Tsai, Y.H.H., Barfoot, T.D., Zhang, J.: KPConvX: modernizing kernel point convolution with kernel attention. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00528"},{"key":"12_CR74","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: ICML (2021)"},{"key":"12_CR75","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"12_CR76","doi-asserted-by":"crossref","unstructured":"Wang, P.S.: OctFormer: octree-based transformers for 3d point clouds. ACM Trans. Graph. (SIGGRAPH) 42(4) (2023)","DOI":"10.1145\/3592131"},{"key":"12_CR77","doi-asserted-by":"publisher","unstructured":"Wightman, R.: PyTorch image models (2019). https:\/\/github.com\/rwightman\/pytorch-image-models. https:\/\/doi.org\/10.5281\/zenodo.4414861","DOI":"10.5281\/zenodo.4414861"},{"key":"12_CR78","doi-asserted-by":"crossref","unstructured":"Wu, W., Qi, Z., Fuxin, L.: Pointconv: deep convolutional networks on 3D point clouds. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00985"},{"key":"12_CR79","doi-asserted-by":"crossref","unstructured":"Wu, X., et al.: Point transformer V3: simpler, faster, stronger. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00463"},{"key":"12_CR80","doi-asserted-by":"crossref","unstructured":"Wu, X., Lao, Y., Jiang, L., Liu, X., Zhao, H.: Point transformer V2: grouped vector attention and partition-based pooling. In: NeurIPS (2022)","DOI":"10.52202\/068431-2415"},{"key":"12_CR81","doi-asserted-by":"crossref","unstructured":"Wu, X., et al.: Towards large-scale 3D representation learning with multi-dataset point prompt training. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01849"},{"key":"12_CR82","unstructured":"Wu, Z., et al.: 3D ShapeNets: a deep representation for volumetric shapes. In: CVPR (2015)"},{"key":"12_CR83","unstructured":"Yang, Y.Q., et al.: Swin3D: a pretrained transformer backbone for 3D indoor scene understanding. arXiv preprint arXiv:2304.06906 (2023)"},{"key":"12_CR84","doi-asserted-by":"crossref","unstructured":"Yao, L., Wang, Y., Liu, M., Chau, L.P.: SGIFormer: semantic-guided and geometric-enhanced interleaving transformer for 3D instance segmentation. IEEE Trans. Circuits Syst. Video Technol. (2024)","DOI":"10.1109\/TCSVT.2024.3498041"},{"key":"12_CR85","doi-asserted-by":"crossref","unstructured":"Yeshwanth, C., Liu, Y.C., Nie\u00dfner, M., Dai, A.: ScanNet++: a high-fidelity dataset of 3d indoor scenes. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"12_CR86","doi-asserted-by":"crossref","unstructured":"Yilmaz, K., Schult, J., Nekrasov, A., Leibe, B.: Mask4Former: mask transformer for 4d panoptic segmentation. In: ICRA (2024)","DOI":"10.1109\/ICRA57147.2024.10610262"},{"key":"12_CR87","doi-asserted-by":"crossref","unstructured":"Yu, X., Tang, L., Rao, Y., Huang, T., Zhou, J., Lu, J.: Point-BERT: pre-training 3D point cloud transformers with masked point modeling. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"12_CR88","unstructured":"Yue, Y., et al.: LitePT: Lighter Yet Stronger Point Transformer. arXiv:2512.13689 arXiv preprint (2025)"},{"key":"12_CR89","doi-asserted-by":"crossref","unstructured":"Zhao, B., Song, R., Liang, J.: Cumulative spatial knowledge distillation for vision transformers. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00565"},{"key":"12_CR90","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jiang, L., Jia, J., Torr, P.H., Koltun, V.: Point transformer. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"12_CR91","doi-asserted-by":"crossref","unstructured":"Zheng, J., Zhang, J., Li, J., Tang, R., Gao, S., Zhou, Z.: Structured3D: a large photo-realistic dataset for structured 3D modeling. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58545-7_30"},{"key":"12_CR92","doi-asserted-by":"crossref","unstructured":"Zhu, X., et al.: Cylindrical and asymmetrical 3D convolution networks for LiDAR segmentation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00981"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37044-0_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:23:07Z","timestamp":1788891787000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37044-0_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370433","9783032370440"],"references-count":92,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37044-0_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"9 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}