{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T10:51:01Z","timestamp":1785322261326,"version":"3.55.0"},"reference-count":100,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,1,4]],"date-time":"2022-01-04T00:00:00Z","timestamp":1641254400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,4]],"date-time":"2022-01-04T00:00:00Z","timestamp":1641254400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000270","name":"Natural Environment Research Council","doi-asserted-by":"publisher","award":["NE\/P017134\/1"],"award-info":[{"award-number":["NE\/P017134\/1"]}],"id":[{"id":"10.13039\/501100000270","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2022,2]]},"DOI":"10.1007\/s11263-021-01554-9","type":"journal-article","created":{"date-parts":[[2022,1,4]],"date-time":"2022-01-04T12:02:41Z","timestamp":1641297761000},"page":"316-343","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":114,"title":["SensatUrban: Learning Semantics from Urban-Scale Photogrammetric Point Clouds"],"prefix":"10.1007","volume":"130","author":[{"given":"Qingyong","family":"Hu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2419-4140","authenticated-orcid":false,"given":"Bo","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheikh","family":"Khalid","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Niki","family":"Trigoni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Markham","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,1,4]]},"reference":[{"key":"1554_CR1","doi-asserted-by":"crossref","unstructured":"Aksoy, E. E., Baci, S., & Cavdar, S. (2019). Salsanet: Fast road and vehicle segmentation in LiDAR point clouds for autonomous driving. In 2020 IEEE intelligent vehicles symposium (IV) (pp. 926\u2013932).","DOI":"10.1109\/IV47402.2020.9304694"},{"key":"1554_CR2","unstructured":"Armeni, I., Sax, S., Zamir, A. R., & Savarese, S. (2017). Joint 2D-3D-semantic data for indoor scene understanding. In Proceedings of the IEEE\/CVF international conference on computer vision."},{"key":"1554_CR3","doi-asserted-by":"crossref","unstructured":"Behley, J., Garbade, M., Milioto, A., Quenzel, J., Behnke, S., Stachniss, C., & Gall, J. (2019). SemanticKITTI: A dataset for semantic scene understanding of LiDAR sequences. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 9297\u20139307)","DOI":"10.1109\/ICCV.2019.00939"},{"key":"1554_CR4","doi-asserted-by":"crossref","unstructured":"Berman, M., Rannen\u00a0Triki, A., & Blaschko, M. B. (2018). The lov\u00e1sz-softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 4413\u20134421).","DOI":"10.1109\/CVPR.2018.00464"},{"key":"1554_CR5","unstructured":"Boulch, A. (2019). Generalizing discrete convolutions for unstructured point clouds. arXiv preprint arXiv:1904.02375."},{"key":"1554_CR6","doi-asserted-by":"crossref","unstructured":"Caesar, H., Bankiti, V., Lang, AH., Vora, S., Liong, VE., Xu, Q., Krishnan, A., Pan, Y., Baldan, G., & Beijbom, O. (2020). nuScenes: A multimodal dataset for autonomous driving. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 11621\u201311631).","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"1554_CR7","doi-asserted-by":"crossref","unstructured":"Chang, A., Dai, A., Funkhouser, T., Halber, M., Niebner, M., Savva, M., Song, S., Zeng, A., & Zhang, Y. (2018). Matterport3D: Learning from RGB-D data in indoor environments. In 7th IEEE international conference on 3D vision, 3DV 2017 (pp. 667\u2013676).","DOI":"10.1109\/3DV.2017.00081"},{"key":"1554_CR8","unstructured":"Chang, AX., Funkhouser, T., Guibas, L., Hanrahan, P., Huang, Q., Li, Z., Savarese, S., Savva, M., Song, S., & Su, H., et\u00a0al. (2015). ShapeNet: An information-rich 3D model repository. arXiv preprint arXiv:1512.03012."},{"key":"1554_CR9","doi-asserted-by":"crossref","unstructured":"Chang, MF., Lambert, J., Sangkloy, P., Singh, J., Bak, S., Hartnett, A., Wang, D., Carr, P., Lucey, S., Ramanan, D., et\u00a0al. (2019) Argoverse: 3D tracking and forecasting with rich maps. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 8748\u20138757).","DOI":"10.1109\/CVPR.2019.00895"},{"key":"1554_CR10","unstructured":"Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A simple framework for contrastive learning of visual representations. In International conference on machine learning (pp. 1597\u20131607)."},{"key":"1554_CR11","doi-asserted-by":"crossref","unstructured":"Cheng, R., Razani, R., Taghavi, E., Li, E., & Liu, B. (2021) 2-s3net: Attentive feature fusion with adaptive feature selection for sparse semantic segmentation network. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 12547\u201312556).","DOI":"10.1109\/CVPR46437.2021.01236"},{"key":"1554_CR12","doi-asserted-by":"crossref","unstructured":"Choy, C., Gwak, J., & Savarese, S. (2019). 4D spatio-temporal convnets: Minkowski convolutional neural networks. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 3075\u20133084).","DOI":"10.1109\/CVPR.2019.00319"},{"key":"1554_CR13","doi-asserted-by":"crossref","unstructured":"Cortinhal, T., Tzelepis, G., & Aksoy, EE. (2020). Salsanext: Fast semantic segmentation of LiDAR point clouds for autonomous driving. arXiv preprint arXiv:2003.03653.","DOI":"10.1007\/978-3-030-64559-5_16"},{"key":"1554_CR14","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, AX., Savva, M., Halber, M., Funkhouser, T., & Nie\u00dfner, M. (2017). ScanNet: Richly-annotated 3D reconstructions of indoor scenes. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 5828\u20135839).","DOI":"10.1109\/CVPR.2017.261"},{"key":"1554_CR15","unstructured":"De\u00a0Deuge, M., Quadros, A., Hung, C., & Douillard, B. (2013). Unsupervised feature learning for classification of outdoor 3D scans. In Australasian conference on robitics and automation (Vol.\u00a02, p.\u00a01)."},{"key":"1554_CR16","doi-asserted-by":"crossref","unstructured":"Gaidon, A., Wang, Q., Cabon, Y., & Vig, E. (2016). Virtual worlds as proxy for multi-object tracking analysis. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 4340\u20134349).","DOI":"10.1109\/CVPR.2016.470"},{"key":"1554_CR17","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., & Urtasun, R. (2012). Are we ready for autonomous driving? the KITTI vision benchmark suite. In 2012 IEEE conference on computer vision and pattern recognition (pp. 3354\u20133361).","DOI":"10.1109\/CVPR.2012.6248074"},{"issue":"11","key":"1554_CR18","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A., Lenz, P., Stiller, C., & Urtasun, R. (2013). Vision meets robotics: The kitti dataset. The International Journal of Robotics Research, 32(11), 1231\u20131237.","journal-title":"The International Journal of Robotics Research"},{"issue":"9","key":"1554_CR19","doi-asserted-by":"publisher","first-page":"885","DOI":"10.14358\/PERS.77.9.885","volume":"77","author":"M Gerke","year":"2011","unstructured":"Gerke, M., & Kerle, N. (2011). Automatic structural seismic damage assessment with airborne oblique pictometry imagery. Photogrammetric Engineering& Remote Sensing, 77(9), 885\u2013898.","journal-title":"Photogrammetric Engineering & Remote Sensing"},{"key":"1554_CR20","unstructured":"Geyer, J., Kassahun, Y., Mahmudi, M., Ricou, X., Durgesh, R., Chung, A. S., Hauswald, L., Pham, V. H., M\u00fchlegg, M., Dorn, S., et\u00a0al. (2020) A2D2: Audi autonomous driving dataset. arXiv preprint arXiv:2004.06320."},{"key":"1554_CR21","doi-asserted-by":"crossref","unstructured":"Graham, B., Engelcke, M., & van\u00a0der Maaten, L. (2018). 3D semantic segmentation with submanifold sparse convolutional networks. In Proceedings of the IEEE\/CVF international conference on computer vision.","DOI":"10.1109\/CVPR.2018.00961"},{"key":"1554_CR22","doi-asserted-by":"crossref","unstructured":"Guo, Y., Wang, H., Hu, Q., Liu, H., Liu, L., & Bennamoun, M. (2020). Deep learning for 3D point clouds: A survey. IEEE TPAMI.","DOI":"10.1109\/TPAMI.2020.3005434"},{"key":"1554_CR23","doi-asserted-by":"crossref","unstructured":"Hackel, T., Savinov, N., Ladicky, L., Wegner, JD., Schindler, K., & Pollefeys, M. (2017). Semantic3D.Net: A new large-scale point cloud classification benchmark. ISPRS Annals of Photogrammetry, Remote Sensing & Spatial Information Sciences","DOI":"10.5194\/isprs-annals-IV-1-W1-91-2017"},{"key":"1554_CR24","doi-asserted-by":"crossref","unstructured":"Han, L., Zheng, T., Xu, L., & Fang, L. (2020). Occuseg: Occupancy-aware 3D instance segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 2940\u20132949).","DOI":"10.1109\/CVPR42600.2020.00301"},{"key":"1554_CR25","doi-asserted-by":"crossref","unstructured":"Handa, A., Patraucean, V., Badrinarayanan, V., Stent, S., & Cipolla, R. (2016). SceneNet: understanding real world indoor scenes with synthetic data. In Proceedings of the IEEE\/CVF international conference on computer vision.","DOI":"10.1109\/CVPR.2016.442"},{"key":"1554_CR26","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R (2020). Momentum contrast for unsupervised visual representation learning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 9729\u20139738).","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"1554_CR27","doi-asserted-by":"crossref","unstructured":"Hou, J., Graham, B., Nie\u00dfner, M., & Xie, S. (2020). Exploring data-efficient 3D scene understanding with contrastive scene contexts. arXiv preprint arXiv:2012.09165.","DOI":"10.1109\/CVPR46437.2021.01533"},{"issue":"2","key":"1554_CR28","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1109\/JPROC.2013.2295327","volume":"102","author":"L Hou","year":"2014","unstructured":"Hou, L., Wang, Y., Wang, X., Maynard, N., Cameron, I. T., Zhang, S., & Jiao, Y. (2014). Combining photogrammetry and augmented reality towards an integrated facility management system for the oil industry. Proceedings of the IEEE, 102(2), 204\u2013220.","journal-title":"Proceedings of the IEEE"},{"issue":"6","key":"1554_CR29","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1109\/MCG.2003.1242383","volume":"23","author":"J Hu","year":"2003","unstructured":"Hu, J., You, S., & Neumann, U. (2003). Approaches to large-scale urban modeling. IEEE Computer Graphics and Applications, 23(6), 62\u201369.","journal-title":"IEEE Computer Graphics and Applications"},{"key":"1554_CR30","doi-asserted-by":"crossref","unstructured":"Hu, Q., Yang, B., Xie, L., Rosa, S., Guo, Y., Wang, Z., Trigoni, N., & Markham, A. (2020). RandLA-Net: Efficient semantic segmentation of large-scale point clouds. In Proceedings of the IEEE\/CVF international conference on computer vision.","DOI":"10.1109\/CVPR42600.2020.01112"},{"key":"1554_CR31","doi-asserted-by":"crossref","unstructured":"Hu, Q., Yang, B., Khalid, S., Xiao, W., Trigoni, N., & Markham, A. (2021). Towards semantic segmentation of urban-scale 3D point clouds: A dataset, benchmarks and challenges. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 4977\u20134987).","DOI":"10.1109\/CVPR46437.2021.00494"},{"key":"1554_CR32","doi-asserted-by":"crossref","unstructured":"Jiang, L., Zhao, H., Shi, S., Liu, S., Fu, CW., & Jia, J. (2020). Pointgroup: Dual-set point grouping for 3D instance segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and Pattern recognition (pp. 4867\u20134876).","DOI":"10.1109\/CVPR42600.2020.00492"},{"key":"1554_CR33","doi-asserted-by":"crossref","unstructured":"K\u00f6lle, M., Laupheimer, D., Schmohl, S., Haala, N., Rottensteiner, F., Wegner, JD., & Ledoux, H. (2021). H3d: Benchmark on semantic segmentation of high-resolution 3d point clouds and textured meshes from uav lidar and multi-view-stereo. arXiv preprint arXiv:2102.05346.","DOI":"10.1016\/j.ophoto.2021.100001"},{"key":"1554_CR34","doi-asserted-by":"crossref","unstructured":"Landrieu, L., & Simonovsky, M. (2018). Large-scale point cloud semantic segmentation with superpoint graphs. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 4558\u20134567).","DOI":"10.1109\/CVPR.2018.00479"},{"key":"1554_CR35","doi-asserted-by":"crossref","unstructured":"Lang, AH., Vora, S., Caesar, H., Zhou, L., Yang, J., & Beijbom, O. (2019). Pointpillars: Fast encoders for object detection from point clouds. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 12697\u201312705).","DOI":"10.1109\/CVPR.2019.01298"},{"key":"1554_CR36","doi-asserted-by":"crossref","unstructured":"Le, T., & Duan, Y. (2018). PointGrid: A deep network for 3D shape understanding. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 9204\u20139214).","DOI":"10.1109\/CVPR.2018.00959"},{"key":"1554_CR37","doi-asserted-by":"crossref","unstructured":"Lei, H., Akhtar, N., & Mian, A. (2020). Spherical kernel for efficient graph convolution on 3D point clouds. IEEE Transactions on Pattern Analysis and Machine Intelligence.","DOI":"10.1109\/TPAMI.2020.2983410"},{"key":"1554_CR38","doi-asserted-by":"crossref","unstructured":"Li, X., Li, C., Tong, Z., Lim, A., Yuan, J., Wu, Y., Tang, J., & Huang, R. (2020). Campus3D: A photogrammetry point cloud benchmark for hierarchical understanding of outdoor scene. ACM MM.","DOI":"10.1145\/3394171.3413661"},{"key":"1554_CR39","unstructured":"Li, Y., Bu, R., Sun, M., Wu, W., Di, X., & Chen, B. (2018). PointCNN: Convolution on X-transformed points. Advances in Neural Information Processing Systems."},{"key":"1554_CR40","doi-asserted-by":"crossref","unstructured":"Lin, TY., Goyal, P., Girshick, R., He, K., & Doll\u00e1r, P. (2017). Focal loss for dense object detection. In Proceedings of the IEEE\/CVF international conference on computer vision.","DOI":"10.1109\/ICCV.2017.324"},{"key":"1554_CR41","unstructured":"Liu, Z., Tang, H., Lin, Y., & Han, S. (2019). Point-voxel cnn for efficient 3D deep learning. Advances in Neural Information Processing Systems."},{"key":"1554_CR42","doi-asserted-by":"crossref","unstructured":"Lyu, Y., Huang, X., & Zhang, Z. (2020). Learning to segment 3D point clouds in 2D image space. In Proceedings of the IEEE\/CVF International Conference on Computer Vision.","DOI":"10.1109\/CVPR42600.2020.01227"},{"key":"1554_CR43","unstructured":"McCormac, J., Handa, A., Leutenegger, S., & Davison, AJ. (2016) SceneNet RGB-D: 5m photorealistic images of synthetic indoor trajectories with ground truth. arXiv preprint arXiv:1612.05079."},{"key":"1554_CR44","doi-asserted-by":"crossref","unstructured":"Meng, HY., Gao, L., Lai, YK., & Manocha, D. (2019). VV-Net: Voxel vae net with group convolutions for point cloud segmentation. In Proceedings of the IEEE\/CVF international conference on computer vision.","DOI":"10.1109\/ICCV.2019.00859"},{"key":"1554_CR45","doi-asserted-by":"crossref","unstructured":"Milioto, A., Vizzo, I., Behley, J., & Stachniss, C. (2019). Rangenet++: Fast and accurate LiDAR semantic segmentation. In 2019 IEEE\/RSJ international conference on intelligent robots and systems (IROS) (pp. 4213\u20134220).","DOI":"10.1109\/IROS40897.2019.8967762"},{"key":"1554_CR46","doi-asserted-by":"crossref","unstructured":"Mo, K., Zhu, S., Chang, AX., Yi, L., Tripathi, S., Guibas, LJ., & Su, H. (2019). PartNet: A large-scale benchmark for fine-grained and hierarchical part-level 3D object understanding. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 909\u2013918).","DOI":"10.1109\/CVPR.2019.00100"},{"key":"1554_CR47","doi-asserted-by":"crossref","unstructured":"Munoz, D., Bagnell, JA., Vandapel, N., & Hebert, M. (2009). Contextual classification with functional max-margin markov networks. In Proceedings of the IEEE\/CVF international conference on computer vision.","DOI":"10.1109\/CVPR.2009.5206590"},{"key":"1554_CR48","doi-asserted-by":"crossref","unstructured":"\u00d6zdemir, E., Toschi, I., & Remondino, F. (2019). a multi-purpose benchmark for photogrammetric urban 3D reconstruction in a controlled environment. Evaluation and Benchmarking Sensors, Systems and Geospatial Data in Photogrammetry and Remote Sensing, 42, 53\u201360.","DOI":"10.5194\/isprs-archives-XLII-1-W2-53-2019"},{"key":"1554_CR49","doi-asserted-by":"crossref","unstructured":"Pan, Y., Gao, B., Mei, J., Geng, S., Li, C., & Zhao, H. (2020). Semanticposs: A point cloud dataset with large quantity of dynamic instances. arXiv preprint arXiv:2002.09147.","DOI":"10.1109\/IV47402.2020.9304596"},{"key":"1554_CR50","doi-asserted-by":"crossref","unstructured":"Poursaeed, O., Jiang, T., Qiao, Q., Xu, N., & Kim, V. G. (2020). Self-supervised learning of point clouds via orientation estimation. arXiv preprint arXiv:2008.00305.","DOI":"10.1109\/3DV50981.2020.00112"},{"key":"1554_CR51","unstructured":"Qi, CR., Su, H., Mo, K., & Guibas, LJ. (2017a). PointNet: Deep learning on point sets for 3D classification and segmentation. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 652\u2013660)."},{"key":"1554_CR52","unstructured":"Qi, CR., Yi, L., Su, H., & Guibas, LJ. (2017b). PointNet++: Deep hierarchical feature learning on point sets in a metric space. Advances in Neural Information Processing Systems."},{"key":"1554_CR53","doi-asserted-by":"crossref","unstructured":"Qin, N., Tan, W., Ma, L., Zhang, D., & Li, J. (2021). Opengf: An ultra-large-scale ground filtering dataset built upon open als point clouds around the world. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 1082\u20131091).","DOI":"10.1109\/CVPRW53098.2021.00119"},{"key":"1554_CR54","doi-asserted-by":"crossref","unstructured":"Rao, D., Le, Q. V., Phoka, T., Quigley, M., Sudsang, A., & Ng, A. Y. (2010). Grasping novel objects with depth segmentation. In 2010 IEEE\/RSJ international conference on intelligent robots and systems (pp. 2578\u20132585).","DOI":"10.1109\/IROS.2010.5650493"},{"key":"1554_CR55","doi-asserted-by":"crossref","unstructured":"Ros, G., Sellart, L., Materzynska, J., Vazquez, D., & Lopez, A. M. (2016). The SYNTHIA dataset: A large collection of synthetic images for semantic segmentation of urban scenes. In Proceedings of the IEEE\/CVF international conference on computer vision pp. 3234\u20133243).","DOI":"10.1109\/CVPR.2016.352"},{"key":"1554_CR56","unstructured":"Rosu, R. A., Sch\u00fctt, P., Quenzel, J., & Behnke, S. (2019). LatticeNet: Fast point cloud segmentation using permutohedral lattices. arXiv preprint arXiv:1912.05905."},{"issue":"1","key":"1554_CR57","doi-asserted-by":"publisher","first-page":"293","DOI":"10.5194\/isprsannals-I-3-293-2012","volume":"1","author":"F Rottensteiner","year":"2012","unstructured":"Rottensteiner, F., Sohn, G., Jung, J., Gerke, M., Baillard, C., Benitez, S., & Breitkopf, U. (2012). The ISPRS benchmark on urban object classification and 3D building reconstruction. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences I-3 (2012), Nr 1, 1(1), 293\u2013298.","journal-title":"ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences I-3 (2012), Nr 1"},{"issue":"6","key":"1554_CR58","doi-asserted-by":"publisher","first-page":"545","DOI":"10.1177\/0278364918767506","volume":"37","author":"X Roynard","year":"2018","unstructured":"Roynard, X., Deschaud, J. E., & Goulette, F. (2018). Paris-Lille-3D: A large and high-quality ground-truth urban point cloud dataset for automatic segmentation and classification. The International Journal of Robotics Research, 37(6), 545\u2013557.","journal-title":"The International Journal of Robotics Research"},{"key":"1554_CR59","unstructured":"Sauder, J., & Sievers, B. (2019). Self-supervised deep learning on point clouds by reconstructing space. Advances in Neural Information Processing Systems, 12962\u201312972."},{"key":"1554_CR60","unstructured":"Serna, A., Marcotegui, B., Goulette, F., & Deschaud, JE. (2014). Paris-rue-madame database: A 3D mobile laser scanner dataset for benchmarking urban detection, segmentation and classification methods. In 4th international conference on pattern recognition, applications and methods ICPRAM 2014."},{"key":"1554_CR61","doi-asserted-by":"crossref","unstructured":"Silberman, N., Hoiem, D., Kohli, P., & Fergus, R. (2012). Indoor segmentation and support inference from RGBD images. In European conference on computer vision (pp. 746\u2013760).","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"1554_CR62","doi-asserted-by":"crossref","unstructured":"Song, S., Lichtenberg, S. P., & Xiao, J. (2015). Sun RGB-D: A RGB-D scene understanding benchmark suite. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 567\u2013576).","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"1554_CR63","doi-asserted-by":"crossref","unstructured":"Sun, P., Kretzschmar, H., Dotiwalla, X., Chouard, A., Patnaik, V., Tsui, P., Guo, J., Zhou, Y., Chai, Y. Caine B, et\u00a0al. (2020) Scalability in perception for autonomous driving: Waymo open dataset. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 2446\u20132454).","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"1554_CR64","doi-asserted-by":"crossref","unstructured":"Tan, W., Qin, N., Ma, L., Li, Y., Du, J., Cai, G., Yang, K., & Li, J. (2020). Toronto-3D: A large-scale mobile LiDAR dataset for semantic segmentation of urban roadways. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops (pp. 202\u2013203).","DOI":"10.1109\/CVPRW50498.2020.00109"},{"key":"1554_CR65","doi-asserted-by":"crossref","unstructured":"Tang, H., Liu, Z., Zhao, S., Lin, Y., Lin, J., Wang, H., & Han, S. (2020). Searching efficient 3D architectures with sparse point-voxel convolution. In European conference on computer vision (pp. 685\u2013702).","DOI":"10.1007\/978-3-030-58604-1_41"},{"key":"1554_CR66","doi-asserted-by":"crossref","unstructured":"Tatarchenko, M., Park, J., Koltun, V., & Zhou, Q. Y. (2018). Tangent convolutions for dense prediction in 3D. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 3887\u20133896).","DOI":"10.1109\/CVPR.2018.00409"},{"key":"1554_CR67","doi-asserted-by":"crossref","unstructured":"Tchapmi, L., Choy, C., Armeni, I., Gwak, J., & Savarese, S. (2017). Segcloud: Semantic segmentation of 3D point clouds. In 2017 international conference on 3D vision (3DV) (pp. 537\u2013547).","DOI":"10.1109\/3DV.2017.00067"},{"key":"1554_CR68","doi-asserted-by":"crossref","unstructured":"Thomas H, Qi CR, Deschaud JE, Marcotegui B, Goulette F, & Guibas LJ (2019) KPConv: Flexible and deformable convolution for point clouds. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 6411\u20136420).","DOI":"10.1109\/ICCV.2019.00651"},{"key":"1554_CR69","doi-asserted-by":"crossref","unstructured":"Tong, G., Li, Y., Chen, D., Sun, Q., Cao, W., & Xiang, G. (2020). CSPC-dataset: New LiDAR point cloud dataset and benchmark for large-scale scene semantic segmentation. IEEE Access.","DOI":"10.1109\/ACCESS.2020.2992612"},{"key":"1554_CR70","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. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 1588\u20131597).","DOI":"10.1109\/ICCV.2019.00167"},{"key":"1554_CR71","doi-asserted-by":"crossref","unstructured":"Valada, A., Vertens, J., Dhall, A., & Burgard, W. (2017). Adapnet: Adaptive semantic segmentation in adverse environmental conditions. In 2017 IEEE international conference on robotics and automation (ICRA) (pp. 4644\u20134651).","DOI":"10.1109\/ICRA.2017.7989540"},{"key":"1554_CR72","doi-asserted-by":"crossref","unstructured":"Vallet, B., Br\u00e9dif, M., Serna, A., Marcotegui, B., & Paparoditis, N. (2015). TerraMobilita\/iQmulus urban point cloud analysis benchmark. Computers & Graphics","DOI":"10.1016\/j.cag.2015.03.004"},{"key":"1554_CR73","doi-asserted-by":"crossref","unstructured":"Varney, N., Asari, V. K., & Graehling, Q. (2020). DALES: A large-scale aerial LiDAR data set for semantic segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops (pp 186\u2013187).","DOI":"10.1109\/CVPRW50498.2020.00101"},{"key":"1554_CR74","unstructured":"Wang, H., Liu, Q., Yue, X., Lasenby, J., & Kusner, M. J. (2020). Pre-training by completing point clouds. arXiv preprint arXiv:2010.01089."},{"key":"1554_CR75","doi-asserted-by":"crossref","unstructured":"Wang, L., Huang, Y., Hou, Y., Zhang, S., & Shan, J. (2019a). Graph attention convolution for point cloud semantic segmentation. In Proceedings of the IEEE\/CVF international conference on computer vision.","DOI":"10.1109\/CVPR.2019.01054"},{"issue":"5","key":"1554_CR76","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. ACM Transactions on Graphics (TOG), 38(5), 1\u201312.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"1554_CR77","doi-asserted-by":"crossref","unstructured":"Wei, J., Lin, G., Yap, K. H., Hung, T. Y., & Xie, L. (2020). Multi-path region mining for weakly supervised 3D semantic segmentation on point clouds. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 4384\u20134393).","DOI":"10.1109\/CVPR42600.2020.00444"},{"key":"1554_CR78","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1016\/j.geomorph.2012.08.021","volume":"179","author":"MJ Westoby","year":"2012","unstructured":"Westoby, M. J., Brasington, J., Glasser, N. F., Hambrey, M. J., & Reynolds, J. M. (2012). \u2018structure-from-motion\u2019 photogrammetry: A low-cost, effective tool for geoscience applications. Geomorphology, 179, 300\u2013314.","journal-title":"Geomorphology"},{"key":"1554_CR79","doi-asserted-by":"crossref","unstructured":"Wu, B., Wan, A., Yue, X., & Keutzer, K. (2018a). SqueezeSeg: Convolutional neural nets with recurrent CRF for real-time road-object segmentation from 3D LiDAR point cloud. In 2018 IEEE international conference on robotics and automation (ICRA) (pp. 1887\u20131893).","DOI":"10.1109\/ICRA.2018.8462926"},{"key":"1554_CR80","doi-asserted-by":"crossref","unstructured":"Wu, B., Zhou, X., Zhao, S., Yue, X., & Keutzer, K. (2019). Squeezesegv2: Improved model structure and unsupervised domain adaptation for road-object segmentation from a LiDAR point cloud. In 2019 international conference on robotics and automation (ICRA) (pp. 4376\u20134382).","DOI":"10.1109\/ICRA.2019.8793495"},{"key":"1554_CR81","doi-asserted-by":"crossref","unstructured":"Wu, W., Qi, Z., & Fuxin, L. (2018b). PointConv: Deep convolutional networks on 3D point clouds. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 9621\u20139630).","DOI":"10.1109\/CVPR.2019.00985"},{"key":"1554_CR82","unstructured":"Wu, Z., Song, S., Khosla, A., Yu, F., Zhang, L., Tang, X., & Xiao, J. (2015). 3D ShapeNets: A deep representation for volumetric shapes. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 1912\u20131920)."},{"key":"1554_CR83","doi-asserted-by":"crossref","unstructured":"Xie, S., Gu, J., Guo, D., Qi, C. R., Guibas, L., & Litany, O. (2020). Pointcontrast: Unsupervised pre-training for 3D point cloud understanding. In European conference on computer vision (pp. 574\u2013591).","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"1554_CR84","doi-asserted-by":"crossref","unstructured":"Xu, C., Wu, B., Wang, Z., Zhan, W., Vajda, P., Keutzer, K., & Tomizuka, M. (2020). SqueezeSegV3: Spatially-adaptive convolution for efficient point-cloud segmentation. In Proceedings of the European conference on computer vision (ECCV) (pp. 1\u201319).","DOI":"10.1007\/978-3-030-58604-1_1"},{"key":"1554_CR85","doi-asserted-by":"crossref","unstructured":"Xu, X., & Lee, G. H. (2020). Weakly supervised semantic point cloud segmentation: Towards 10x fewer labels. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 13706\u201313715)","DOI":"10.1109\/CVPR42600.2020.01372"},{"key":"1554_CR86","doi-asserted-by":"crossref","unstructured":"Yan, X., Zheng, C., Li, Z., Wang, S., & Cui, S. (2020). PointASNL: Robust point clouds processing using nonlocal neural networks with adaptive sampling. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 5589\u20135598).","DOI":"10.1109\/CVPR42600.2020.00563"},{"key":"1554_CR87","unstructured":"Yang, B., Wang, J., Clark, R., Hu, Q., Wang, S., Markham, A., & Trigoni, N. (2019). Learning object bounding boxes for 3D instance segmentation on point clouds. Advances in Neural Information Processing Systems."},{"key":"1554_CR88","doi-asserted-by":"crossref","unstructured":"Ye, X., Li, J., Huang, H., Du, L., & Zhang, X. (2018). 3D recurrent neural networks with context fusion for point cloud semantic segmentation. In Proceedings of the European conference on computer vision (ECCV)","DOI":"10.1007\/978-3-030-01234-2_25"},{"key":"1554_CR89","doi-asserted-by":"crossref","unstructured":"Ye, Z., Xu, Y., Huang, R., Tong, X., Li, X., Liu, X., Luan, K., Hoegner, L., & Stilla, U. (2020). LASDU: A large-scale aerial LiDAR dataset for semantic labeling in dense urban areas. ISPRS International Journal of Geo-Information, 9(7), 450.","DOI":"10.3390\/ijgi9070450"},{"issue":"6","key":"1554_CR90","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2980179.2980238","volume":"35","author":"L Yi","year":"2016","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. ACM Transactions on Graphics (TOG), 35(6), 1\u201312.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"1554_CR91","doi-asserted-by":"crossref","unstructured":"Yuan, W., Khot, T., Held, D., Mertz, C., & Hebert, M. (2018). PCN: Point completion network. In 2018 International Conference on 3D Vision (3DV) (pp. 728\u2013737)","DOI":"10.1109\/3DV.2018.00088"},{"key":"1554_CR92","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhou, Z., David, P., Yue, X., Xi, Z., Gong, B., & Foroosh, H. (2020). PolarNet: An improved grid representation for online LiDAR point clouds semantic segmentation. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 9601\u20139610).","DOI":"10.1109\/CVPR42600.2020.00962"},{"key":"1554_CR93","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/j.jag.2018.04.002","volume":"70","author":"Z Zhang","year":"2018","unstructured":"Zhang, Z., Gerke, M., Vosselman, G., & Yang, M. Y. (2018). A patch-based method for the evaluation of dense image matching quality. International Journal of Applied Earth Observation and Geoinformation, 70, 25\u201334.","journal-title":"International Journal of Applied Earth Observation and Geoinformation"},{"key":"1554_CR94","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Hua, B. S., & Yeung, S. K. (2019) ShellNet: Efficient point cloud convolutional neural networks using concentric shells statistics. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 1607\u20131616).","DOI":"10.1109\/ICCV.2019.00169"},{"key":"1554_CR95","unstructured":"Zhang, Z., Girdhar, R., Joulin, A., & Misra, I. (2021). Self-supervised pretraining of 3D features on any point-cloud. arXiv preprint arXiv:2101.02691."},{"key":"1554_CR96","unstructured":"Zhao, H., Jiang, L., Jia, J., Torr, P., & Koltun, V. (2020). Point transformer. arXiv preprint arXiv:2012.09164."},{"key":"1554_CR97","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., & Torralba, A. (2017). Scene parsing through ADE20K dataset. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 633\u2013641).","DOI":"10.1109\/CVPR.2017.544"},{"key":"1554_CR98","doi-asserted-by":"crossref","unstructured":"Zhou, Y., & Tuzel, O. (2018). VoxelNet: End-to-end learning for point cloud based 3D object detection. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 4490\u20134499).","DOI":"10.1109\/CVPR.2018.00472"},{"key":"1554_CR99","doi-asserted-by":"crossref","unstructured":"Zhu, X., Zhou, H., Wang, T., Hong, F., Ma, Y., Li, W., Li, H., & Lin, D. (2021). Cylindrical and asymmetrical 3D convolution networks for LiDAR segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR46437.2021.00981"},{"key":"1554_CR100","unstructured":"Zolanvari, S., Ruano, S., Rana, A., Cummins, A., da\u00a0Silva, R. E., Rahbar, M., & Smolic, A. (2019). DublinCity: Annotated LiDAR point cloud and its applications. In British machine vision conference."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01554-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-021-01554-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01554-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,16]],"date-time":"2022-02-16T10:21:53Z","timestamp":1645006913000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-021-01554-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,4]]},"references-count":100,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,2]]}},"alternative-id":["1554"],"URL":"https:\/\/doi.org\/10.1007\/s11263-021-01554-9","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,4]]},"assertion":[{"value":"19 February 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 November 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 January 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}