{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T17:52:12Z","timestamp":1775325132167,"version":"3.50.1"},"publisher-location":"Cham","reference-count":85,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198359","type":"print"},{"value":"9783031198366","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19836-6_36","type":"book-chapter","created":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T09:04:58Z","timestamp":1666343098000},"page":"638-656","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":43,"title":["Image2Point: 3D Point-Cloud Understanding with\u00a02D Image Pretrained Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4941-6985","authenticated-orcid":false,"given":"Chenfeng","family":"Xu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7016-9333","authenticated-orcid":false,"given":"Shijia","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Tomer","family":"Galanti","sequence":"additional","affiliation":[]},{"given":"Bichen","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Xiangyu","family":"Yue","sequence":"additional","affiliation":[]},{"given":"Bohan","family":"Zhai","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Zhan","sequence":"additional","affiliation":[]},{"given":"Peter","family":"Vajda","sequence":"additional","affiliation":[]},{"given":"Kurt","family":"Keutzer","sequence":"additional","affiliation":[]},{"given":"Masayoshi","family":"Tomizuka","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,22]]},"reference":[{"key":"36_CR1","unstructured":"Armeni, I., Sax, S., Zamir, A.R., Savarese, S.: Joint 2d\u20133d-semantic data for indoor scene understanding. arXiv preprint arXiv:1702.01105 (2017)"},{"key":"36_CR2","unstructured":"Bachman, P., Hjelm, R.D., Buchwalter, W.: Learning representations by maximizing mutual information across views. arXiv preprint arXiv:1906.00910 (2019)"},{"key":"36_CR3","doi-asserted-by":"crossref","unstructured":"Behley, J., Garbade, M., Milioto, A., Quenzel, J., Behnke, S., Stachniss, C., Gall, J.: SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00939"},{"key":"36_CR4","doi-asserted-by":"crossref","unstructured":"Ben-david, S., Blitzer, J., Crammer, K., Pereira, F.: Analysis of representations for domain adaptation. In: Advances in Neural Information Processing Systems 19, pp. 137\u2013144. Curran Associates, Inc. (2006)","DOI":"10.7551\/mitpress\/7503.003.0022"},{"key":"36_CR5","doi-asserted-by":"crossref","unstructured":"Boulch, A., Le Saux, B., Audebert, N.: Unstructured point cloud semantic labeling using deep segmentation networks. 3DOR 2, 7 (2017)","DOI":"10.1016\/j.cag.2017.11.010"},{"key":"36_CR6","doi-asserted-by":"crossref","unstructured":"Caesar, H.,et al.: A multimodal dataset for autonomous driving. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"36_CR7","doi-asserted-by":"crossref","unstructured":"Caron, M., Bojanowski, P., Mairal, J., Joulin, A.: Unsupervised pre-training of image features on non-curated data. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2959\u20132968 (2019)","DOI":"10.1109\/ICCV.2019.00305"},{"key":"36_CR8","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. arXiv preprint arXiv:2006.09882 (2020)"},{"key":"36_CR9","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"36_CR10","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International conference on machine learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"36_CR11","unstructured":"Chen, T., Kornblith, S., Swersky, K., Norouzi, M., Hinton, G.: Big self-supervised models are strong semi-supervised learners. arXiv preprint arXiv:2006.10029 (2020)"},{"key":"36_CR12","unstructured":"Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)"},{"key":"36_CR13","doi-asserted-by":"crossref","unstructured":"Choy, C., Gwak, J., Savarese, S.: 4d spatio-temporal convnets: Minkowski convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3075\u20133084 (2019)","DOI":"10.1109\/CVPR.2019.00319"},{"key":"36_CR14","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: Proceedings of the Computer Vision and Pattern Recognition (CVPR), IEEE (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"36_CR15","doi-asserted-by":"crossref","unstructured":"Dai, A., Nie\u00dfner, M.: 3dmv: Joint 3d-multi-view prediction for 3d semantic scene segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 452\u2013468 (2018)","DOI":"10.1007\/978-3-030-01249-6_28"},{"key":"36_CR16","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: 2009 IEEE conference on computer vision and pattern recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"36_CR17","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"36_CR18","doi-asserted-by":"crossref","unstructured":"Feng, D., Zhou, Y., Xu, C., Tomizuka, M., Zhan, W.: A simple and efficient multi-task network for 3d object detection and road understanding. arXiv preprint arXiv:2103.04056 (2021)","DOI":"10.1109\/IROS51168.2021.9635858"},{"key":"36_CR19","unstructured":"Galanti, T., Gy\u00f6rgy, A., Hutter, M.: On the role of neural collapse in transfer learning. In: International Conference on Learning Representations (2022), https:\/\/openreview.net\/forum?id=SwIp410B6aQ"},{"key":"36_CR20","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for Autonomous Driving? The KITTI Vision Benchmark Suite. In: Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3354\u20133361 (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"36_CR21","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"36_CR22","unstructured":"Goyal, A., Law, H., Liu, B., Newell, A., Deng, J.: Revisiting point cloud shape classification with a simple and effective baseline. arXiv preprint arXiv:2106.05304 (2021)"},{"key":"36_CR23","unstructured":"Goyal, P., et al.: Self-supervised pretraining of visual features in the wild. arXiv preprint arXiv:2103.01988 (2021)"},{"key":"36_CR24","doi-asserted-by":"crossref","unstructured":"Gur, S., Wolf, L.: Single image depth estimation trained via depth from defocus cues. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7683\u20137692 (2019)","DOI":"10.1109\/CVPR.2019.00787"},{"key":"36_CR25","unstructured":"Han, X.Y., Papyan, V., Donoho, D.L.: Neural collapse under mse loss: Proximity to and dynamics on the central path (2021)"},{"key":"36_CR26","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"36_CR27","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"36_CR28","unstructured":"Henaff, O.: Data-efficient image recognition with contrastive predictive coding. In: International Conference on Machine Learning, pp. 4182\u20134192. PMLR (2020)"},{"key":"36_CR29","unstructured":"Hjelm, R.D., et al.: Learning deep representations by mutual information estimation and maximization. arXiv preprint arXiv:1808.06670 (2018)"},{"key":"36_CR30","doi-asserted-by":"crossref","unstructured":"Hou, J., Graham, B., Nie\u00dfner, M., Xie, S.: Exploring data-efficient 3d scene understanding with contrastive scene contexts. arXiv preprint arXiv:2012.09165 (2020)","DOI":"10.1109\/CVPR46437.2021.01533"},{"key":"36_CR31","doi-asserted-by":"crossref","unstructured":"Hou, J., Graham, B., Nie\u00dfner, M., Xie, S.: Exploring data-efficient 3D scene understanding with contrastive scene contexts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15587\u201315597 (2021)","DOI":"10.1109\/CVPR46437.2021.01533"},{"key":"36_CR32","doi-asserted-by":"crossref","unstructured":"Hua, B.S., Tran, M.K., Yeung, S.K.: Pointwise convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 984\u2013993 (2018)","DOI":"10.1109\/CVPR.2018.00109"},{"key":"36_CR33","doi-asserted-by":"crossref","unstructured":"Jing, L., Tian, Y.: Self-supervised visual feature learning with deep neural networks: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence (2020)","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"36_CR34","doi-asserted-by":"crossref","unstructured":"Kataoka, H., et al.: Pre-training without natural images. In: Proceedings of the Asian Conference on Computer Vision (2020)","DOI":"10.1007\/978-3-030-69544-6_35"},{"key":"36_CR35","doi-asserted-by":"crossref","unstructured":"Klokov, R., Lempitsky, V.: Escape from cells: Deep kd-networks for the recognition of 3d point cloud models. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 863\u2013872 (2017)","DOI":"10.1109\/ICCV.2017.99"},{"key":"36_CR36","doi-asserted-by":"crossref","unstructured":"Komarichev, A., Zhong, Z., Hua, J.: A-cnn: Annularly convolutional neural networks on point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7421\u20137430 (2019)","DOI":"10.1109\/CVPR.2019.00760"},{"key":"36_CR37","doi-asserted-by":"crossref","unstructured":"Lang, A.H., Vora, S., Caesar, H., Zhou, L., Yang, J., Beijbom, O.: 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 (2019)","DOI":"10.1109\/CVPR.2019.01298"},{"key":"36_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1007\/978-3-319-64689-3_8","volume-title":"Computer Analysis of Images and Patterns","author":"FJ Lawin","year":"2017","unstructured":"Lawin, F.J., Danelljan, M., Tosteberg, P., Bhat, G., Khan, F.S., Felsberg, M.: Deep projective 3D semantic segmentation. In: Felsberg, M., Heyden, A., Kr\u00fcger, N. (eds.) CAIP 2017. LNCS, vol. 10424, pp. 95\u2013107. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-64689-3_8"},{"key":"36_CR39","doi-asserted-by":"crossref","unstructured":"Lee, D., et al.: Regularization strategy for point cloud via rigidly mixed sample. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15900\u201315909 (2021)","DOI":"10.1109\/CVPR46437.2021.01564"},{"key":"36_CR40","doi-asserted-by":"crossref","unstructured":"Li, J., Chen, B.M., Lee, G.H.: So-net: Self-organizing network for point cloud analysis. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 9397\u20139406 (2018)","DOI":"10.1109\/CVPR.2018.00979"},{"key":"36_CR41","unstructured":"Li, Y., Bu, R., Sun, M., Wu, W., Di, X., Chen, B.: Pointcnn: Convolution on $$\\chi $$-transformed points. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems. pp. 828\u2013838 (2018)"},{"key":"36_CR42","doi-asserted-by":"crossref","unstructured":"Liu, Y., Fan, B., Meng, G., Lu, J., Xiang, S., Pan, C.: Densepoint: Learning densely contextual representation for efficient point cloud processing. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5239\u20135248 (2019)","DOI":"10.1109\/ICCV.2019.00534"},{"key":"36_CR43","unstructured":"Liu, Y.C., et al.: Learning from 2d: Pixel-to-point knowledge transfer for 3d pretraining. arXiv preprint arXiv:2104.04687 (2021)"},{"key":"36_CR44","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"326","DOI":"10.1007\/978-3-030-58592-1_20","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Liu","year":"2020","unstructured":"Liu, Z., Hu, H., Cao, Y., Zhang, Z., Tong, X.: A closer look at local aggregation operators in point cloud analysis. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12368, pp. 326\u2013342. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58592-1_20"},{"key":"36_CR45","doi-asserted-by":"crossref","unstructured":"Liu, Z., Qi, X., Fu, C.W.: 3d-to-2d distillation for indoor scene parsing. arXiv preprint arXiv:2104.02243 (2021)","DOI":"10.1109\/CVPR46437.2021.00444"},{"key":"36_CR46","doi-asserted-by":"crossref","unstructured":"Lu, K., Grover, A., Abbeel, P., Mordatch, I.: Pretrained transformers as universal computation engines. arXiv preprint arXiv:2103.05247 (2021)","DOI":"10.1609\/aaai.v36i7.20729"},{"key":"36_CR47","unstructured":"Lu, Y., et al.: Open-vocabulary 3d detection via image-level class and debiased cross-modal contrastive learning. arXiv preprint arXiv:2207.01987 (2022)"},{"key":"36_CR48","doi-asserted-by":"crossref","unstructured":"Mansour, Y.: Learning and domain adaptation. In: Algorithmic Learning Theory, 20th International Conference, ALT, pp. 4\u20136 (2009)","DOI":"10.1007\/978-3-642-04414-4_4"},{"key":"36_CR49","unstructured":"Mansour, Y., Mohri, M., Rostamizadeh, A.: Domain adaptation: Learning bounds and algorithms. In: COLT - The 22nd Conference on Learning Theory (2009)"},{"key":"36_CR50","doi-asserted-by":"crossref","unstructured":"Milioto, A., Vizzo, I., Behley, J., Stachniss, C.: Rangenet++: Fast and accurate lidar semantic segmentation. In: 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4213\u20134220. IEEE (2019)","DOI":"10.1109\/IROS40897.2019.8967762"},{"issue":"40","key":"36_CR51","doi-asserted-by":"publisher","first-page":"24652","DOI":"10.1073\/pnas.2015509117","volume":"117","author":"V Papyan","year":"2020","unstructured":"Papyan, V., Han, X.Y., Donoho, D.L.: Prevalence of neural collapse during the terminal phase of deep learning training. Proc. Natl. Acad. Sci. 117(40), 24652\u201324663 (2020)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"36_CR52","doi-asserted-by":"crossref","unstructured":"Park, J., Xu, C., Zhou, Y., Tomizuka, M., Zhan, W.: Detmatch: Two teachers are better than one for joint 2d and 3d semi-supervised object detection. arXiv preprint arXiv:2203.09510 (2022)","DOI":"10.1007\/978-3-031-20080-9_22"},{"issue":"1","key":"36_CR53","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/2300000035","volume":"4","author":"F Pomerleau","year":"2015","unstructured":"Pomerleau, F., Colas, F., Siegwart, R.: A review of point cloud registration algorithms for mobile robotics. Foundations Trends Robot. 4(1), 1\u2013104 (2015)","journal-title":"Foundations Trends Robot."},{"key":"36_CR54","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: Deep learning on point sets for 3d classification and segmentation (2016). arxiv:1612.00593"},{"key":"36_CR55","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: Deep hierarchical feature learning on point sets in a metric space. arXiv preprint arXiv:1706.02413 (2017)"},{"key":"36_CR56","doi-asserted-by":"crossref","unstructured":"Qiu, S., Anwar, S., Barnes, N.: Dense-resolution network for point cloud classification and segmentation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3813\u20133822 (2021)","DOI":"10.1109\/WACV48630.2021.00386"},{"key":"36_CR57","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"36_CR58","unstructured":"Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., Koltun, V.: Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) (2020)"},{"key":"36_CR59","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"issue":"6","key":"36_CR60","doi-asserted-by":"publisher","first-page":"1522","DOI":"10.1109\/TMI.2018.2832217","volume":"37","author":"H Shan","year":"2018","unstructured":"Shan, H., Zhang, Y., Yang, Q., Kruger, U., Kalra, M.K., Sun, L., Cong, W., Wang, G.: 3-D convolutional encoder-decoder network for low-dose ct via transfer learning from a 2-d trained network. IEEE Trans. Med. Imaging 37(6), 1522\u20131534 (2018)","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"12","key":"36_CR61","doi-asserted-by":"publisher","first-page":"2339","DOI":"10.1109\/LSP.2015.2480802","volume":"22","author":"B Shi","year":"2015","unstructured":"Shi, B., Bai, S., Zhou, Z., Bai, X.: Deeppano: deep panoramic representation for 3-D shape recognition. IEEE Signal Process. Lett. 22(12), 2339\u20132343 (2015). https:\/\/doi.org\/10.1109\/LSP.2015.2480802","journal-title":"IEEE Signal Process. Lett."},{"key":"36_CR62","unstructured":"Sketchup: 3d modeling online free|3d warehouse models. https:\/\/3dwarehouse.sketchup.com (2021)"},{"key":"36_CR63","doi-asserted-by":"crossref","unstructured":"Su, H., Maji, S., Kalogerakis, E., Learned-Miller, E.: Multi-view convolutional neural networks for 3d shape recognition. In: Proceedings of the IEEE international conference on computer vision, pp. 945\u2013953 (2015)","DOI":"10.1109\/ICCV.2015.114"},{"key":"36_CR64","doi-asserted-by":"crossref","unstructured":"Tang, H., et al.: Searching efficient 3d architectures with sparse point-voxel convolution. In: European Conference on Computer Vision (2020)","DOI":"10.1007\/978-3-030-58604-1_41"},{"key":"36_CR65","doi-asserted-by":"crossref","unstructured":"Wang, H., Liu, Q., Yue, X., Lasenby, J., Kusner, M.J.: Unsupervised point cloud pre-training via view-point occlusion, completion. arXiv preprint arXiv:2010.01089 (2020)","DOI":"10.1109\/ICCV48922.2021.00964"},{"issue":"4","key":"36_CR66","first-page":"1","volume":"36","author":"PS Wang","year":"2017","unstructured":"Wang, P.S., Liu, Y., Guo, Y.X., Sun, C.Y., Tong, X.: O-cnn: Octree-based convolutional neural networks for 3d shape analysis. ACM Trans. Graph. (TOG) 36(4), 1\u201311 (2017)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"36_CR67","doi-asserted-by":"crossref","unstructured":"Wang, Y., Chao, W.L., Garg, D., Hariharan, B., Campbell, M., Weinberger, K.: Pseudo-lidar from visual depth estimation: Bridging the gap in 3D object detection for autonomous driving. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00864"},{"issue":"5","key":"36_CR68","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.: Dynamic graph cnn for learning on point clouds. Acm Trans. Graph. (tog) 38(5), 1\u201312 (2019)","journal-title":"Acm Trans. Graph. (tog)"},{"key":"36_CR69","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhan, W., Tomizuka, M.: Fusing bird\u2019s eye view lidar point cloud and front view camera image for 3D object detection. In: 2018 IEEE Intelligent Vehicles Symposium (IV), pp. 1\u20136. IEEE (2018)","DOI":"10.1109\/IVS.2018.8500387"},{"key":"36_CR70","doi-asserted-by":"crossref","unstructured":"Wu, B., Wan, A., Yue, X., Keutzer, K.: Squeezeseg: Convolutional neural nets with recurrent crf for real-time road-object segmentation from 3D lidar point cloud. In: ICRA (2018)","DOI":"10.1109\/ICRA.2018.8462926"},{"key":"36_CR71","doi-asserted-by":"crossref","unstructured":"Wu, B., Zhou, X., Zhao, S., Yue, X., Keutzer, K.: Squeezesegv 2: Improved model structure and unsupervised domain adaptation for road-object segmentation from a lidar point cloud. In: ICRA (2019)","DOI":"10.1109\/ICRA.2019.8793495"},{"key":"36_CR72","unstructured":"Wu, Z., Song, S., Khosla, A., Yu, F., Zhang, L., Tang, X., Xiao, J.: 3d shapenets: A deep representation for volumetric shapes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)"},{"key":"36_CR73","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1007\/978-3-030-58580-8_34","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Xie","year":"2020","unstructured":"Xie, S., Gu, J., Guo, D., Qi, C.R., Guibas, L., Litany, O.: PointContrast: unsupervised pre-training for 3D point cloud understanding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 574\u2013591. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_34"},{"key":"36_CR74","doi-asserted-by":"crossref","unstructured":"Xu, C., et al.: Pretram: Self-supervised pre-training via connecting trajectory and map. arXiv preprint arXiv:2204.10435 (2022)","DOI":"10.1007\/978-3-031-19842-7_3"},{"key":"36_CR75","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-030-58604-1_1","volume-title":"Computer Vision \u2013 ECCV 2020","author":"C Xu","year":"2020","unstructured":"Xu, C.: SqueezeSegV3: spatially-adaptive convolution for efficient point-cloud segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12373, pp. 1\u201319. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58604-1_1"},{"key":"36_CR76","doi-asserted-by":"crossref","unstructured":"Xu, C., et al.: You only group once: Efficient point-cloud processing with token representation and relation inference module. arXiv preprint arXiv:2103.09975 (2021)","DOI":"10.1109\/IROS51168.2021.9636858"},{"key":"36_CR77","doi-asserted-by":"crossref","unstructured":"Xu, X., Lee, G.H.: 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 (2020)","DOI":"10.1109\/CVPR42600.2020.01372"},{"issue":"10","key":"36_CR78","doi-asserted-by":"publisher","first-page":"3337","DOI":"10.3390\/s18103337","volume":"18","author":"Y Yan","year":"2018","unstructured":"Yan, Y., Mao, Y., Li, B.: Second: sparsely embedded convolutional detection. Sensors 18(10), 3337 (2018)","journal-title":"Sensors"},{"key":"36_CR79","doi-asserted-by":"crossref","unstructured":"Yang, B., Luo, W., Urtasun, R.: Pixor: Real-time 3D object detection from point clouds. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 7652\u20137660 (2018)","DOI":"10.1109\/CVPR.2018.00798"},{"key":"36_CR80","doi-asserted-by":"crossref","unstructured":"Yin, W., Liu, Y., Shen, C.: Virtual normal: Enforcing geometric constraints for accurate and robust depth prediction. IEEE Transactions on Pattern Analysis and Machine Intelligence (2021)","DOI":"10.1109\/TPAMI.2021.3097396"},{"key":"36_CR81","doi-asserted-by":"crossref","unstructured":"Yue, X., Wu, B., Seshia, S.A., Keutzer, K., Sangiovanni-Vincentelli, A.L.: A lidar point cloud generator: from a virtual world to autonomous driving. In: Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval, pp. 458\u2013464 (2018)","DOI":"10.1145\/3206025.3206080"},{"key":"36_CR82","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Pointcutmix: Regularization strategy for point cloud classification. arXiv preprint arXiv:2101.01461 (2021)","DOI":"10.1016\/j.neucom.2022.07.049"},{"key":"36_CR83","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Girdhar, R., Joulin, A., Misra, I.: Self-supervised pretraining of 3d features on any point-cloud. arXiv preprint arXiv:2101.02691 (2021)","DOI":"10.1109\/ICCV48922.2021.01009"},{"key":"36_CR84","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jiang, L., Jia, J., Torr, P.H., Koltun, V.: Point transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16259\u201316268 (2021)","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"36_CR85","unstructured":"Zhou, H., et al.: Cylinder3d: An effective 3d framework for driving-scene lidar semantic segmentation. arXiv preprint arXiv:2008.01550 (2020)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19836-6_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T08:44:53Z","timestamp":1728204293000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19836-6_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198359","9783031198366"],"references-count":85,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19836-6_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"22 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}