{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T19:19:22Z","timestamp":1762111162408,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":88,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031729911"},{"type":"electronic","value":"9783031729928"}],"license":[{"start":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:00:00Z","timestamp":1730246400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:00:00Z","timestamp":1730246400000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72992-8_17","type":"book-chapter","created":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T08:29:02Z","timestamp":1730190542000},"page":"291-310","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Text2LiDAR: Text-Guided LiDAR Point Cloud Generation via\u00a0Equirectangular Transformer"],"prefix":"10.1007","author":[{"given":"Yang","family":"Wu","sequence":"first","affiliation":[]},{"given":"Kaihua","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Jianjun","family":"Qian","sequence":"additional","affiliation":[]},{"given":"Jin","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Jian","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,30]]},"reference":[{"key":"17_CR1","unstructured":"Achlioptas, P., Diamanti, O., Mitliagkas, I., Guibas, L.: Learning representations and generative models for 3D point clouds. In: International Conference on Machine Learning, pp. 40\u201349. PMLR (2018)"},{"issue":"6","key":"17_CR2","doi-asserted-by":"publisher","first-page":"1408","DOI":"10.1002\/we.2493","volume":"23","author":"R Bakhshi","year":"2020","unstructured":"Bakhshi, R., Sandborn, P.: Maximizing the returns of LIDAR systems in wind farms for yaw error correction applications. Wind Energy 23(6), 1408\u20131421 (2020)","journal-title":"Wind Energy"},{"key":"17_CR3","doi-asserted-by":"crossref","unstructured":"Behley, J., et al.: SemanticKITTI: a dataset for semantic scene understanding of LiDAR sequences. In: Proceedings of the IEEE\/CVF International Conference\u00a0on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00939"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Caccia, L., Van\u00a0Hoof, H., Courville, A., Pineau, J.: Deep generative modeling of LiDAR data. In: 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 5034\u20135040. IEEE (2019)","DOI":"10.1109\/IROS40897.2019.8968535"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuScenes: 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":"17_CR6","doi-asserted-by":"crossref","unstructured":"Chai, Y., et al.: To the point: efficient 3D object detection in the range image with graph convolution kernels. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2021)","DOI":"10.1109\/CVPR46437.2021.01574"},{"key":"17_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1007\/978-3-030-20893-6_7","volume-title":"Computer Vision \u2013 ACCV 2018","author":"K Chen","year":"2019","unstructured":"Chen, K., Choy, C.B., Savva, M., Chang, A.X., Funkhouser, T., Savarese, S.: Text2Shape: generating shapes from natural language by learning joint embeddings. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018, Part III. LNCS, vol. 11363, pp. 100\u2013116. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20893-6_7"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Chen, R., Chen, Y., Jiao, N., Jia, K.: Fantasia3D: disentangling geometry and appearance for high-quality text-to-3D content creation. arXiv preprint arXiv:2303.13873 (2023)","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Z., Wang, F., Liu, H.: Text-to-3D using gaussian splatting. arXiv preprint arXiv:2309.16585 (2023)","DOI":"10.1109\/CVPR52733.2024.02022"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Cho, J., Zala, A., Bansal, M.: DALL-Eval: probing the reasoning skills and social biases of text-to-image generation models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3043\u20133054 (2023)","DOI":"10.1109\/ICCV51070.2023.00283"},{"key":"17_CR11","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1007\/978-3-031-19836-6_6","volume-title":"European Conference on Computer Vision 2022","author":"K Crowson","year":"2022","unstructured":"Crowson, K., et al.: VQGAN-CLIP: open domain image generation and editing with natural language guidance. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13697, pp. 88\u2013105. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19836-6_6"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Cui, C., et\u00a0al.: A survey on multimodal large language models for autonomous driving. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 958\u2013979 (2024)","DOI":"10.1109\/WACVW60836.2024.00106"},{"issue":"8","key":"17_CR13","doi-asserted-by":"publisher","first-page":"1997","DOI":"10.1007\/s12524-021-01366-x","volume":"49","author":"SI Deliry","year":"2021","unstructured":"Deliry, S.I., Avdan, U.: Accuracy of unmanned aerial systems photogrammetry and structure from motion in surveying and mapping: a review. J. Indian Soc. Remote Sens. 49(8), 1997\u20132017 (2021)","journal-title":"J. Indian Soc. Remote Sens."},{"key":"17_CR14","unstructured":"Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A., Koltun, V.: CARLA: an open urban driving simulator. In: Conference on Robot Learning, pp. 1\u201316. PMLR (2017)"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Dreissig, M., Scheuble, D., Piewak, F., Boedecker, J.: Survey on LiDAR perception in adverse weather conditions. arXiv preprint arXiv:2304.06312 (2023)","DOI":"10.1109\/IV55152.2023.10186539"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Fu, M., Liu, H., Yu, Y., Chen, J., Wang, K.: DW-GAN: a discrete wavelet transform GAN for nonhomogeneous dehazing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 203\u2013212 (2021)","DOI":"10.1109\/CVPRW53098.2021.00029"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Ge, S., Park, T., Zhu, J.Y., Huang, J.B.: Expressive text-to-image generation with rich text. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7545\u20137556 (2023)","DOI":"10.1109\/ICCV51070.2023.00694"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133361. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"17_CR19","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"17_CR20","unstructured":"Gulino, C., et\u00a0al.: Waymax: an accelerated, data-driven simulator for large-scale autonomous driving research. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: LVIS: a dataset for large vocabulary instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5356\u20135364 (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"17_CR22","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"17_CR23","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6840\u20136851 (2020)"},{"key":"17_CR24","unstructured":"Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., Chen, W.: Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"17_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1007\/978-3-030-58555-6_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"L Hui","year":"2020","unstructured":"Hui, L., Xu, R., Xie, J., Qian, J., Yang, J.: Progressive point cloud deconvolution generation network. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part XV. LNCS, vol. 12360, pp. 397\u2013413. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_24"},{"issue":"1\u20133","key":"17_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/0600000079","volume":"12","author":"J Janai","year":"2020","unstructured":"Janai, J., G\u00fcney, F., Behl, A., Geiger, A., et al.: Computer vision for autonomous vehicles: problems, datasets and state of the art. Found. Trends\u00ae Comput. Graph. Vis. 12(1\u20133), 1\u2013308 (2020)","journal-title":"Found. Trends\u00ae Comput. Graph. Vis."},{"key":"17_CR27","unstructured":"Kasten, Y., Rahamim, O., Chechik, G.: Point cloud completion with pretrained text-to-image diffusion models. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"17_CR28","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D Gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42(4), 139-1 (2023)","DOI":"10.1145\/3592433"},{"key":"17_CR29","doi-asserted-by":"crossref","unstructured":"Kim, Y., Lee, J., Kim, J.H., Ha, J.W., Zhu, J.Y.: Dense text-to-image generation with attention modulation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7701\u20137711 (2023)","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"17_CR30","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"17_CR31","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"17_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1007\/978-3-030-58592-1_41","volume-title":"Computer Vision \u2013 ECCV 2020","author":"R Klokov","year":"2020","unstructured":"Klokov, R., Boyer, E., Verbeek, J.: Discrete point flow networks for efficient point cloud generation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12368, pp. 694\u2013710. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58592-1_41"},{"key":"17_CR33","doi-asserted-by":"crossref","unstructured":"Kong, L., et al.: Robo3D: towards robust and reliable 3D perception against corruptions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19994\u201320006 (2023)","DOI":"10.1109\/ICCV51070.2023.01830"},{"key":"17_CR34","unstructured":"Kuo, W., Cui, Y., Gu, X., Piergiovanni, A., Angelova, A.: F-VLM: open-vocabulary object detection upon frozen vision and language models. arXiv preprint arXiv:2209.15639 (2022)"},{"key":"17_CR35","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: PromptKD: unsupervised prompt distillation for vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26617\u201326626 (2024)","DOI":"10.1109\/CVPR52733.2024.02513"},{"key":"17_CR36","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Curriculum temperature for knowledge distillation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 1504\u20131512 (2023)","DOI":"10.1609\/aaai.v37i2.25236"},{"issue":"3","key":"17_CR37","doi-asserted-by":"publisher","first-page":"3292","DOI":"10.1109\/TPAMI.2022.3179507","volume":"45","author":"Y Liao","year":"2022","unstructured":"Liao, Y., Xie, J., Geiger, A.: KITTI-360: a novel dataset and benchmarks for urban scene understanding in 2D and 3D. IEEE Trans. Pattern Anal. Mach. Intell. 45(3), 3292\u20133310 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"17_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part V. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"17_CR39","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wang, Y., Qi, X., Fu, C.W.: Towards implicit text-guided 3D shape generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17896\u201317906 (2022)","DOI":"10.1109\/CVPR52688.2022.01737"},{"key":"17_CR40","doi-asserted-by":"crossref","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., Van\u00a0Gool, L.: RePaint: inpainting using denoising diffusion probabilistic models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11461\u201311471 (2022)","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"17_CR41","doi-asserted-by":"crossref","unstructured":"Luo, S., Hu, W.: Diffusion probabilistic models for 3D point cloud generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2837\u20132845 (2021)","DOI":"10.1109\/CVPR46437.2021.00286"},{"key":"17_CR42","doi-asserted-by":"crossref","unstructured":"Manivasagam, S., et al.: LiDARsim: realistic LiDAR simulation by leveraging the real world. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11167\u201311176 (2020)","DOI":"10.1109\/CVPR42600.2020.01118"},{"key":"17_CR43","doi-asserted-by":"crossref","unstructured":"Meyer, G.P., Laddha, A., Kee, E., Vallespi-Gonzalez, C., Wellington, C.K.: LaserNet: an efficient probabilistic 3D object detector for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12677\u201312686 (2019)","DOI":"10.1109\/CVPR.2019.01296"},{"issue":"1","key":"17_CR44","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. Commun. ACM 65(1), 99\u2013106 (2021)","journal-title":"Commun. ACM"},{"key":"17_CR45","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":"1","key":"17_CR46","first-page":"109","volume":"16","author":"SAH Mohsan","year":"2023","unstructured":"Mohsan, S.A.H., Othman, N.Q.H., Li, Y., Alsharif, M.H., Khan, M.A.: Unmanned aerial vehicles (UAVs): practical aspects, applications, open challenges, security issues, and future trends. Intell. Serv. Robot. 16(1), 109\u2013137 (2023)","journal-title":"Intell. Serv. Robot."},{"key":"17_CR47","doi-asserted-by":"crossref","unstructured":"Nakashima, K., Iwashita, Y., Kurazume, R.: Generative range imaging for learning scene priors of 3D LiDAR data. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1256\u20131266 (2023)","DOI":"10.1109\/WACV56688.2023.00131"},{"key":"17_CR48","doi-asserted-by":"crossref","unstructured":"Nakashima, K., Kurazume, R.: Learning to drop points for LiDAR scan synthesis. In: 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 222\u2013229. IEEE (2021)","DOI":"10.1109\/IROS51168.2021.9636747"},{"key":"17_CR49","doi-asserted-by":"crossref","unstructured":"Nakashima, K., Kurazume, R.: LiDAR data synthesis with denoising diffusion probabilistic models. arXiv preprint arXiv:2309.09256 (2023)","DOI":"10.1109\/ICRA57147.2024.10611480"},{"key":"17_CR50","unstructured":"Paszke, A., et\u00a0al.: PyTorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"issue":"7","key":"17_CR51","doi-asserted-by":"publisher","first-page":"4322","DOI":"10.1109\/LRA.2023.3282382","volume":"8","author":"A Piroli","year":"2023","unstructured":"Piroli, A., Dallabetta, V., Kopp, J., Walessa, M., Meissner, D., Dietmayer, K.: Energy-based detection of adverse weather effects in LiDAR data. IEEE Robot. Autom. Lett. 8(7), 4322\u20134329 (2023)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"17_CR52","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: DreamFusion: Text-to-3D using 2D diffusion. arXiv preprint arXiv:2209.14988 (2022)"},{"key":"17_CR53","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652\u2013660 (2017)"},{"key":"17_CR54","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"17_CR55","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with CLIP latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"17_CR56","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, Part III. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"17_CR57","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. In: Advances in Neural Information Processing Systems, vol. 35, pp. 36479\u201336494 (2022)"},{"key":"17_CR58","unstructured":"Sauer, A., Chitta, K., M\u00fcller, J., Geiger, A.: Projected GANs converge faster. In: Advances in Neural Information Processing Systems, vol. 34, pp. 17480\u201317492 (2021)"},{"key":"17_CR59","doi-asserted-by":"crossref","unstructured":"Schubert, S., Neubert, P., P\u00f6schmann, J., Protzel, P.: Circular convolutional neural networks for panoramic images and laser data. In: 2019 IEEE Intelligent Vehicles Symposium (IV), pp. 653\u2013660. IEEE (2019)","DOI":"10.1109\/IVS.2019.8813862"},{"key":"17_CR60","unstructured":"Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models. In: Advances in Neural Information Processing Systems, vol. 35, pp. 25278\u201325294 (2022)"},{"key":"17_CR61","unstructured":"Song, Y., Ermon, S.: Generative modeling by estimating gradients of the data distribution. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"17_CR62","unstructured":"Tancik, M., et al.: Fourier features let networks learn high frequency functions in low dimensional domains. In: Advances in Neural Information Processing Systems, vol. 33, pp. 7537\u20137547 (2020)"},{"key":"17_CR63","doi-asserted-by":"crossref","unstructured":"Tyszkiewicz, M.J., Fua, P., Trulls, E.: GECCO: geometrically-conditioned point diffusion models. arXiv preprint arXiv:2303.05916 (2023)","DOI":"10.1109\/ICCV51070.2023.00203"},{"key":"17_CR64","unstructured":"Valsesia, D., Fracastoro, G., Magli, E.: Learning localized generative models for 3D point clouds via graph convolution. In: International Conference on Learning Representations (2018)"},{"key":"17_CR65","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"17_CR66","unstructured":"Wang, J., Yuan, H., Chen, D., Zhang, Y., Wang, X., Zhang, S.: ModelScope text-to-video technical report. arXiv preprint arXiv:2308.06571 (2023)"},{"issue":"8","key":"17_CR67","doi-asserted-by":"publisher","first-page":"2122","DOI":"10.1007\/s11263-023-01784-z","volume":"131","author":"Y Wang","year":"2023","unstructured":"Wang, Y., et al.: Multi-modal 3D object detection in autonomous driving: a survey. Int. J. Comput. Vis. 131(8), 2122\u20132152 (2023)","journal-title":"Int. J. Comput. Vis."},{"key":"17_CR68","unstructured":"Wang, Z., Liu, W., He, Q., Wu, X., Yi, Z.: CLIP-GEN: language-free training of a text-to-image generator with CLIP. arXiv preprint arXiv:2203.00386 (2022)"},{"key":"17_CR69","doi-asserted-by":"crossref","unstructured":"Wang, Z.J., Montoya, E., Munechika, D., Yang, H., Hoover, B., Chau, D.H.: DiffusionDB: a large-scale prompt gallery dataset for text-to-image generative models. arXiv preprint arXiv:2210.14896 (2022)","DOI":"10.18653\/v1\/2023.acl-long.51"},{"key":"17_CR70","doi-asserted-by":"crossref","unstructured":"Wen, C., Yu, B., Tao, D.: Learning progressive point embeddings for 3D point cloud generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10266\u201310275 (2021)","DOI":"10.1109\/CVPR46437.2021.01013"},{"key":"17_CR71","doi-asserted-by":"crossref","unstructured":"Wu, J.Z., et al.: Tune-A-Video: one-shot tuning of image diffusion models for text-to-video generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7623\u20137633 (2023)","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"17_CR72","doi-asserted-by":"crossref","unstructured":"Wu, L., et al.: Fast point cloud generation with straight flows. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9445\u20139454 (2023)","DOI":"10.1109\/CVPR52729.2023.00911"},{"key":"17_CR73","doi-asserted-by":"crossref","unstructured":"Wu, Z., Wang, Y., Feng, M., Xie, H., Mian, A.: Sketch and text guided diffusion model for colored point cloud generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8929\u20138939 (2023)","DOI":"10.1109\/ICCV51070.2023.00820"},{"issue":"5","key":"17_CR74","first-page":"6320","volume":"45","author":"P Xiang","year":"2022","unstructured":"Xiang, P., et al.: Snowflake point deconvolution for point cloud completion and generation with skip-transformer. IEEE Trans. Pattern Anal. Mach. Intell. 45(5), 6320\u20136338 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"17_CR75","unstructured":"Xu, J., et al.: ImageReward: learning and evaluating human preferences for text-to-image generation. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"17_CR76","doi-asserted-by":"crossref","unstructured":"Xu, Z., Xing, S., Sangineto, E., Sebe, N.: SpectralCLIP: preventing artifacts in text-guided style transfer from a spectral perspective. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5121\u20135130 (2024)","DOI":"10.1109\/WACV57701.2024.00504"},{"key":"17_CR77","unstructured":"Xue, M., He, J., He, Y., Liu, Z., Wang, W., Zhou, M.: Low-light image enhancement via CLIP-Fourier guided wavelet diffusion. arXiv preprint arXiv:2401.03788 (2024)"},{"key":"17_CR78","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1007\/978-3-031-19769-7_22","volume-title":"European Conference on Computer Vision 2022","author":"Z Yan","year":"2022","unstructured":"Yan, Z., Li, X., Wang, K., Zhang, Z., Li, J., Yang, J.: Multi-modal masked pre-training for monocular panoramic depth completion. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13661, pp. 378\u2013395. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19769-7_22"},{"key":"17_CR79","doi-asserted-by":"crossref","unstructured":"Yan, Z., et al.: Tri-perspective view decomposition for geometry-aware depth completion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4874\u20134884 (2024)","DOI":"10.1109\/CVPR52733.2024.00466"},{"key":"17_CR80","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1007\/978-3-031-19812-0_13","volume-title":"European Conference on Computer Vision 2022","author":"Z Yan","year":"2022","unstructured":"Yan, Z., Wang, K., Li, X., Zhang, Z., Li, J., Yang, J.: RigNet: repetitive image guided network for depth completion. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13687, pp. 214\u2013230. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19812-0_13"},{"key":"17_CR81","doi-asserted-by":"crossref","unstructured":"Yang, G., Huang, X., Hao, Z., Liu, M.Y., Belongie, S., Hariharan, B.: PointFlow: 3D point cloud generation with continuous normalizing flows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4541\u20134550 (2019)","DOI":"10.1109\/ICCV.2019.00464"},{"key":"17_CR82","doi-asserted-by":"crossref","unstructured":"Yang, X., Zhou, D., Feng, J., Wang, X.: Diffusion probabilistic model made slim. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22552\u201322562 (2023)","DOI":"10.1109\/CVPR52729.2023.02160"},{"key":"17_CR83","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2022.104641","volume":"146","author":"H Yin","year":"2023","unstructured":"Yin, H., Lin, Z., Yeoh, J.K.: Semantic localization on BIM-generated maps using a 3D LiDAR sensor. Autom. Constr. 146, 104641 (2023)","journal-title":"Autom. Constr."},{"key":"17_CR84","doi-asserted-by":"crossref","unstructured":"Yuan, L., et al.: Tokens-to-Token ViT: training vision transformers from scratch on ImageNet. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 558\u2013567 (2021)","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"17_CR85","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2020.102921","volume":"193","author":"M Zamorski","year":"2020","unstructured":"Zamorski, M., et al.: Adversarial autoencoders for compact representations of 3D point clouds. Comput. Vis. Image Underst. 193, 102921 (2020)","journal-title":"Comput. Vis. Image Underst."},{"key":"17_CR86","doi-asserted-by":"crossref","unstructured":"Zhou, Y., et al.: Towards language-free training for text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17907\u201317917 (2022)","DOI":"10.1109\/CVPR52688.2022.01738"},{"issue":"7","key":"17_CR87","doi-asserted-by":"publisher","first-page":"6907","DOI":"10.1109\/TITS.2021.3063477","volume":"23","author":"Q Zou","year":"2021","unstructured":"Zou, Q., Sun, Q., Chen, L., Nie, B., Li, Q.: A comparative analysis of LiDAR SLAM-based indoor navigation for autonomous vehicles. IEEE Trans. Intell. Transp. Syst. 23(7), 6907\u20136921 (2021)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"17_CR88","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/978-3-031-20050-2_2","volume-title":"European Conference on Computer Vision 2022","author":"V Zyrianov","year":"2022","unstructured":"Zyrianov, V., Zhu, X., Wang, S.: Learning to generate realistic LiDAR point clouds. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13683, pp. 17\u201335. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20050-2_2"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72992-8_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T12:05:31Z","timestamp":1732968331000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72992-8_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,30]]},"ISBN":["9783031729911","9783031729928"],"references-count":88,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72992-8_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,10,30]]},"assertion":[{"value":"30 October 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}