{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T11:37:31Z","timestamp":1769859451537,"version":"3.49.0"},"publisher-location":"Cham","reference-count":103,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031728549","type":"print"},{"value":"9783031728556","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T00:00:00Z","timestamp":1731110400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T00:00:00Z","timestamp":1731110400000},"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\/978-3-031-72855-6_25","type":"book-chapter","created":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T18:48:07Z","timestamp":1731091687000},"page":"434-453","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["FrePolad: Frequency-Rectified Point Latent Diffusion for\u00a0Point Cloud Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1096-1927","authenticated-orcid":false,"given":"Chenliang","family":"Zhou","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5964-5282","authenticated-orcid":false,"given":"Fangcheng","family":"Zhong","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7985-4177","authenticated-orcid":false,"given":"Param","family":"Hanji","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7660-3102","authenticated-orcid":false,"given":"Zhilin","family":"Guo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1888-4006","authenticated-orcid":false,"given":"Kyle","family":"Fogarty","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3312-3272","authenticated-orcid":false,"given":"Alejandro","family":"Sztrajman","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5546-6906","authenticated-orcid":false,"given":"Hongyun","family":"Gao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4700-2236","authenticated-orcid":false,"given":"Cengiz","family":"Oztireli","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,9]]},"reference":[{"key":"25_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)"},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Blattmann, A., et al.: Align your latents: high-resolution video synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22563\u201322575 (2023)","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"25_CR3","unstructured":"Bonev, B., et al.: Spherical fourier neural operators: learning stable dynamics on the sphere (2023)"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: Instructpix2pix: learning to follow image editing instructions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18392\u201318402 (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"25_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"364","DOI":"10.1007\/978-3-030-58580-8_22","volume-title":"Computer Vision \u2013 ECCV 2020","author":"R Cai","year":"2020","unstructured":"Cai, R., et al.: Learning gradient fields for shape generation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 364\u2013381. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_22"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Chandrasegaran, K., Tran, N.T., Cheung, N.M.: A closer look at fourier spectrum discrepancies for CNN-generated images detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7200\u20137209 (2021)","DOI":"10.1109\/CVPR46437.2021.00712"},{"key":"25_CR7","unstructured":"Chang, A.X., et al.: Shapenet: an information-rich 3D model repository. arXiv preprint arXiv:1512.03012 (2015)"},{"key":"25_CR8","unstructured":"Chen, N., Zhang, Y., Zen, H., Weiss, R.J., Norouzi, M., Chan, W.: Wavegrad: estimating gradients for waveform generation. arXiv preprint arXiv:2009.00713 (2020)"},{"key":"25_CR9","unstructured":"Chen, R.T., Rubanova, Y., Bettencourt, J., Duvenaud, D.K.: Neural ordinary differential equations. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"25_CR10","unstructured":"Chen, X., et al.: Variational lossy autoencoder. arXiv preprint arXiv:1611.02731 (2016)"},{"key":"25_CR11","volume-title":"Methods of Mathematical Physics: Partial Differential Equations","author":"R Courant","year":"2008","unstructured":"Courant, R., Hilbert, D.: Methods of Mathematical Physics: Partial Differential Equations. Wiley, Hoboken (2008)"},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Csisz\u00e1r, I.: I-divergence geometry of probability distributions and minimization problems. Ann. Probab. 146\u2013158 (1975)","DOI":"10.1214\/aop\/1176996454"},{"key":"25_CR13","first-page":"2051","volume":"33","author":"S Czolbe","year":"2020","unstructured":"Czolbe, S., Krause, O., Cox, I., Igel, C.: A loss function for generative neural networks based on Watson\u2019s perceptual model. Adv. Neural. Inf. Process. Syst. 33, 2051\u20132061 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR14","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR15","unstructured":"Dinh, L., Krueger, D., Bengio, Y.: Nice: non-linear independent components estimation. arXiv preprint arXiv:1410.8516 (2014)"},{"key":"25_CR16","unstructured":"Dosovitskiy, A., Brox, T.: Generating images with perceptual similarity metrics based on deep networks. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"25_CR17","doi-asserted-by":"crossref","unstructured":"Durall, R., Keuper, M., Keuper, J.: Watch your up-convolution: CNN based generative deep neural networks are failing to reproduce spectral distributions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7890\u20137899 (2020)","DOI":"10.1109\/CVPR42600.2020.00791"},{"key":"25_CR18","first-page":"3022","volume":"33","author":"T Dzanic","year":"2020","unstructured":"Dzanic, T., Shah, K., Witherden, F.: Fourier spectrum discrepancies in deep network generated images. Adv. Neural. Inf. Process. Syst. 33, 3022\u20133032 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12873\u201312883 (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Fan, H., Su, H., Guibas, L.J.: A point set generation network for 3D object reconstruction from a single image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 605\u2013613 (2017)","DOI":"10.1109\/CVPR.2017.264"},{"key":"25_CR21","unstructured":"Fourier, J.: M\u00e9moire sur la propagation de la chaleur dans les corps solides (extrait). Nouveau Bulletin des Sciences par la Soci\u00e9t\u00e9 Philomathique de Paris 1, 112\u201316 (1808)"},{"key":"25_CR22","doi-asserted-by":"crossref","unstructured":"Gadelha, M., Wang, R., Maji, S.: Multiresolution tree networks for 3D point cloud processing. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 103\u2013118 (2018)","DOI":"10.1007\/978-3-030-01234-2_7"},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Gao, G., et al.: Neural image compression via attentional multi-scale back projection and frequency decomposition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14677\u201314686 (2021)","DOI":"10.1109\/ICCV48922.2021.01441"},{"issue":"11","key":"25_CR24","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.: Vision meets robotics: the kitti dataset. Int. J. Robot. Res. 32(11), 1231\u20131237 (2013)","journal-title":"Int. J. Robot. Res."},{"key":"25_CR25","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"25_CR26","unstructured":"Grathwohl, W., Chen, R.T., Bettencourt, J., Sutskever, I., Duvenaud, D.: Ffjord: free-form continuous dynamics for scalable reversible generative models. arXiv preprint arXiv:1810.01367 (2018)"},{"key":"25_CR27","doi-asserted-by":"crossref","unstructured":"Groueix, T., Fisher, M., Kim, V.G., Russell, B.C., Aubry, M.: A papier-m\u00e2ch\u00e9 approach to learning 3D surface generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 216\u2013224 (2018)","DOI":"10.1109\/CVPR.2018.00030"},{"key":"25_CR28","unstructured":"He, Y., Yang, T., Zhang, Y., Shan, Y., Chen, Q.: Latent video diffusion models for high-fidelity video generation with arbitrary lengths. arXiv preprint arXiv:2211.13221 (2022)"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"He, Y., Tang, D., Zhang, Y., Xue, X., Fu, Y.: Grad-PU: arbitrary-scale point cloud upsampling via gradient descent with learned distance functions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5354\u20135363 (2023)","DOI":"10.1109\/CVPR52729.2023.00518"},{"key":"25_CR30","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"1","key":"25_CR31","first-page":"2249","volume":"23","author":"J Ho","year":"2022","unstructured":"Ho, J., Saharia, C., Chan, W., Fleet, D.J., Norouzi, M., Salimans, T.: Cascaded diffusion models for high fidelity image generation. J. Mach. Learn. Res. 23(1), 2249\u20132281 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Hou, X., Shen, L., Sun, K., Qiu, G.: Deep feature consistent variational autoencoder. In: 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1133\u20131141. IEEE (2017)","DOI":"10.1109\/WACV.2017.131"},{"key":"25_CR33","doi-asserted-by":"crossref","unstructured":"Jeong, M., Kim, H., Cheon, S.J., Choi, B.J., Kim, N.S.: Diff-TTS: a denoising diffusion model for text-to-speech. arXiv preprint arXiv:2104.01409 (2021)","DOI":"10.21437\/Interspeech.2021-469"},{"key":"25_CR34","doi-asserted-by":"crossref","unstructured":"Jiang, L., Dai, B., Wu, W., Loy, C.C.: Focal frequency loss for image reconstruction and synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13919\u201313929 (2021)","DOI":"10.1109\/ICCV48922.2021.01366"},{"key":"25_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1007\/978-3-319-46475-6_43","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Johnson","year":"2016","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694\u2013711. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_43"},{"key":"25_CR36","unstructured":"Karush, W.: Minima of functions of several variables with inequalities as side constraints. M.Sc. dissertation, Department of Mathematics, University of Chicago (1939)"},{"key":"25_CR37","first-page":"16388","volume":"33","author":"H Kim","year":"2020","unstructured":"Kim, H., Lee, H., Kang, W.H., Lee, J.Y., Kim, N.S.: Softflow: probabilistic framework for normalizing flow on manifolds. Adv. Neural. Inf. Process. Syst. 33, 16388\u201316397 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR38","doi-asserted-by":"crossref","unstructured":"Kim, J., Hua, B.S., Nguyen, T., Yeung, S.K.: Pointinverter: point cloud reconstruction and editing via a generative model with shape priors. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 592\u2013601 (2023)","DOI":"10.1109\/WACV56688.2023.00066"},{"key":"25_CR39","doi-asserted-by":"crossref","unstructured":"Kim, J., Yoo, J., Lee, J., Hong, S.: Setvae: learning hierarchical composition for generative modeling of set-structured data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15059\u201315068 (2021)","DOI":"10.1109\/CVPR46437.2021.01481"},{"key":"25_CR40","doi-asserted-by":"crossref","unstructured":"Kim, S.Y., et al.: Zoom-to-inpaint: image inpainting with high-frequency details. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 477\u2013487 (2022)","DOI":"10.1109\/CVPRW56347.2022.00063"},{"key":"25_CR41","first-page":"21696","volume":"34","author":"D Kingma","year":"2021","unstructured":"Kingma, D., Salimans, T., Poole, B., Ho, J.: Variational diffusion models. Adv. Neural. Inf. Process. Syst. 34, 21696\u201321707 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR42","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"25_CR43","unstructured":"Kingma, D.P., Dhariwal, P.: Glow: generative flow with invertible 1x1 convolutions. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"25_CR44","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":"25_CR45","doi-asserted-by":"crossref","unstructured":"Kuhn, H., Tucker, A.: Nonlinear programming. In: Proceedings of 2nd Berkeley Symposium, pp. 481\u2013492 (1951)","DOI":"10.1525\/9780520411586-036"},{"key":"25_CR46","doi-asserted-by":"crossref","unstructured":"Kurenkov, A., et al.: Deformnet: free-form deformation network for 3D shape reconstruction from a single image. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 858\u2013866. IEEE (2018)","DOI":"10.1109\/WACV.2018.00099"},{"key":"25_CR47","doi-asserted-by":"crossref","unstructured":"Lee, D., Kim, C., Kim, S., Cho, M., Han, W.S.: Autoregressive image generation using residual quantization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11523\u201311532 (2022)","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"25_CR48","unstructured":"Li, C.L., Zaheer, M., Zhang, Y., Poczos, B., Salakhutdinov, R.: Point cloud GAN. arXiv preprint arXiv:1810.05795 (2018)"},{"key":"25_CR49","doi-asserted-by":"crossref","unstructured":"Li, R., Li, X., Fu, C.W., Cohen-Or, D., Heng, P.A.: Pu-GAN: a point cloud upsampling adversarial network. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7203\u20137212 (2019)","DOI":"10.1109\/ICCV.2019.00730"},{"key":"25_CR50","doi-asserted-by":"crossref","unstructured":"Li, S., Liu, M., Walder, C.: Editvae: unsupervised parts-aware controllable 3D point cloud shape generation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 1386\u20131394 (2022)","DOI":"10.1609\/aaai.v36i2.20027"},{"key":"25_CR51","unstructured":"Li, S., Walder, C., Liu, M.: Spa-VAE: similar-parts-assignment for unsupervised 3D point cloud generation. arXiv preprint arXiv:2203.07825 (2022)"},{"key":"25_CR52","doi-asserted-by":"publisher","first-page":"4540","DOI":"10.1109\/TIP.2021.3073318","volume":"30","author":"Y Li","year":"2021","unstructured":"Li, Y., Baciu, G.: HSGAN: hierarchical graph learning for point cloud generation. IEEE Trans. Image Process. 30, 4540\u20134554 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"25_CR53","doi-asserted-by":"crossref","unstructured":"Lin, X., Li, Y., Hsiao, J., Ho, C., Kong, Y.: Catch missing details: image reconstruction with frequency augmented variational autoencoder. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1736\u20131745 (2023)","DOI":"10.1109\/CVPR52729.2023.00173"},{"key":"25_CR54","unstructured":"Liu, S., Su, D., Yu, D.: DiffGAN-TTS: high-fidelity and efficient text-to-speech with denoising diffusion GANs. arXiv preprint arXiv:2201.11972 (2022)"},{"key":"25_CR55","unstructured":"Liu, Z., Tang, H., Lin, Y., Han, S.: Point-voxel CNN for efficient 3D deep learning. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"25_CR56","unstructured":"Lopez-Paz, D., Oquab, M.: Revisiting classifier two-sample tests. arXiv preprint arXiv:1610.06545 (2016)"},{"key":"25_CR57","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"},{"issue":"1","key":"25_CR58","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":"25_CR59","unstructured":"Mittal, G., Engel, J., Hawthorne, C., Simon, I.: Symbolic music generation with diffusion models. arXiv preprint arXiv:2103.16091 (2021)"},{"key":"25_CR60","unstructured":"Mo, S., et al.: DIT-3D: exploring plain diffusion transformers for 3D shape generation. arXiv preprint arXiv:2307.01831 (2023)"},{"key":"25_CR61","doi-asserted-by":"crossref","unstructured":"Mustafa, A., Hanji, P., Mantiuk, R.: Distilling style from image pairs for global forward and inverse tone mapping. In: Proceedings of the 19th ACM SIGGRAPH European Conference on Visual Media Production, pp. 1\u201310 (2022)","DOI":"10.1145\/3565516.3565520"},{"issue":"2","key":"25_CR62","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0271388","volume":"18","author":"H Naderi","year":"2023","unstructured":"Naderi, H., Noorbakhsh, K., Etemadi, A., Kasaei, S.: LPF-defense: 3D adversarial defense based on frequency analysis. PLoS ONE 18(2), e0271388 (2023)","journal-title":"PLoS ONE"},{"key":"25_CR63","doi-asserted-by":"crossref","unstructured":"Nakayama, G.K., Uy, M.A., Huang, J., Hu, S.M., Li, K., Guibas, L.: Difffacto: controllable part-based 3D point cloud generation with cross diffusion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14257\u201314267 (2023)","DOI":"10.1109\/ICCV51070.2023.01311"},{"key":"25_CR64","unstructured":"Pandey, K., Mukherjee, A., Rai, P., Kumar, A.: Diffusevae: efficient, controllable and high-fidelity generation from low-dimensional latents. arXiv preprint arXiv:2201.00308 (2022)"},{"key":"25_CR65","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1016\/j.jhydrol.2012.10.019","volume":"476","author":"AP Piotrowski","year":"2013","unstructured":"Piotrowski, A.P., Napiorkowski, J.J.: A comparison of methods to avoid overfitting in neural networks training in the case of catchment runoff modelling. J. Hydrol. 476, 97\u2013111 (2013)","journal-title":"J. Hydrol."},{"key":"25_CR66","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: Dreamfusion: text-to-3D using 2D diffusion. arXiv (2022)"},{"key":"25_CR67","doi-asserted-by":"crossref","unstructured":"Preechakul, K., Chatthee, N., Wizadwongsa, S., Suwajanakorn, S.: Diffusion autoencoders: toward a meaningful and decodable representation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10619\u201310629 (2022)","DOI":"10.1109\/CVPR52688.2022.01036"},{"key":"25_CR68","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":"25_CR69","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: deep hierarchical feature learning on point sets in a metric space. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"25_CR70","doi-asserted-by":"crossref","unstructured":"Qian, G., Abualshour, A., Li, G., Thabet, A., Ghanem, B.: Pu-GCN: point cloud upsampling using graph convolutional networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11683\u201311692 (2021)","DOI":"10.1109\/CVPR46437.2021.01151"},{"key":"25_CR71","unstructured":"Rahaman, N., et al.: On the spectral bias of neural networks. In: International Conference on Machine Learning, pp. 5301\u20135310. PMLR (2019)"},{"key":"25_CR72","unstructured":"Rahimi, A., Recht, B.: Random features for large-scale kernel machines. In: Advances in Neural Information Processing Systems, vol. 20 (2007)"},{"key":"25_CR73","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, vol. 1, no. 2, p. 3 (2022)"},{"key":"25_CR74","unstructured":"Razavi, A., Van\u00a0den Oord, A., Vinyals, O.: Generating diverse high-fidelity images with VQ-VAE-2. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"25_CR75","unstructured":"Rezende, D., Mohamed, S.: Variational inference with normalizing flows. In: International Conference on Machine Learning, pp. 1530\u20131538. PMLR (2015)"},{"key":"25_CR76","unstructured":"Rezende, D.J., Mohamed, S., Wierstra, D.: Stochastic backpropagation and approximate inference in deep generative models. In: International Conference on Machine Learning, pp. 1278\u20131286. PMLR (2014)"},{"key":"25_CR77","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"25_CR78","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"},{"key":"25_CR79","unstructured":"Rosca, M., Lakshminarayanan, B., Mohamed, S.: Distribution matching in variational inference. arXiv preprint arXiv:1802.06847 (2018)"},{"key":"25_CR80","unstructured":"Serna, A., Marcotegui, B., Goulette, F., Deschaud, J.E.: 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 (2014)"},{"key":"25_CR81","doi-asserted-by":"crossref","unstructured":"Shu, D.W., Park, S.W., Kwon, J.: 3D point cloud generative adversarial network based on tree structured graph convolutions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3859\u20133868 (2019)","DOI":"10.1109\/ICCV.2019.00396"},{"key":"25_CR82","first-page":"12533","volume":"34","author":"A Sinha","year":"2021","unstructured":"Sinha, A., Song, J., Meng, C., Ermon, S.: D2C: diffusion-decoding models for few-shot conditional generation. Adv. Neural. Inf. Process. Syst. 34, 12533\u201312548 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR83","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning, pp. 2256\u20132265. PMLR (2015)"},{"key":"25_CR84","unstructured":"Song, Y., Shen, L., Xing, L., Ermon, S.: Solving inverse problems in medical imaging with score-based generative models. arXiv preprint arXiv:2111.08005 (2021)"},{"key":"25_CR85","doi-asserted-by":"crossref","unstructured":"Sun, Y., Wang, Y., Liu, Z., Siegel, J., Sarma, S.: Pointgrow: autoregressively learned point cloud generation with self-attention. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 61\u201370 (2020)","DOI":"10.1109\/WACV45572.2020.9093430"},{"key":"25_CR86","first-page":"7537","volume":"33","author":"M Tancik","year":"2020","unstructured":"Tancik, M., et al.: Fourier features let networks learn high frequency functions in low dimensional domains. Adv. Neural. Inf. Process. Syst. 33, 7537\u20137547 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR87","unstructured":"Tomczak, J., Welling, M.: VAE with a vampprior. In: International Conference on Artificial Intelligence and Statistics, pp. 1214\u20131223. PMLR (2018)"},{"key":"25_CR88","first-page":"11287","volume":"34","author":"A Vahdat","year":"2021","unstructured":"Vahdat, A., Kreis, K., Kautz, J.: Score-based generative modeling in latent space. Adv. Neural. Inf. Process. Syst. 34, 11287\u201311302 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR89","first-page":"10021","volume":"35","author":"A Vahdat","year":"2022","unstructured":"Vahdat, A., et al.: Lion: latent point diffusion models for 3D shape generation. Adv. Neural. Inf. Process. Syst. 35, 10021\u201310039 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR90","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"25_CR91","unstructured":"Wang, L., Huang, Y., Tao, P., Hou, Y., Liu, Y.: Learning geometry-image representation for 3D point cloud generation. arXiv preprint arXiv:2011.14289 (2020)"},{"key":"25_CR92","doi-asserted-by":"publisher","first-page":"115205","DOI":"10.1109\/ACCESS.2021.3100891","volume":"9","author":"Y Wang","year":"2021","unstructured":"Wang, Y., Cai, L., Zhang, D., Huang, S.: The frequency discrepancy between real and generated images. IEEE Access 9, 115205\u2013115216 (2021)","journal-title":"IEEE Access"},{"key":"25_CR93","unstructured":"Whang, J., Lindgren, E., Dimakis, A.: Composing normalizing flows for inverse problems. In: International Conference on Machine Learning, pp. 11158\u201311169. PMLR (2021)"},{"key":"25_CR94","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":"25_CR95","unstructured":"Xu, Z.Q.J., Zhang, Y., Luo, T., Xiao, Y., Ma, Z.: Frequency principle: fourier analysis sheds light on deep neural networks. arXiv preprint arXiv:1901.06523 (2019)"},{"key":"25_CR96","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":"25_CR97","doi-asserted-by":"crossref","unstructured":"Yang, Y., Feng, C., Shen, Y., Tian, D.: Foldingnet: point cloud auto-encoder via deep grid deformation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 206\u2013215 (2018)","DOI":"10.1109\/CVPR.2018.00029"},{"key":"25_CR98","doi-asserted-by":"crossref","unstructured":"Yu, L., Li, X., Fu, C.W., Cohen-Or, D., Heng, P.A.: EC-net: an edge-aware point set consolidation network. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 386\u2013402 (2018)","DOI":"10.1007\/978-3-030-01234-2_24"},{"key":"25_CR99","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."},{"issue":"10","key":"25_CR100","doi-asserted-by":"publisher","first-page":"6792","DOI":"10.1109\/TCSVT.2022.3170588","volume":"32","author":"R Zhang","year":"2022","unstructured":"Zhang, R., Chen, J., Gao, W., Li, G., Li, T.H.: Pointot: interpretable geometry-inspired point cloud generative model via optimal transport. IEEE Trans. Circuits Syst. Video Technol. 32(10), 6792\u20136806 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"5","key":"25_CR101","doi-asserted-by":"publisher","first-page":"726","DOI":"10.1109\/TETCI.2021.3100641","volume":"5","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Ti\u0148o, P., Leonardis, A., Tang, K.: A survey on neural network interpretability. IEEE Trans. Emerg. Top. Comput. Intell. 5(5), 726\u2013742 (2021)","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"25_CR102","unstructured":"Zhou, D., Wang, W., Yan, H., Lv, W., Zhu, Y., Feng, J.: Magicvideo: efficient video generation with latent diffusion models. arXiv preprint arXiv:2211.11018 (2022)"},{"key":"25_CR103","doi-asserted-by":"crossref","unstructured":"Zhou, L., Du, Y., Wu, J.: 3D shape generation and completion through point-voxel diffusion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5826\u20135835 (2021)","DOI":"10.1109\/ICCV48922.2021.00577"}],"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\/978-3-031-72855-6_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T19:07:52Z","timestamp":1731092872000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72855-6_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,9]]},"ISBN":["9783031728549","9783031728556"],"references-count":103,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72855-6_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,9]]},"assertion":[{"value":"9 November 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"}}]}}