{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:13:07Z","timestamp":1768781587072,"version":"3.49.0"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729065","type":"print"},{"value":"9783031729072","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"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\/978-3-031-72907-2_21","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:22:17Z","timestamp":1730301737000},"page":"354-370","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Fast Training of\u00a0Diffusion Transformer with\u00a0Extreme Masking for\u00a03D Point Clouds Generation"],"prefix":"10.1007","author":[{"given":"Shentong","family":"Mo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enze","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junsong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthias","family":"Nie\u00dfner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenguo","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"21_CR1","unstructured":"Achlioptas, P., Diamanti, O., Mitliagkas, I., Guibas, L.: Learning representations and generative models for 3D point clouds. In: Proceedings of the International Conference on Machine Learning (ICML) (2018)"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Bao, F., et al.: All are worth words: a VIT backbone for diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"21_CR3","unstructured":"Bao, F., et al.: One transformer fits all distributions in multi-modal diffusion at scale. arXiv preprint arXiv:2303.06555 (2023)"},{"key":"21_CR4","unstructured":"Chang, A.X., et al.: Shapenet: an information-rich 3D model repository. arXiv preprint arXiv:1512.03012 (2015)"},{"key":"21_CR5","unstructured":"Chang, H., et al.: Muse: text-to-image generation via masked generative transformers. arXiv preprint arXiv:2301.00704 (2023)"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Chang, H., Zhang, H., Jiang, L., Liu, C., Freeman, W.T.: Maskgit: masked generative image transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11315\u201311325 (2022)","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Objaverse-xl: a universe of 10M+ 3D objects. arXiv preprint arXiv:2307.05663 (2023)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Objaverse: a universe of annotated 3D objects. arXiv preprint arXiv:2212.08051 (2022)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"21_CR9","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"21_CR10","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: Proceedings of International Conference on Learning Representations (ICLR) (2021)"},{"key":"21_CR11","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"21_CR12","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) (2018)","DOI":"10.1007\/978-3-030-01234-2_7"},{"key":"21_CR13","unstructured":"Gao, J., et al.: GET3D: a generative model of high quality 3D textured shapes learned from images. In: Proceedings of Advances In Neural Information Processing Systems (NeurIPS) (2022)"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Gao, S., Zhou, P., Cheng, M.M., Yan, S.: Masked diffusion transformer is a strong image synthesizer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 23164\u201323173 (2023)","DOI":"10.1109\/ICCV51070.2023.02117"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"21_CR16","unstructured":"Kim, H., Lee, H., Kang, W., Lee, J.Y., Kim, N.S.: Softflow: probabilistic framework for normalizing flow on manifolds. In: Proceedings of Advances in Neural Information Processing Systems (NeurIPS) (2020)"},{"key":"21_CR17","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 (CVPR), pp. 15059\u201315068 (2021)","DOI":"10.1109\/CVPR46437.2021.01481"},{"key":"21_CR18","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Klokov, R., Boyer, E., Verbeek, J.: Discrete point flow networks for efficient point cloud generation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 694\u2013710 (2020)","DOI":"10.1007\/978-3-030-58592-1_41"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Li, Y., Fan, H., Hu, R., Feichtenhofer, C., He, K.: Scaling language-image pre-training via masking. arXiv preprint arXiv:2212.00794 (2022)","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"21_CR21","unstructured":"Liu, Z., Feng, Y., Black, M.J., Nowrouzezahrai, D., Paull, L., Liu, W.: Meshdiffusion: score-based generative 3D mesh modeling. In: Proceedings of International Conference on Learning Representations (ICLR) (2023)"},{"key":"21_CR22","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 (CVPR), pp. 2837\u20132845 (2021)","DOI":"10.1109\/CVPR46437.2021.00286"},{"key":"21_CR23","unstructured":"Mo, S., et al.: DiT-3D: exploring plain diffusion transformers for 3D shape generation. In: Proceedings of Advances In Neural Information Processing Systems (NeurIPS) (2023)"},{"key":"21_CR24","unstructured":"Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Proceedings of Advances in Neural Information Processing Systems (NeurIPS), pp. 8026\u20138037 (2019)"},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. arXiv preprint arXiv:2212.09748 (2022)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"21_CR26","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et\u00a0al.: Improving language understanding by generative pre-training. OpenAI (2018)"},{"key":"21_CR27","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 (ICCV), pp. 3859\u20133868 (2019)","DOI":"10.1109\/ICCV.2019.00396"},{"key":"21_CR28","unstructured":"Valsesia, D., Fracastoro, G., Magli, E.: Learning localized generative models for 3D point clouds via graph convolution. In: Proceedings of International Conference on Learning Representations (ICLR) (2019)"},{"key":"21_CR29","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"21_CR30","doi-asserted-by":"crossref","unstructured":"Xie, E., et al.: Difffit: unlocking transferability of large diffusion models via simple parameter-efficient fine-tuning. arXiv preprint arXiv:2304.06648 (2023)","DOI":"10.1109\/ICCV51070.2023.00390"},{"key":"21_CR31","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 (ICCV), pp. 4541\u20134550 (2019)","DOI":"10.1109\/ICCV.2019.00464"},{"key":"21_CR32","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 (CVPR), pp. 206\u2013215 (2018)","DOI":"10.1109\/CVPR.2018.00029"},{"key":"21_CR33","unstructured":"Zeng, X., et al.: Lion: latent point diffusion models for 3D shape generation. In: Proceedings of Advances in Neural Information Processing Systems (NeurIPS) (2022)"},{"key":"21_CR34","unstructured":"Zheng, H., Nie, W., Vahdat, A., Anandkumar, A.: Fast training of diffusion models with masked transformers (2023)"},{"key":"21_CR35","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 (ICCV), 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\/978-3-031-72907-2_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:33:46Z","timestamp":1730302426000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72907-2_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031729065","9783031729072"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72907-2_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 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"}}]}}