{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:22:48Z","timestamp":1780392168268,"version":"3.54.1"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729799","type":"print"},{"value":"9783031729805","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-72980-5_18","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:15:43Z","timestamp":1730106943000},"page":"305-322","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["LATTE3D: Large-scale Amortized Text-To-Enhanced3D Synthesis"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5098-904X","authenticated-orcid":false,"given":"Kevin","family":"Xie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1255-6554","authenticated-orcid":false,"given":"Jonathan","family":"Lorraine","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6579-6044","authenticated-orcid":false,"given":"Tianshi","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3521-0417","authenticated-orcid":false,"given":"Jun","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4580-7937","authenticated-orcid":false,"given":"James","family":"Lucas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4915-0256","authenticated-orcid":false,"given":"Antonio","family":"Torralba","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1040-3260","authenticated-orcid":false,"given":"Sanja","family":"Fidler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6686-0589","authenticated-orcid":false,"given":"Xiaohui","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"key":"18_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":"18_CR2","doi-asserted-by":"crossref","unstructured":"Chan, E.R., et al.: Efficient geometry-aware 3D generative adversarial networks. In: arXiv (2021)","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"18_CR3","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. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"18_CR4","unstructured":"Chen, Y., Li, Z., Liu, P.: ET3D: efficient text-to-3d generation via multi-view distillation. arXiv 2311.15561 (2023)"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Objaverse-xl: a universe of 10m+ 3d objects (2023)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Objaverse: a universe of annotated 3d objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13142\u201313153 (2023)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"18_CR7","unstructured":"Gao, J., et al.: Get3d: a generative model of high quality 3D textured shapes learned from images. In: Advances in Neural Information Processing Systems (2022)"},{"key":"18_CR8","unstructured":"Guo, Y.C., et al.: threestudio: a unified framework for 3d content generation (2023). https:\/\/github.com\/threestudio-project\/threestudio"},{"key":"18_CR9","unstructured":"Gupta, A., Xiong, W., Nie, Y., Jones, I., O\u011fuz, B.: 3dgen: triplane latent diffusion for textured mesh generation. arXiv preprint arXiv:2303.05371 (2023)"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Henzler, P., Mitra, N.J., Ritschel, T.: Escaping plato\u2019s cave: 3d shape from adversarial rendering. In: The IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.01008"},{"key":"18_CR11","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Hunter, J.D.: Matplotlib: a 2D graphics environment. Comput. Sci. Eng. (2007)","DOI":"10.1109\/MCSE.2007.55"},{"key":"18_CR13","unstructured":"Jun, H., Nichol, A.: Shap-e: generating conditional 3d implicit functions. arXiv preprint arXiv:2305.02463 (2023)"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Laine, S., Hellsten, J., Karras, T., Seol, Y., Lehtinen, J., Aila, T.: Modular primitives for high-performance differentiable rendering. ACM Trans. Graph. 39(6) (2020)","DOI":"10.1145\/3414685.3417861"},{"key":"18_CR15","unstructured":"Li, J., et al.: Instant3d: fast text-to-3d with sparse-view generation and large reconstruction model. arXiv preprint arXiv:2311.06214 (2023)"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: Instant3d: instant text-to-3d generation. arXiv preprint arXiv:2311.08403 (2023)","DOI":"10.1007\/s11263-024-02193-6"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Lin, C.H., et al.: Magic3d: high-resolution text-to-3d content creation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"18_CR18","unstructured":"Liu, M., Xu, C., Jin, H., Chen, L., Xu, Z., Su, H., et\u00a0al.: One-2-3-45: any single image to 3d mesh in 45 seconds without per-shape optimization. arXiv preprint arXiv:2306.16928 (2023)"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Liu, R., Wu, R., Hoorick, B.V., Tokmakov, P., Zakharov, S., Vondrick, C.: Zero-1-to-3: zero-shot one image to 3d object (2023)","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Lorensen, W.E., Cline, H.E.: Marching cubes: a high resolution 3d surface construction algorithm. In: Seminal Graphics: Pioneering Efforts that Shaped the Field, pp. 347\u2013353 (1998)","DOI":"10.1145\/280811.281026"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Lorraine, J., et al.: Att3d: amortized text-to-3d object synthesis. In: Proceedings of the International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01645"},{"key":"18_CR22","unstructured":"Lunz, S., Li, Y., Fitzgibbon, A., Kushman, N.: Inverse graphics GAN: learning to generate 3d shapes from unstructured 2d data. arXiv preprint arXiv:2002.12674 (2020)"},{"key":"18_CR23","unstructured":"Luo, T., Rockwell, C., Lee, H., Johnson, J.: Scalable 3d captioning with pretrained models. arXiv preprint arXiv:2306.07279 (2023)"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Mescheder, L., Oechsle, M., Niemeyer, M., Nowozin, S., Geiger, A.: Occupancy networks: learning 3d reconstruction in function space. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4460\u20134470 (2019)","DOI":"10.1109\/CVPR.2019.00459"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Metzer, G., Richardson, E., Patashnik, O., Giryes, R., Cohen-Or, D.: Latent-nerf for shape-guided generation of 3d shapes and textures. arXiv preprint arXiv:2211.07600 (2022)","DOI":"10.1109\/CVPR52729.2023.01218"},{"key":"18_CR26","doi-asserted-by":"crossref","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. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Munkberg, J., et al.: Extracting triangular 3d models, materials, and lighting from images. In: CVPR, pp. 8280\u20138290 (2022)","DOI":"10.1109\/CVPR52688.2022.00810"},{"key":"18_CR28","unstructured":"Nash, C., Ganin, Y., Eslami, S.M.A., Battaglia, P.W.: Polygen: an autoregressive generative model of 3d meshes (2020)"},{"key":"18_CR29","unstructured":"Nichol, A., Jun, H., Dhariwal, P., Mishkin, P., Chen, M.: Point-e: a system for generating 3d point clouds from complex prompts. arXiv preprint arXiv:2212.08751 (2022)"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Oliphant, T.E.: Python for scientific computing. Comput. Sci. Eng. (2007)","DOI":"10.1109\/MCSE.2007.58"},{"key":"18_CR31","unstructured":"OpenAI: Gpt-4 technical report. ArXiv abs\/2303.08774 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257532815"},{"key":"18_CR32","unstructured":"Paszke, A., et al.: Automatic differentiation in PyTorch. Openreview (2017)"},{"key":"18_CR33","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: Dreamfusion: text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988 (2022)"},{"key":"18_CR34","unstructured":"Qian, G., et\u00a0al.: Atom: amortized text-to-mesh using 2d diffusion. arXiv preprint arXiv:2402.00867 (2024)"},{"key":"18_CR35","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":"18_CR36","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International Conference on Machine Learning, pp. 8821\u20138831. PMLR (2021)"},{"key":"18_CR37","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 (CVPR), pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"18_CR38","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. In: Advance in Neural Information Processing System, vol. 35, pp. 36479\u201336494 (2022)"},{"key":"18_CR39","unstructured":"Shen, T., Gao, J., Yin, K., Liu, M.Y., Fidler, S.: Deep marching tetrahedra: a hybrid representation for high-resolution 3d shape synthesis. In: Advances in Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"18_CR40","doi-asserted-by":"publisher","unstructured":"Shen, T., et al.: Flexible isosurface extraction for gradient-based mesh optimization. ACM Trans. Graph. 42(4) (2023). https:\/\/doi.org\/10.1145\/3592430","DOI":"10.1145\/3592430"},{"key":"18_CR41","unstructured":"Shi, R., et al.: Zero123++: a single image to consistent multi-view diffusion base model (2023)"},{"key":"18_CR42","unstructured":"Shi, Y., Wang, P., Ye, J., Mai, L., Li, K., Yang, X.: Mvdream: multi-view diffusion for 3d generation. arXiv:2308.16512 (2023)"},{"key":"18_CR43","doi-asserted-by":"crossref","unstructured":"Tang, J., Chen, Z., Chen, X., Wang, T., Zeng, G., Liu, Z.: Lgm: large multi-view gaussian model for high-resolution 3d content creation. arXiv preprint arXiv:2402.05054 (2024)","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"18_CR44","doi-asserted-by":"crossref","unstructured":"Tatarchenko, M., Dosovitskiy, A., Brox, T.: Octree generating networks: Efficient convolutional architectures for high-resolution 3d outputs. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2088\u20132096 (2017)","DOI":"10.1109\/ICCV.2017.230"},{"key":"18_CR45","unstructured":"Van\u00a0Rossum, G., Drake\u00a0Jr, F.L.: Python reference manual. Centrum voor Wiskunde en Informatica Amsterdam (1995)"},{"key":"18_CR46","doi-asserted-by":"crossref","unstructured":"Wang, H., Du, X., Li, J., Yeh, R.A., Shakhnarovich, G.: Score Jacobian chaining: lifting pretrained 2d diffusion models for 3d generation. arXiv preprint arXiv:2212.00774 (2022)","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"18_CR47","unstructured":"Wang, Z., et al.: Prolificdreamer: high-fidelity and diverse text-to-3d generation with variational score distillation. arXiv preprint arXiv:2305.16213 (2023)"},{"key":"18_CR48","unstructured":"Wu, J., Zhang, C., Xue, T., Freeman, B., Tenenbaum, J.: Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"18_CR49","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 (2019)","DOI":"10.1109\/ICCV.2019.00464"},{"key":"18_CR50","unstructured":"Yariv, L., Gu, J., Kasten, Y., Lipman, Y.: Volume rendering of neural implicit surfaces. In: Advances in Neural Information Processing Systems, vol. 34 (2021)"},{"key":"18_CR51","unstructured":"Zeng, X., et al.: Lion: latent point diffusion models for 3d shape generation. In: Advances in Neural Information Processing Systems (NeurIPS) (2022)"},{"key":"18_CR52","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"18_CR53","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\/978-3-031-72980-5_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:22:00Z","timestamp":1730107320000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72980-5_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031729799","9783031729805"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72980-5_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"29 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NVIDIA funded this work.Kevin Xie, Jonathan Lorraine, Tianshi Cao, Jun Gao, and Xiaohui Zeng had funding from student scholarships at the University of Toronto and the Vector Institute, which are not in direct support of this work.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Funding"}},{"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"}}]}}