{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T04:27:08Z","timestamp":1765254428373,"version":"3.40.3"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031726484"},{"type":"electronic","value":"9783031726491"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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\/978-3-031-72649-1_16","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:01:50Z","timestamp":1727593310000},"page":"276-292","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Compress3D: A\u00a0Compressed Latent Space for\u00a03D Generation from\u00a0a\u00a0Single Image"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7919-1748","authenticated-orcid":false,"given":"Bowen","family":"Zhang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9674-5220","authenticated-orcid":false,"given":"Tianyu","family":"Yang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1865-8276","authenticated-orcid":false,"given":"Yu","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6926-0538","authenticated-orcid":false,"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3993-9870","authenticated-orcid":false,"given":"Xi","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"16_CR1","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":"16_CR2","doi-asserted-by":"crossref","unstructured":"Cheng, Y.C., Lee, H.Y., Tulyakov, S., Schwing, A.G., Gui, L.Y.: Sdfusion: multimodal 3d shape completion, reconstruction, and generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4456\u20134465 (2023)","DOI":"10.1109\/CVPR52729.2023.00433"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Deitke, M., et\u00a0al.: Objaverse-xl: a universe of 10m+ 3d objects. Adv. Neural Inf. Process. Syst. 36 (2024)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"16_CR4","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, pp. 13142\u201313153 (2023)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"16_CR5","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":"16_CR6","unstructured":"He, Z., Wang, T.: Openlrm: open-source large reconstruction models (2023). https:\/\/github.com\/3DTopia\/OpenLRM"},{"key":"16_CR7","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."},{"key":"16_CR8","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"16_CR9","unstructured":"Hong, Y., et al.: Lrm: large reconstruction model for single image to 3d. arXiv preprint arXiv:2311.04400 (2023)"},{"key":"16_CR10","unstructured":"Jun, H., Nichol, A.: Shap-e: generating conditional 3d implicit functions. arXiv preprint arXiv:2305.02463 (2023)"},{"key":"16_CR11","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":"16_CR12","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":"16_CR13","doi-asserted-by":"crossref","unstructured":"Li, M., Duan, Y., Zhou, J., Lu, J.: Diffusion-sdf: text-to-shape via voxelized diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12642\u201312651 (2023)","DOI":"10.1109\/CVPR52729.2023.01216"},{"issue":"4","key":"16_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3450626.3459852","volume":"40","author":"R Li","year":"2021","unstructured":"Li, R., Li, X., Hui, K.H., Fu, C.W.: Sp-gan: sphere-guided 3d shape generation and manipulation. ACM Trans. Graph. (TOG) 40(4), 1\u201312 (2021)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Li, S., et al.: Instant-3d: instant neural radiance field training towards on-device ar\/vr 3d reconstruction. In: Proceedings of the 50th Annual International Symposium on Computer Architecture, pp. 1\u201313 (2023)","DOI":"10.1145\/3579371.3589115"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Lin, C.H., et al.: Magic3d: high-resolution text-to-3d content creation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 300\u2013309 (2023)","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"16_CR17","unstructured":"Liu, M., et al.: Openshape: scaling up 3d shape representation towards open-world understanding. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"16_CR18","unstructured":"Liu, M., et al.: One-2-3-45: any single image to 3d mesh in 45 seconds without per-shape optimization. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Liu, R., et al.: Zero-1-to-3: zero-shot one image to 3d object. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9298\u20139309 (2023)","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"16_CR20","unstructured":"Liu, Z., Feng, Y., Black, M.J., Nowrouzezahrai, D., Paull, L., Liu, W.: Meshdiffusion: score-based generative 3d mesh modeling. arXiv preprint arXiv:2303.08133 (2023)"},{"key":"16_CR21","unstructured":"Mercier, A., et al.: Hexagen3d: stablediffusion is just one step away from fast and diverse text-to-3d generation. arXiv preprint arXiv:2401.07727 (2024)"},{"issue":"1","key":"16_CR22","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":"16_CR23","doi-asserted-by":"crossref","unstructured":"Mittal, P., Cheng, Y.C., Singh, M., Tulsiani, S.: Autosdf: shape priors for 3d completion, reconstruction and generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 306\u2013315 (2022)","DOI":"10.1109\/CVPR52688.2022.00040"},{"key":"16_CR24","unstructured":"Nash, C., Ganin, Y., Eslami, S.A., Battaglia, P.: Polygen: an autoregressive generative model of 3d meshes. In: International Conference on Machine Learning, pp. 7220\u20137229. PMLR (2020)"},{"key":"16_CR25","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":"16_CR26","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: Dreamfusion: text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988 (2022)"},{"key":"16_CR27","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":"16_CR28","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":"16_CR29","unstructured":"Schaefer, S., Warren, J.: Dual marching cubes: primal contouring of dual grids. In: 12th Pacific Conference on Computer Graphics and Applications, 2004. PG 2004. Proceedings, pp. 70\u201376. IEEE (2004)"},{"key":"16_CR30","first-page":"25278","volume":"35","author":"C Schuhmann","year":"2022","unstructured":"Schuhmann, C., et al.: Laion-5b: an open large-scale dataset for training next generation image-text models. Adv. Neural. Inf. Process. Syst. 35, 25278\u201325294 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR31","first-page":"6087","volume":"34","author":"T Shen","year":"2021","unstructured":"Shen, T., Gao, J., Yin, K., Liu, M.Y., Fidler, S.: Deep marching tetrahedra: a hybrid representation for high-resolution 3d shape synthesis. Adv. Neural. Inf. Process. Syst. 34, 6087\u20136101 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"4","key":"16_CR32","first-page":"1","volume":"42","author":"T Shen","year":"2023","unstructured":"Shen, T., et al.: Flexible isosurface extraction for gradient-based mesh optimization. ACM Trans. Graph. (TOG) 42(4), 1\u201316 (2023)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Shim, J., Kang, C., Joo, K.: Diffusion-based signed distance fields for 3d shape generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20887\u201320897 (2023)","DOI":"10.1109\/CVPR52729.2023.02001"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Shue, J.R., Chan, E.R., Po, R., Ankner, Z., Wu, J., Wetzstein, G.: 3d neural field generation using triplane diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20875\u201320886 (2023)","DOI":"10.1109\/CVPR52729.2023.02000"},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Siddiqui, Y., et al.: Meshgpt: generating triangle meshes with decoder-only transformers. arXiv preprint arXiv:2311.15475 (2023)","DOI":"10.1109\/CVPR52733.2024.01855"},{"key":"16_CR36","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"16_CR37","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":"16_CR38","unstructured":"Tang, J., Ren, J., Zhou, H., Liu, Z., Zeng, G.: Dreamgaussian: generative gaussian splatting for efficient 3d content creation. arXiv preprint arXiv:2309.16653 (2023)"},{"key":"16_CR39","doi-asserted-by":"crossref","unstructured":"Tang, J., et al.: Make-it-3d: high-fidelity 3d creation from a single image with diffusion prior. arXiv preprint arXiv:2303.14184 (2023)","DOI":"10.1109\/ICCV51070.2023.02086"},{"key":"16_CR40","doi-asserted-by":"crossref","unstructured":"Wang, T., et\u00a0al.: Rodin: a generative model for sculpting 3d digital avatars using diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4563\u20134573 (2023)","DOI":"10.1109\/CVPR52729.2023.00443"},{"key":"16_CR41","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":"16_CR42","unstructured":"Yi, T., et al.: Gaussiandreamer: fast generation from text to 3d gaussian splatting with point cloud priors. arXiv preprint arXiv:2310.08529 (2023)"},{"key":"16_CR43","unstructured":"Zeng, X., et al.: Lion: latent point diffusion models for 3d shape generation. arXiv preprint arXiv:2210.06978 (2022)"},{"key":"16_CR44","first-page":"21871","volume":"35","author":"B Zhang","year":"2022","unstructured":"Zhang, B., Nie\u00dfner, M., Wonka, P.: 3dilg: irregular latent grids for 3d generative modeling. Adv. Neural. Inf. Process. Syst. 35, 21871\u201321885 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, B., Tang, J., Niessner, M., Wonka, P.: 3dshape2vecset: a 3d shape representation for neural fields and generative diffusion models. arXiv preprint arXiv:2301.11445 (2023)","DOI":"10.1145\/3592442"},{"key":"16_CR46","doi-asserted-by":"crossref","unstructured":"Zou, Z.X., et al.: Triplane meets gaussian splatting: fast and generalizable single-view 3d reconstruction with transformers. arXiv preprint arXiv:2312.09147 (2023)","DOI":"10.1109\/CVPR52733.2024.00983"}],"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\/978-3-031-72649-1_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T21:19:09Z","timestamp":1732828749000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72649-1_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031726484","9783031726491"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72649-1_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 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"}}]}}