{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T11:18:41Z","timestamp":1775128721259,"version":"3.50.1"},"publisher-location":"Cham","reference-count":63,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732348","type":"print"},{"value":"9783031732355","type":"electronic"}],"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\/978-3-031-73235-5_1","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T06:01:53Z","timestamp":1727589713000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":173,"title":["LGM: Large Multi-view Gaussian Model for\u00a0High-Resolution 3D Content Creation"],"prefix":"10.1007","author":[{"given":"Jiaxiang","family":"Tang","sequence":"first","affiliation":[]},{"given":"Zhaoxi","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Xiaokang","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Tengfei","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Gang","family":"Zeng","sequence":"additional","affiliation":[]},{"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"1_CR1","unstructured":"Cao, Z., Hong, F., Wu, T., Pan, L., Liu, Z.: Large-vocabulary 3D diffusion model with transformer. arXiv preprint arXiv:2309.07920 (2023)"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Chan, E.R., et al.: Efficient geometry-aware 3D generative adversarial networks. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Charatan, D., Li, S., Tagliasacchi, A., Sitzmann, V.: pixelSplat: 3D gaussian splats from image pairs for scalable generalizable 3D reconstruction. arXiv preprint arXiv:2312.12337 (2023)","DOI":"10.1109\/CVPR52733.2024.01840"},{"key":"1_CR4","unstructured":"Chen, G., Wang, W.: A survey on 3D gaussian splatting. arXiv preprint arXiv:2401.03890 (2024)"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Chen, H., et al.: Single-stage diffusion nerf: a unified approach to 3D generation and reconstruction. arXiv preprint arXiv:2304.06714 (2023)","DOI":"10.1109\/ICCV51070.2023.00229"},{"key":"1_CR6","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":"1_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Gaussianeditor: swift and controllable 3D editing with gaussian splatting. arXiv preprint arXiv:2311.14521 (2023)","DOI":"10.1109\/CVPR52733.2024.02029"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: IT3D: improved text-to-3D generation with explicit view synthesis. arXiv preprint arXiv:2308.11473 (2023)","DOI":"10.1609\/aaai.v38i2.27886"},{"key":"1_CR9","unstructured":"Chen, Z., Hong, F., Mei, H., Wang, G., Yang, L., Liu, Z.: Primdiffusion: volumetric primitives diffusion for 3D human generation. arXiv preprint arXiv:2312.04559 (2023)"},{"key":"1_CR10","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":"1_CR11","doi-asserted-by":"crossref","unstructured":"Deitke, M., et\u00a0al.: Objaverse-xl: a universe of 10m+ 3D objects. arXiv preprint arXiv:2307.05663 (2023)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Objaverse: a universe of annotated 3D objects. In: CVPR, pp. 13142\u201313153 (2023)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1_CR14","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS, vol. 33, pp. 6840\u20136851 (2020)"},{"key":"1_CR15","unstructured":"Hong, Y., et al.: LRM: large reconstruction model for single image to 3D. arXiv preprint arXiv:2311.04400 (2023)"},{"key":"1_CR16","unstructured":"Jun, H., Nichol, A.: Shap-e: generating conditional 3D implicit functions. arXiv preprint arXiv:2305.02463 (2023)"},{"issue":"4","key":"1_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592433","volume":"42","author":"B Kerbl","year":"2023","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D gaussian splatting for real-time radiance field rendering. ToG 42(4), 1\u201314 (2023)","journal-title":"ToG"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Laine, S., Hellsten, J., Karras, T., Seol, Y., Lehtinen, J., Aila, T.: Modular primitives for high-performance differentiable rendering. ToG 39(6) (2020)","DOI":"10.1145\/3414685.3417861"},{"key":"1_CR19","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":"1_CR20","unstructured":"Li, W., Chen, R., Chen, X., Tan, P.: Sweetdreamer: aligning geometric priors in 2D diffusion for consistent text-to-3D. arXiv preprint arXiv:2310.02596 (2023)"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Focaldreamer: text-driven 3D editing via focal-fusion assembly. arXiv preprint arXiv:2308.10608 (2023)","DOI":"10.1609\/aaai.v38i4.28113"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Lin, C.H., et al.: Magic3d: high-resolution text-to-3D content creation. In: CVPR, pp. 300\u2013309 (2023)","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Ling, H., Kim, S.W., Torralba, A., Fidler, S., Kreis, K.: Align your gaussians: text-to-4D with dynamic 3D gaussians and composed diffusion models. arXiv preprint arXiv:2312.13763 (2023)","DOI":"10.1109\/CVPR52733.2024.00819"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Liu, R., Wu, R., Van\u00a0Hoorick, B., Tokmakov, P., Zakharov, S., Vondrick, C.: Zero-1-to-3: zero-shot one image to 3D object. arXiv preprint arXiv:2303.11328 (2023)","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"1_CR25","unstructured":"Liu, Y., et al.: Syncdreamer: generating multiview-consistent images from a single-view image. arXiv preprint arXiv:2309.03453 (2023)"},{"key":"1_CR26","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":"1_CR27","doi-asserted-by":"crossref","unstructured":"Long, X., et\u00a0al.: Wonder3d: single image to 3D using cross-domain diffusion. arXiv preprint arXiv:2310.15008 (2023)","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"1_CR28","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":"1_CR29","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"1_CR30","unstructured":"Luo, T., Rockwell, C., Lee, H., Johnson, J.: Scalable 3D captioning with pretrained models. arXiv preprint arXiv:2306.07279 (2023)"},{"key":"1_CR31","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":"1_CR32","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":"1_CR33","doi-asserted-by":"crossref","unstructured":"M\u00fcller, N., Siddiqui, Y., Porzi, L., Bulo, S.R., Kontschieder, P., Nie\u00dfner, M.: Diffrf: rendering-guided 3D radiance field diffusion. In: CVPR, pp. 4328\u20134338 (2023)","DOI":"10.1109\/CVPR52729.2023.00421"},{"issue":"4","key":"1_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530127","volume":"41","author":"T M\u00fcller","year":"2022","unstructured":"M\u00fcller, T., Evans, A., Schied, C., Keller, A.: Instant neural graphics primitives with a multiresolution hash encoding. ACM TOG 41(4), 1\u201315 (2022)","journal-title":"ACM TOG"},{"key":"1_CR35","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":"1_CR36","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: Dreamfusion: text-to-3D using 2D diffusion. arXiv preprint arXiv:2209.14988 (2022)"},{"key":"1_CR37","unstructured":"Qian, G., et\u00a0al.: Magic123: one image to high-quality 3D object generation using both 2D and 3D diffusion priors. arXiv preprint arXiv:2306.17843 (2023)"},{"key":"1_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107404","volume":"106","author":"X Qin","year":"2020","unstructured":"Qin, X., Zhang, Z., Huang, C., Dehghan, M., Zaiane, O.R., Jagersand, M.: U2-net: going deeper with nested u-structure for salient object detection. Pattern Recogn. 106, 107404 (2020)","journal-title":"Pattern Recogn."},{"key":"1_CR39","unstructured":"Ren, J., Pan, L., Tang, J., Zhang, C., Cao, A., Zeng, G., Liu, Z.: Dreamgaussian4d: generative 4D gaussian splatting. arXiv preprint arXiv:2312.17142 (2023)"},{"key":"1_CR40","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"1_CR41","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":"1_CR42","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. In: NeurIPS, vol. 35, pp. 36479\u201336494 (2022)"},{"key":"1_CR43","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: NeurIPS (2021)"},{"key":"1_CR44","unstructured":"Shi, R., et al.: Zero123++: a single image to consistent multi-view diffusion base model (2023)"},{"key":"1_CR45","unstructured":"Shi, Y., Wang, P., Ye, J., Long, M., Li, K., Yang, X.: Mvdream: multi-view diffusion for 3D generation. arXiv preprint arXiv:2308.16512 (2023)"},{"key":"1_CR46","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"1_CR47","doi-asserted-by":"crossref","unstructured":"Szymanowicz, S., Rupprecht, C., Vedaldi, A.: Splatter image: ultra-fast single-view 3D reconstruction. arXiv (2023)","DOI":"10.1109\/CVPR52733.2024.00972"},{"key":"1_CR48","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":"1_CR49","doi-asserted-by":"crossref","unstructured":"Tang, J., et al.: Delicate textured mesh recovery from nerf via adaptive surface refinement. arXiv preprint arXiv:2303.02091 (2022)","DOI":"10.1109\/ICCV51070.2023.01626"},{"key":"1_CR50","doi-asserted-by":"crossref","unstructured":"Tsalicoglou, C., Manhardt, F., Tonioni, A., Niemeyer, M., Tombari, F.: Textmesh: generation of realistic 3d meshes from text prompts. arXiv preprint arXiv:2304.12439 (2023)","DOI":"10.1109\/3DV62453.2024.00154"},{"key":"1_CR51","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS, vol. 30 (2017)"},{"key":"1_CR52","unstructured":"Wang, P., Shi, Y.: Imagedream: image-prompt multi-view diffusion for 3D generation. arXiv preprint arXiv:2312.02201 (2023)"},{"key":"1_CR53","unstructured":"Wang, P., et al.: PF-LRM: pose-free large reconstruction model for joint pose and shape prediction. arXiv preprint arXiv:2311.12024 (2023)"},{"key":"1_CR54","doi-asserted-by":"crossref","unstructured":"Wang, T., et\u00a0al.: Rodin: a generative model for sculpting 3D digital avatars using diffusion. In: CVPR, pp. 4563\u20134573 (2023)","DOI":"10.1109\/CVPR52729.2023.00443"},{"key":"1_CR55","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":"1_CR56","unstructured":"Weng, Z., et al.: Single-view 3D human digitalization with large reconstruction models. arXiv preprint arXiv:2401.12175 (2024)"},{"key":"1_CR57","unstructured":"Xu, D., et al.: AGG: amortized generative 3D gaussians for single image to 3D. arXiv preprint arXiv:2401.04099 (2024)"},{"key":"1_CR58","unstructured":"Xu, Y., et\u00a0al.: Dmv3d: denoising multi-view diffusion using 3D large reconstruction model. arXiv preprint arXiv:2311.09217 (2023)"},{"key":"1_CR59","doi-asserted-by":"crossref","unstructured":"Yariv, L., Puny, O., Neverova, N., Gafni, O., Lipman, Y.: Mosaic-SDF for 3D generative models. arXiv preprint arXiv:2312.09222 (2023)","DOI":"10.1109\/CVPR52733.2024.00443"},{"key":"1_CR60","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":"1_CR61","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"1_CR62","unstructured":"Zhao, Z., et al.: Michelangelo: conditional 3D shape generation based on shape-image-text aligned latent representation. arXiv preprint arXiv:2306.17115 (2023)"},{"key":"1_CR63","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\/978-3-031-73235-5_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T21:15:48Z","timestamp":1732828548000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73235-5_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031732348","9783031732355"],"references-count":63,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73235-5_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"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"}}]}}