{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T06:29:23Z","timestamp":1776407363138,"version":"3.51.2"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729393","type":"print"},{"value":"9783031729409","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,17]],"date-time":"2024-11-17T00:00:00Z","timestamp":1731801600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,17]],"date-time":"2024-11-17T00:00:00Z","timestamp":1731801600000},"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\/978-3-031-72940-9_2","type":"book-chapter","created":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T20:42:10Z","timestamp":1731789730000},"page":"19-35","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":32,"title":["Expressive Whole-Body 3D Gaussian Avatar"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0610-7936","authenticated-orcid":false,"given":"Gyeongsik","family":"Moon","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1012-415X","authenticated-orcid":false,"given":"Takaaki","family":"Shiratori","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2053-3472","authenticated-orcid":false,"given":"Shunsuke","family":"Saito","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,17]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Alldieck, T., Magnor, M., Xu, W., Theobalt, C., Pons-Moll, G.: Video based reconstruction of 3D people models. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00875"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Alldieck, T., Xu, H., Sminchisescu, C.: imGHUM: implicit generative models of 3D human shape and articulated pose. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00541"},{"key":"2_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3450626.3459850","volume":"40","author":"T Bagautdinov","year":"2021","unstructured":"Bagautdinov, T., et al.: Driving-signal aware full-body avatars. ACM TOG 40, 1\u201317 (2021)","journal-title":"ACM TOG"},{"key":"2_CR4","unstructured":"Cai, Z., et\u00a0al.: SMPLer-X: scaling up expressive human pose and shape estimation. In: NeurIPS (2023)"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Chan, E.R., et\u00a0al.: Efficient geometry-aware 3D generative adversarial networks. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"2_CR6","unstructured":"Chen, J., et al.: Animatable neural radiance fields from monocular RGB videos. arXiv preprint arXiv:2106.13629 (2021)"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: URhand: universal relightable hands. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00020"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Choi, H., Moon, G., Armando, M., Leroy, V., Lee, K.M., Rogez, G.: MonoNHR: monocular neural human renderer. In: 3DV (2022)","DOI":"10.1109\/3DV57658.2022.00036"},{"key":"2_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/978-3-030-58607-2_2","volume-title":"Computer Vision \u2013 ECCV 2020","author":"V Choutas","year":"2020","unstructured":"Choutas, V., Pavlakos, G., Bolkart, T., Tzionas, D., Black, M.J.: Monocular expressive body regression through body-driven attention. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12355, pp. 20\u201340. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58607-2_2"},{"key":"2_CR10","unstructured":"Contributors, M.: Openmmlab pose estimation toolbox and benchmark (2020). https:\/\/github.com\/open-mmlab\/mmpose"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Feng, Y., Choutas, V., Bolkart, T., Tzionas, D., Black, M.J.: Collaborative regression of expressive bodies using moderation. In: 3DV (2021)","DOI":"10.1109\/3DV53792.2021.00088"},{"key":"2_CR12","first-page":"1","volume":"40","author":"Y Feng","year":"2021","unstructured":"Feng, Y., Feng, H., Black, M.J., Bolkart, T.: Learning an animatable detailed 3D face model from in-the-wild images. ACM TOG 40, 1\u201313 (2021)","journal-title":"ACM TOG"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Guo, C., Jiang, T., Chen, X., Song, J., Hilliges, O.: Vid2Avatar: 3D avatar reconstruction from videos in the wild via self-supervised scene decomposition. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01236"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Hu, L., et al.: GaussianAvatar: towards realistic human avatar modeling from a single video via animatable 3D Gaussians. arXiv preprint arXiv:2312.02134 (2023)","DOI":"10.1109\/CVPR52733.2024.00067"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Jiang, T., Chen, X., Song, J., Hilliges, O.: InstantAvatar: learning avatars from monocular video in 60 seconds. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01623"},{"key":"2_CR17","doi-asserted-by":"publisher","unstructured":"Jiang, W., Yi, K.M., Samei, G., Tuzel, O., Ranjan, A.: NeuMan: neural human radiance field from a single video. In: Avidan, S., Brostow, G., Cisse, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13692, pp. 402\u2013418. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19824-3_24","DOI":"10.1007\/978-3-031-19824-3_24"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Joo, H., Simon, T., Sheikh, Y.: Total capture: a 3D deformation model for tracking faces, hands, and bodies. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00868"},{"issue":"4","key":"2_CR19","doi-asserted-by":"publisher","first-page":"139-1","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. ACM TOG 42(4), 139\u20131 (2023)","journal-title":"ACM TOG"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Chang, J.H.R., Gabriel, J., Tuzel, O., Ranjan, A.: HUGS: human Gaussian splats. arXiv preprint arXiv:2311.17910 (2023)","DOI":"10.1109\/CVPR52733.2024.00055"},{"key":"2_CR21","unstructured":"Kwon, Y., Kim, D., Ceylan, D., Fuchs, H.: Neural human performer: learning generalizable radiance fields for human performance rendering. In: NeurIPS (2021)"},{"key":"2_CR22","unstructured":"Li, J., Bian, S., Xu, C., Chen, Z., Yang, L., Lu, C.: HybrIK-X: hybrid analytical-neural inverse kinematics for whole-body mesh recovery. arXiv preprint arXiv:2304.05690 (2023)"},{"key":"2_CR23","first-page":"1","volume":"36","author":"T Li","year":"2017","unstructured":"Li, T., Bolkart, T., Black, M.J., Li, H., Romero, J.: Learning a model of facial shape and expression from 4D scans. ACM TOG 36, 1\u201317 (2017)","journal-title":"ACM TOG"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Lin, J., Zeng, A., Wang, H., Zhang, L., Li, Y.: One-stage 3D whole-body mesh recovery with component aware transformer. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02027"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Liu, S., Li, T., Chen, W., Li, H.: Soft rasterizer: a differentiable renderer for image-based 3D reasoning. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00780"},{"key":"2_CR26","unstructured":"Liu, X., et al.: GEA: reconstructing expressive 3D Gaussian avatar from monocular video. arXiv preprint arXiv:2402.16607 (2024)"},{"key":"2_CR27","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. Commun. ACM (2021)","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Moon, G., Choi, H., Lee, K.M.: Accurate 3D hand pose estimation for whole-body 3D human mesh estimation. In: CVPRW (2022)","DOI":"10.1109\/CVPRW56347.2022.00257"},{"key":"2_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"440","DOI":"10.1007\/978-3-030-58536-5_26","volume-title":"Computer Vision \u2013 ECCV 2020","author":"G Moon","year":"2020","unstructured":"Moon, G., Shiratori, T., Lee, K.M.: DeepHandMesh: a weakly-supervised deep encoder-decoder framework for high-fidelity hand mesh modeling. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 440\u2013455. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_26"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Moon, G., Xu, W., Joshi, R., Wu, C., Shiratori, T.: Authentic hand avatar from a phone scan via universal hand model. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00198"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Patel, P., Huang, C.H.P., Tesch, J., Hoffmann, D.T., Tripathi, S., Black, M.J.: AGORA: avatars in geography optimized for regression analysis. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01326"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., et al.: Expressive body capture: 3D hands, face, and body from a single image. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01123"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Peng, S., et al.: Animatable neural radiance fields for modeling dynamic human bodies. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01405"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Peng, S., et al.: Neural body: implicit neural representations with structured latent codes for novel view synthesis of dynamic humans. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00894"},{"key":"2_CR35","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: DreamFusion: text-to-3D using 2D diffusion. In: ICLR (2023)"},{"key":"2_CR36","doi-asserted-by":"crossref","unstructured":"Qian, Z., Wang, S., Mihajlovic, M., Geiger, A., Tang, S.: 3DGS-avatar: animatable avatars via deformable 3D Gaussian splatting. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00480"},{"key":"2_CR37","unstructured":"Ravi, N., et al.: Accelerating 3D deep learning with PyTorch3D. arXiv preprint arXiv:2007.08501 (2020)"},{"key":"2_CR38","doi-asserted-by":"crossref","unstructured":"Remelli, E., et\u00a0al.: Drivable volumetric avatars using texel-aligned features. In: ACM SIGGRAPH Conference Proceedings (2022)","DOI":"10.1145\/3528233.3530740"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Rong, Y., Shiratori, T., Joo, H.: FrankMocap: a monocular 3D whole-body pose estimation system via regression and integration. In: ICCVW (2021)","DOI":"10.1109\/ICCVW54120.2021.00201"},{"key":"2_CR40","doi-asserted-by":"crossref","unstructured":"Saito, S., Huang, Z., Natsume, R., Morishima, S., Kanazawa, A., Li, H.: PIFu: pixel-aligned implicit function for high-resolution clothed human digitization. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00239"},{"key":"2_CR41","doi-asserted-by":"crossref","unstructured":"Shen, K., et al.: X-Avatar: expressive human avatars. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01622"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Weng, C.Y., Curless, B., Srinivasan, P.P., Barron, J.T., Kemelmacher-Shlizerman, I.: HumanNeRF: free-viewpoint rendering of moving people from monocular video. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01573"},{"key":"2_CR43","doi-asserted-by":"crossref","unstructured":"Xu, H., Bazavan, E.G., Zanfir, A., Freeman, W.T., Sukthankar, R., Sminchisescu, C.: GHUM & GHUML: generative 3D human shape and articulated pose models. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00622"},{"issue":"10","key":"2_CR44","doi-asserted-by":"publisher","first-page":"12287","DOI":"10.1109\/TPAMI.2023.3271691","volume":"45","author":"H Zhang","year":"2023","unstructured":"Zhang, H., et al.: PyMAF-X: towards well-aligned full-body model regression from monocular images. TPAMI 45(10), 12287\u201312303 (2023)","journal-title":"TPAMI"},{"key":"2_CR45","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"}],"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\/978-3-031-72940-9_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T21:31:35Z","timestamp":1731792695000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72940-9_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,17]]},"ISBN":["9783031729393","9783031729409"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72940-9_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,17]]},"assertion":[{"value":"17 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"}}]}}