{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T23:10:25Z","timestamp":1743117025079,"version":"3.40.3"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031820205"},{"type":"electronic","value":"9783031820212"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-82021-2_14","type":"book-chapter","created":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T09:45:37Z","timestamp":1740822337000},"page":"199-210","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Survey on\u00a0Multi-person 3D Reconstruction from\u00a0Monocular View"],"prefix":"10.1007","author":[{"given":"Jingyao","family":"Cai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boyuan","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingjie","family":"Xi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaosong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,3,1]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Zanfir, A., Marinoiu, E., Sminchisescu, C.: Monocular 3D pose and shape estimation of multiple people in natural scenes-the importance of multiple scene constraints. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2148\u20132157 (2018)","DOI":"10.1109\/CVPR.2018.00229"},{"key":"14_CR2","unstructured":"Zanfir, A., Marinoiu, E., Zanfir, M., et al.: Deep network for the integrated 3D sensing of multiple people in natural images. In: Advances in Neural Information Processing Systems, pp. 31 (2018)"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Jiang, W., Kolotouros, N., Pavlakos, G., et al.: Coherent reconstruction of multiple humans from a single image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5579\u20135588 (2020)","DOI":"10.1109\/CVPR42600.2020.00562"},{"key":"14_CR4","unstructured":"Rajasegaran, J., Pavlakos, G., Kanazawa, A., et al.: Tracking people with 3D representations. arXiv preprint arXiv:2111.07868 (2021)"},{"key":"14_CR5","first-page":"19385","volume":"34","author":"M Fieraru","year":"2021","unstructured":"Fieraru, M., Zanfir, M., Szente, T., et al.: REMIPS: physically consistent 3D reconstruction of multiple interacting people under weak supervision. Adv. Neural. Inf. Process. Syst. 34, 19385\u201319397 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Ugrinovic, N., Ruiz, A., Agudo, A., et al.: Body size and depth disambiguation in multi-person reconstruction from single images. In: 2021 International Conference on 3D Vision (3DV). IEEE, pp. 53\u201363 (2021)","DOI":"10.1109\/3DV53792.2021.00016"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Sun, Y., Bao, Q., Liu, W., et al.: Monocular, one-stage, regression of multiple 3D people. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11179\u201311188 (2021)","DOI":"10.1109\/ICCV48922.2021.01099"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Zhang, J., Yu, D., et al.: Body meshes as points. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 546\u2013556 (2021)","DOI":"10.1109\/CVPR46437.2021.00061"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Mustafa, A., Caliskan, A., Agapito, L., et al.: Multi-person implicit reconstruction from a single image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14474\u201314483 (2021)","DOI":"10.1109\/CVPR46437.2021.01424"},{"key":"14_CR10","doi-asserted-by":"publisher","first-page":"4679","DOI":"10.1109\/TIP.2022.3187294","volume":"31","author":"B Huang","year":"2022","unstructured":"Huang, B., Zhang, T., Wang, Y.: Pose2UV: single-shot multiperson mesh recovery with deep UV prior. IEEE Trans. Image Process. 31, 4679\u20134692 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Iqbal, U., Molchanov, P., et al.: GLAMR: Global occlusion-aware human mesh recovery with dynamic cameras. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11038\u201311049 (2022)","DOI":"10.1109\/CVPR52688.2022.01076"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Khirodkar, R., Tripathi, S., Kitani, K.: Occluded human mesh recovery. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1715\u20131725 (2022)","DOI":"10.1109\/CVPR52688.2022.00176"},{"key":"14_CR13","doi-asserted-by":"publisher","unstructured":"Cha, J., Saqlain, M., Kim, G.U., et al.: Multi-person 3D pose and shape estimation via inverse kinematics and refinement. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision, pp. 660-677. Springer Nature Switzerland, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20065-6_38","DOI":"10.1007\/978-3-031-20065-6_38"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Sun, Y., Liu, W., Bao, Q., et al.: Putting people in their place: monocular regression of 3D people in depth. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13243\u201313252 (2022)","DOI":"10.1109\/CVPR52688.2022.01289"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Choi, H., Moon, G., Park, J.K., et al.: Learning to estimate robust 3D human mesh from in-the-wild crowded scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1475\u20131484 (2022)","DOI":"10.1109\/CVPR52688.2022.00153"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Goel, S., Pavlakos, G., Rajasegaran, J., et al.: Humans in 4D: reconstructing and tracking humans with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14783\u201314794 (2023)","DOI":"10.1109\/ICCV51070.2023.01358"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yang, Q., Wang, J., et al.: PSVT: End-to-end multi-person 3D pose and shape estimation with progressive video transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21254\u201321263 (2023)","DOI":"10.1109\/CVPR52729.2023.02036"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Wen, H., Huang, J., Cui, H., et al.: Crowd3D: towards hundreds of people reconstruction from a single image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8937\u20138946 (2023)","DOI":"10.1109\/CVPR52729.2023.00863"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Ionescu, C., Papava, D., Olaru, V., et al.: Human3.6M: large scale datasets and predictive methods for 3D human sensing in natural environments. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1325\u20131339 (2013)","DOI":"10.1109\/TPAMI.2013.248"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Joo, H., Liu, H., Tan, L., et al.: Panoptic studio: a massively multiview system for social motion capture. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 3334\u20133342 (2015)","DOI":"10.1109\/ICCV.2015.381"},{"key":"14_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Mehta, D., Sotnychenko, O., Mueller, F., et al.: Single-shot multi-person 3D pose estimation from monocular RGB. In: 2018 International Conference on 3D Vision (3DV). IEEE, pp. 120\u2013130 (2018)","DOI":"10.1109\/3DV.2018.00024"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Mehta, D., Rhodin, H., Casas, D., et al.: Monocular 3D human pose estimation in the wild using improved CNN supervision. In: 2017 International Conference on 3D Vision (3DV). IEEE, pp. 506\u2013516 (2017)","DOI":"10.1109\/3DV.2017.00064"},{"key":"14_CR24","unstructured":"Johnson S, Everingham M. Clustered pose and nonlinear appearance models for human pose estimation. In: BMVC, vol. 2, no. 4, pp. 5 (2010)"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Johnson, S., Everingham, M.: Learning effective human pose estimation from inaccurate annotation. In: CVPR. IEEE, vol. 2011, pp. 1465\u20131472 (2011)","DOI":"10.1109\/CVPR.2011.5995318"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Iqbal, U., Insafutdinov, E., et al.: PoseTrack: a benchmark for human pose estimation and tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5167\u20135176 (2018)","DOI":"10.1109\/CVPR.2018.00542"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Pishchulin, L., Gehler, P., et al.: 2D human pose estimation: new benchmark and state of the art analysis. In: Proceedings of the IEEE Conference on computer Vision and Pattern Recognition, pp. 3686\u20133693 (2014)","DOI":"10.1109\/CVPR.2014.471"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Li, J., Wang, C., Zhu, H., et al.: CrowdPose: efficient crowded scenes pose estimation and a new benchmark. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10863\u201310872 (2019)","DOI":"10.1109\/CVPR.2019.01112"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Patel, P., Huang, C.H.P., Tesch, J., et al.: AGORA: avatars in geography optimized for regression analysis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13468\u201313478 (2021)","DOI":"10.1109\/CVPR46437.2021.01326"},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Von Marcard, T., Henschel, R., Black, M.J., et al.: Recovering accurate 3d human pose in the wild using IMUS and a moving camera. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 601\u2013617 (2018)","DOI":"10.1007\/978-3-030-01249-6_37"},{"issue":"8","key":"14_CR31","doi-asserted-by":"publisher","first-page":"806","DOI":"10.3390\/e22080806","volume":"22","author":"SH Kim","year":"2020","unstructured":"Kim, S.H., Chang, J.Y.: Single-shot 3D multi-person shape reconstruction from a single RGB image. Entropy 22(8), 806 (2020)","journal-title":"Entropy"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Baradel, F., Armando, M., Galaaoui, S., et al.: Multi-HMR: multi-person whole-body human mesh recovery in a single shot. arXiv preprint arXiv:2402.14654 (2024)","DOI":"10.1007\/978-3-031-73337-6_12"},{"key":"14_CR33","doi-asserted-by":"crossref","unstructured":"Gu, C., Sun, C., Ross, D.A., et al.: AVA: a video dataset of spatio-temporally localized atomic visual actions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6047\u20136056 (2018)","DOI":"10.1109\/CVPR.2018.00633"},{"key":"14_CR34","doi-asserted-by":"crossref","unstructured":"Fieraru, M., Zanfir, M., Oneata, E., et al.: Learning complex 3D human self-contact. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 2, pp. 1343\u20131351 (2021)","DOI":"10.1609\/aaai.v35i2.16223"},{"key":"14_CR35","doi-asserted-by":"crossref","unstructured":"Fieraru, M., Zanfir, M., Oneata, E., et al.: Three-dimensional reconstruction of human interactions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7214\u20137223 (2020)","DOI":"10.1109\/CVPR42600.2020.00724"},{"key":"14_CR36","doi-asserted-by":"crossref","unstructured":"Mahmood, N., Ghorbani, N., Troje, N.F., et al.: AMASS: archive of motion capture as surface shapes. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5442\u20135451 (2019:)","DOI":"10.1109\/ICCV.2019.00554"},{"key":"14_CR37","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Choutas, V., Ghorbani, N., et al.: Expressive body capture: 3D hands, face, and body from a single image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10975\u201310985 (2019)","DOI":"10.1109\/CVPR.2019.01123"},{"key":"14_CR38","doi-asserted-by":"crossref","unstructured":"Lin, J., Zeng, A., Wang, H., et al.: One-stage 3D whole-body mesh recovery with component aware transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21159\u201321168 (2023)","DOI":"10.1109\/CVPR52729.2023.02027"},{"key":"14_CR39","doi-asserted-by":"crossref","unstructured":"Black, M.J., Patel, P., Tesch, J., et al.: BEDLAM: a synthetic dataset of bodies exhibiting detailed lifelike animated motion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8726\u20138737 (2023)","DOI":"10.1109\/CVPR52729.2023.00843"}],"container-title":["Lecture Notes in Computer Science","Advances in Computer Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-82021-2_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T09:45:53Z","timestamp":1740822353000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-82021-2_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031820205","9783031820212"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-82021-2_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"1 March 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CGI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Computer Graphics International Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Geneva","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","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":"1 July 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 July 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"41","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cgi2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.cgs-network.org\/cgi24\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}