{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T16:09:34Z","timestamp":1742918974382,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819611508"},{"type":"electronic","value":"9789819611515"}],"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\/978-981-96-1151-5_17","type":"book-chapter","created":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T16:01:30Z","timestamp":1738857690000},"page":"167-176","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Review of\u00a0Human Mesh Reconstruction: Beyond 2D Video Object Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1137-0720","authenticated-orcid":false,"given":"Peng","family":"Wu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6238-8403","authenticated-orcid":false,"given":"Zhicheng","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8796-2680","authenticated-orcid":false,"given":"Feiyu","family":"Pan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0549-7315","authenticated-orcid":false,"given":"Fangkai","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1405-6685","authenticated-orcid":false,"given":"Hao","family":"Hu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9543-6960","authenticated-orcid":false,"given":"Xiankai","family":"Lu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3497-6939","authenticated-orcid":false,"given":"Yiyou","family":"Guo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,2,7]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Choi, H., Moon, G., Chang, J.Y., Lee, K.M.: Beyond static features for temporally consistent 3d human pose and shape from a video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1964\u20131973 (2021)","key":"17_CR1","DOI":"10.1109\/CVPR46437.2021.00200"},{"key":"17_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"769","DOI":"10.1007\/978-3-030-58571-6_45","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Choi","year":"2020","unstructured":"Choi, H., Moon, G., Lee, K.M.: Pose2Mesh: graph convolutional network for 3D human pose and mesh recovery from a 2D human pose. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 769\u2013787. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58571-6_45"},{"unstructured":"Doersch, C., Zisserman, A.: Sim2real transfer learning for 3d human pose estimation: motion to the rescue. Adv. Neural Inf. Process. Syst. 32 (2019)","key":"17_CR3"},{"doi-asserted-by":"crossref","unstructured":"Dwivedi, S.K., Athanasiou, N., Kocabas, M., Black, M.J.: Learning to regress bodies from images using differentiable semantic rendering. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11250\u201311259 (2021)","key":"17_CR4","DOI":"10.1109\/ICCV48922.2021.01106"},{"issue":"4","key":"17_CR5","doi-asserted-by":"publisher","first-page":"5070","DOI":"10.1109\/TPAMI.2022.3194167","volume":"45","author":"S Guan","year":"2022","unstructured":"Guan, S., Xu, J., He, M.Z., Wang, Y., Ni, B., Yang, X.: Out-of-domain human mesh reconstruction via dynamic bilevel online adaptation. IEEE Trans. Pattern Anal. Mach. Intell. 45(4), 5070\u20135086 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"doi-asserted-by":"crossref","unstructured":"Guan, S., Xu, J., Wang, Y., Ni, B., Yang, X.: Bilevel online adaptation for out-of-domain human mesh reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10472\u201310481 (2021)","key":"17_CR6","DOI":"10.1109\/CVPR46437.2021.01033"},{"doi-asserted-by":"crossref","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: 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)","key":"17_CR7","DOI":"10.1109\/TPAMI.2013.248"},{"doi-asserted-by":"crossref","unstructured":"Joo, H., Neverova, N., Vedaldi, A.: Exemplar fine-tuning for 3d human model fitting towards in-the-wild 3d human pose estimation. In: 2021 International Conference on 3D Vision (3DV), pp. 42\u201352. IEEE (2021)","key":"17_CR8","DOI":"10.1109\/3DV53792.2021.00015"},{"doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Black, M.J., Jacobs, D.W., Malik, J.: End-to-end recovery of human shape and pose. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7122\u20137131 (2018)","key":"17_CR9","DOI":"10.1109\/CVPR.2018.00744"},{"doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Zhang, J.Y., Felsen, P., Malik, J.: Learning 3d human dynamics from video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5614\u20135623 (2019)","key":"17_CR10","DOI":"10.1109\/CVPR.2019.00576"},{"unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)","key":"17_CR11"},{"doi-asserted-by":"crossref","unstructured":"Kocabas, M., Athanasiou, N., Black, M.J.: Vibe: video inference for human body pose and shape estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5253\u20135263 (2020)","key":"17_CR12","DOI":"10.1109\/CVPR42600.2020.00530"},{"doi-asserted-by":"crossref","unstructured":"Kolotouros, N., Pavlakos, G., Black, M.J., Daniilidis, K.: Learning to reconstruct 3d human pose and shape via model-fitting in the loop. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2252\u20132261 (2019)","key":"17_CR13","DOI":"10.1109\/ICCV.2019.00234"},{"doi-asserted-by":"crossref","unstructured":"Kolotouros, N., Pavlakos, G., Daniilidis, K.: Convolutional mesh regression for single-image human shape reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4501\u20134510 (2019)","key":"17_CR14","DOI":"10.1109\/CVPR.2019.00463"},{"doi-asserted-by":"crossref","unstructured":"Kolotouros, N., Pavlakos, G., Jayaraman, D., Daniilidis, K.: Probabilistic modeling for human mesh recovery. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11605\u201311614 (2021)","key":"17_CR15","DOI":"10.1109\/ICCV48922.2021.01140"},{"doi-asserted-by":"crossref","unstructured":"Lee, G.H., Lee, S.W.: Uncertainty-aware human mesh recovery from video by learning part-based 3d dynamics. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12375\u201312384 (2021)","key":"17_CR16","DOI":"10.1109\/ICCV48922.2021.01215"},{"doi-asserted-by":"crossref","unstructured":"Lin, K., Wang, L., Liu, Z.: End-to-end human pose and mesh reconstruction with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1954\u20131963 (2021)","key":"17_CR17","DOI":"10.1109\/CVPR46437.2021.00199"},{"doi-asserted-by":"crossref","unstructured":"Lin, K., Wang, L., Liu, Z.: Mesh graphormer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12939\u201312948 (2021)","key":"17_CR18","DOI":"10.1109\/ICCV48922.2021.01270"},{"doi-asserted-by":"crossref","unstructured":"Mehta, D., et al.: Monocular 3d human pose estimation in the wild using improved cnn supervision. In: 2017 International Conference on 3D Vision (3DV), pp. 506\u2013516. IEEE (2017)","key":"17_CR19","DOI":"10.1109\/3DV.2017.00064"},{"key":"17_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"752","DOI":"10.1007\/978-3-030-58571-6_44","volume-title":"Computer Vision \u2013 ECCV 2020","author":"G Moon","year":"2020","unstructured":"Moon, G., Lee, K.M.: I2L-MeshNet: image-to-lixel prediction network for accurate 3D human pose and mesh estimation from a single RGB image. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 752\u2013768. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58571-6_44"},{"doi-asserted-by":"crossref","unstructured":"Nagaraja, N.S., Schmidt, F.R., Brox, T.: Video segmentation with just a few strokes. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3235\u20133243 (2015)","key":"17_CR21","DOI":"10.1109\/ICCV.2015.370"},{"doi-asserted-by":"crossref","unstructured":"Sun, Y., Ye, Y., Liu, W., Gao, W., Fu, Y., Mei, T.: Human mesh recovery from monocular images via a skeleton-disentangled representation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5349\u20135358 (2019)","key":"17_CR22","DOI":"10.1109\/ICCV.2019.00545"},{"unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)","key":"17_CR23"},{"doi-asserted-by":"crossref","unstructured":"Von\u00a0Marcard, T., Henschel, R., Black, M.J., Rosenhahn, B., Pons-Moll, G.: 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)","key":"17_CR24","DOI":"10.1007\/978-3-030-01249-6_37"},{"doi-asserted-by":"crossref","unstructured":"Wu, P., Lu, X., Shen, J., Yin, Y.: Clip fusion with bi-level optimization for human mesh reconstruction from monocular videos. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 105\u2013115 (2023)","key":"17_CR25","DOI":"10.1145\/3581783.3611978"},{"doi-asserted-by":"crossref","unstructured":"Yu, Z., et al.: Skeleton2mesh: kinematics prior injected unsupervised human mesh recovery. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8619\u20138629 (2021)","key":"17_CR26","DOI":"10.1109\/ICCV48922.2021.00850"},{"doi-asserted-by":"crossref","unstructured":"Zanfir, A., Bazavan, E.G., Zanfir, M., Freeman, W.T., Sukthankar, R., Sminchisescu, C.: Neural descent for visual 3d human pose and shape. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14484\u201314493 (2021)","key":"17_CR27","DOI":"10.1109\/CVPR46437.2021.01425"},{"doi-asserted-by":"crossref","unstructured":"Zanfir, M., Zanfir, A., Bazavan, E.G., Freeman, W.T., Sukthankar, R., Sminchisescu, C.: Thundr: transformer-based 3d human reconstruction with markers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12971\u201312980 (2021)","key":"17_CR28","DOI":"10.1109\/ICCV48922.2021.01273"},{"doi-asserted-by":"crossref","unstructured":"Zhang, F., Zhu, X., Dai, H., Ye, M., Zhu, C.: Distribution-aware coordinate representation for human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7093\u20137102 (2020)","key":"17_CR29","DOI":"10.1109\/CVPR42600.2020.00712"},{"doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Pymaf: 3d human pose and shape regression with pyramidal mesh alignment feedback loop. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11446\u201311456 (2021)","key":"17_CR30","DOI":"10.1109\/ICCV48922.2021.01125"},{"doi-asserted-by":"crossref","unstructured":"Zheng, C., Mendieta, M., Wang, P., Lu, A., Chen, C.: A lightweight graph transformer network for human mesh reconstruction from 2d human pose. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 5496\u20135507 (2022)","key":"17_CR31","DOI":"10.1145\/3503161.3547844"}],"container-title":["Lecture Notes in Computer Science","Social Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-1151-5_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T16:01:41Z","timestamp":1738857701000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-1151-5_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819611508","9789819611515"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-1151-5_17","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":"7 February 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors of this paper have no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ICSR + InnoBiz","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Social Robotics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenzhen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"26 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"socrob2024b","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.asianlp.sg\/conferences\/icsr2024\/web\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}