{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:07:11Z","timestamp":1771952831487,"version":"3.50.1"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031915741","type":"print"},{"value":"9783031915758","type":"electronic"}],"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\/978-3-031-91575-8_18","type":"book-chapter","created":{"date-parts":[[2025,5,25]],"date-time":"2025-05-25T17:57:38Z","timestamp":1748195858000},"page":"290-306","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Coarse-to-Fine Human Mesh Recovery with\u00a0Transformers"],"prefix":"10.1007","author":[{"given":"Vatsal","family":"Agarwal","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mara","family":"Levy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Max","family":"Ehrlich","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youbao","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ning","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhinav","family":"Shrivastava","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B.: 2d human pose estimation: new benchmark and state of the art analysis. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2014","DOI":"10.1109\/CVPR.2014.471"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Cho, J., Youwang, K., Oh, T.H.: Cross-attention of disentangled modalities for 3d human mesh recovery with transformers. In: European Conference on Computer Vision, pp. 342\u2013359. Springer (2022)","DOI":"10.1007\/978-3-031-19769-7_20"},{"key":"18_CR3","doi-asserted-by":"crossref","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: European Conference on Computer Vision, pp. 769\u2013787. Springer (2020)","DOI":"10.1007\/978-3-030-58571-6_45"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"18_CR5","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"18_CR6","doi-asserted-by":"publisher","unstructured":"Dou, Z., et al.: Tore: token reduction for efficient human mesh recovery with transformer (2022). https:\/\/doi.org\/10.48550\/ARXIV.2211.10705, https:\/\/arxiv.org\/abs\/2211.10705","DOI":"10.48550\/ARXIV.2211.10705"},{"key":"18_CR7","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 (ICCV), pp. 11250\u201311259, October 2021","DOI":"10.1109\/ICCV48922.2021.01106"},{"key":"18_CR8","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 249\u2013256. JMLR Workshop and Conference Proceedings (2010)"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Goel, S., Pavlakos, G., Rajasegaran, J., Kanazawa*, A., Malik*, J.: Humans in 4D: reconstructing and tracking humans with transformers. In: International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01358"},{"issue":"1","key":"18_CR10","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/BF02291478","volume":"40","author":"JC Gower","year":"1975","unstructured":"Gower, J.C.: Generalized procrustes analysis. Psychometrika 40(1), 33\u201351 (1975)","journal-title":"Psychometrika"},{"key":"18_CR11","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, pp. 770\u2013778. IEEE, June 2016. https:\/\/doi.org\/10.1109\/CVPR.2016.90, http:\/\/ieeexplore.ieee.org\/document\/7780459","DOI":"10.1109\/CVPR.2016.90"},{"key":"18_CR12","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)","DOI":"10.1109\/TPAMI.2013.248"},{"key":"18_CR13","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: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00744"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Huang, C.H.P., Hilliges, O., Black, M.J.: Pare: Part attention regressor for 3d human body estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11127\u201311137 (2021)","DOI":"10.1109\/ICCV48922.2021.01094"},{"key":"18_CR15","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: ICCV, CoRR abs\/1909.12828 (2019). http:\/\/arxiv.org\/abs\/1909.12828","DOI":"10.1109\/ICCV.2019.00234"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Kolotouros, N., Pavlakos, G., Daniilidis, K.: Convolutional mesh regression for single-image human shape reconstruction. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00463"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Lassner, C., Romero, J., Kiefel, M., Bogo, F., Black, M.J., Gehler, P.V.: Unite the people: closing the loop between 3d and 2d human representations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6050\u20136059 (2017)","DOI":"10.1109\/CVPR.2017.500"},{"key":"18_CR18","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)","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"18_CR19","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)","DOI":"10.1109\/ICCV48922.2021.01270"},{"key":"18_CR20","unstructured":"Lin, T.Y., et al.: Microsoft coco: Common objects in context (2014). http:\/\/arxiv.org\/abs\/1405.0312, cite arxiv:1405.0312Comment: 1) updated annotation pipeline description and figures; 2) added new section describing datasets splits; 3) updated author list"},{"issue":"6","key":"18_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2816795.2818013","volume":"34","author":"M Loper","year":"2015","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: Smpl: a skinned multi-person linear model. ACM Trans. Graph. (TOG) 34(6), 1\u201316 (2015)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"18_CR22","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Ma, X., Su, J., Wang, C., Zhu, W., Wang, Y.: 3d human mesh estimation from virtual markers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 534\u2013543, June 2023","DOI":"10.1109\/CVPR52729.2023.00059"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"von Marcard, T., Henschel, R., Black, M., Rosenhahn, B., Pons-Moll, G.: Recovering accurate 3d human pose in the wild using imus and a moving camera. In: European Conference on Computer Vision (ECCV), September 2018","DOI":"10.1007\/978-3-030-01249-6_37"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Mehta, D., et al.: Single-shot multi-person 3d pose estimation from monocular rgb. In: 2018 International Conference on 3D Vision (3DV), pp. 120\u2013130. IEEE (2018)","DOI":"10.1109\/3DV.2018.00024"},{"key":"18_CR26","doi-asserted-by":"crossref","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: ECCV (2020)","DOI":"10.1007\/978-3-030-58571-6_44"},{"key":"18_CR27","unstructured":"Paszke, A., et\u00a0al.: Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019)"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., 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":"18_CR29","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhu, L., Zhou, X., Daniilidis, K.: Learning to estimate 3d human pose and shape from a single color image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 459\u2013468 (2018)","DOI":"10.1109\/CVPR.2018.00055"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Ranjan, A., Bolkart, T., Sanyal, S., Black, M.J.: Generating 3d faces using convolutional mesh autoencoders. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 704\u2013720 (2018)","DOI":"10.1007\/978-3-030-01219-9_43"},{"key":"18_CR31","unstructured":"Research, M.A.: fvcore (2023). https:\/\/github.com\/facebookresearch\/fvcore"},{"key":"18_CR32","doi-asserted-by":"crossref","unstructured":"Romero, J., Tzionas, D., Black, M.J.: Embodied hands: modeling and capturing hands and bodies together. ACM Trans. Graph. (Proc. SIGGRAPH Asia) 36(6), November 2017","DOI":"10.1145\/3130800.3130883"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Sun, Y., Bao, Q., Liu, W., Fu, Y., Black, M.J., Mei, T.: Monocular, one-stage, regression of multiple 3d people. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01099"},{"key":"18_CR34","unstructured":"Vaswani, A., et al.: Attention is all you need. Advances in neural information processing systems 30 (2017)"},{"issue":"10","key":"18_CR35","doi-asserted-by":"publisher","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","volume":"43","author":"J Wang","year":"2020","unstructured":"Wang, J., et al.: Deep high-resolution representation learning for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 43(10), 3349\u20133364 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR36","unstructured":"Yang, S., Heng, W., Liu, G., Luo, G., Yang, W., Yu, G.: Capturing the motion of every joint: 3d human pose and shape estimation with independent tokens (2023). https:\/\/arxiv.org\/abs\/2303.00298"},{"key":"18_CR37","doi-asserted-by":"crossref","unstructured":"Yoshiyasu, Y.: Deformable mesh transformer for 3d human mesh recovery. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17006\u201317015 (2023)","DOI":"10.1109\/CVPR52729.2023.01631"},{"key":"18_CR38","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 International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.01125"},{"key":"18_CR39","doi-asserted-by":"crossref","unstructured":"Zheng, C., Liu, X., Qi, G.J., Chen, C.: Potter: pooling attention transformer for efficient human mesh recovery. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1611\u20131620 (2023)","DOI":"10.1109\/CVPR52729.2023.00161"},{"key":"18_CR40","unstructured":"Zheng, C., Mendieta, M., Yang, T., Qi, G.J., Chen, C.: Feater: an efficient network for human reconstruction feature map-based transformer"},{"issue":"4","key":"18_CR41","doi-asserted-by":"publisher","first-page":"901","DOI":"10.1109\/TPAMI.2018.2816031","volume":"41","author":"X Zhou","year":"2018","unstructured":"Zhou, X., Zhu, M., Pavlakos, G., Leonardos, S., Derpanis, K.G., Daniilidis, K.: Monocap: monocular human motion capture using a cnn coupled with a geometric prior. IEEE Trans. Pattern Anal. Mach. Intell. 41(4), 901\u2013914 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR42","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Barnes, C., Lu, J., Yang, J., Li, H.: On the continuity of rotation representations in neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5745\u20135753 (2019)","DOI":"10.1109\/CVPR.2019.00589"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91575-8_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,25]],"date-time":"2025-05-25T17:57:51Z","timestamp":1748195871000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91575-8_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031915741","9783031915758"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91575-8_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","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"}}]}}