Abstract
In recent years, remarkable strides have been made in 3D human reconstruction. However, the focus has primarily been on pose reconstruction, which fails to capture the true shape of the human body, particularly for individuals who are overweight or underweight. Therefore, based on a combination of regression and optimization, as well as ensuring accurate posture, we incorporate reasonable prior knowledge for the shape part of the reconstructions during iteration to obtain a Skinned Multi-Person Linear Model (SMPL) with a reasonable shape. During the training process, in regard to the pose, we fit 2D joint points, which can be obtained through images, and the training is still feasible even if the ground truth is missing; for the shape, we obtain the dimension information by measurement, but the initial height and waist need to be provided. To assess our method, we collect the dimension data from 200 individuals and achieved a remarkable average precision of 97\(\%\) based on a thorough comparison of the results. Our main research objective is to construct a more realistic model of the human body by adding reasonable body dimension information as prior knowledge during the iterative loop, and to measure 38 body dimensions of the human body. Our experiments demonstrate that our method, in regard to the shape, outperforms other state-of-the-art techniques while simultaneously maintaining postural accuracy.
Graphical Abstract
Similar content being viewed by others
The data availability statement
The “Human3.6M” data that support the findings of this study are available in Human3.6M, the “3DPW” are available in 3DPW, the “MPI-INF-3DHP” are available in MPI-INF-3DHP, the “COCO” are available in COCO, the “LSP” are available in LSP, the “MPII” are available in MPII, and the “SSP-3D” are available in SSP-3D
References
Xiu Y, Yang J, Cao X, Tzionas D, Black MJ (2023) Econ: explicit clothed humans optimized via normal integration. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 512–523
Lassner C, Romero J, Kiefel M, Bogo F, Black MJ, Gehler PV (2017) 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 6050–6059
Bogo F, Kanazawa A, Lassner C, Gehler P, Romero J, Black MJ (2016) Keep it smpl: automatic estimation of 3D human pose and shape from a single image. In: Proceedings of the European conference on computer vision, Springer, pp 561–578
Kanazawa A, Black MJ, Jacobs DW, Malik J (2018) End-to-end recovery of human shape and pose. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7122–7131
Omran M, Lassner C, Pons-Moll G, Gehler P, Schiele B (2018) Neural body fitting: unifying deep learning and model based human pose and shape estimation. In: 2018 International conference on 3D vision, IEEE, pp 484–494
Pavlakos G, Zhu L, Zhou X, Daniilidis K (2018) 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 459–468
Loper M, Mahmood N, Romero J, Pons-Moll G, Black MJ (2015) Smpl: a skinned multi-person linear model. ACM Trans Graphics 34(6):1–16
Song T, Zhang R, Dong Y, Liu F, Zhang Y, Peng R (2021) Mmda: Disease analysis model based on anthropometric measurement. In: 2021 IEEE International conference on bioinformatics and biomedicine, pp 3092–3098
Chen D, Song Y, Liang F, Ma T, Zhu X, Jia T (2023) 3D human body reconstruction based on smpl model. Visual Comput 39(5):1893–1906
Yu H, Cheang C, Fu Y, Xue X (2023) Multi-view shape generation for a 3D human-like body. ACM Trans Multimed Comput, Commun Appl 19(1):1–22
Miura T, Sako S (2023) Simple yet effective 3D ego-pose lift-up based on vector and distance for a mounted omnidirectional camera. Appl Intell 53(3):2616–2628
Yang J, Liu Y, Gu X, Yang G-Z, Guo Y (2022) Posesdf: Simultaneous 3D human shape reconstruction and gait pose estimation using signed distance functions. In: 2022 International conference on robotics and automation, IEEE, pp 1297–1303
Moon G, Nam H, Shiratori T, Lee KM (2022) 3D clothed human reconstruction in the wild. In: Proceedings of the European conference on computer vision, Springer, pp 184—200
Xie X, Bhatnagar BL, Pons-Moll G (2022) Chore: contact, human and object reconstruction from a single RGB image. In: Proceedings of the European conference on computer vision, Springer, pp 125–145
Li Z, Oskarsson M, Heyden A (2022) Detailed 3D human body reconstruction from multi-view images combining voxel super-resolution and learned implicit representation. Appl Intell 52(6):6739–6759
Ren Y, Zhao C, He Y, Cong P, Liang H, Yu J, Xu L, Ma Y (2023) Lidar-aid inertial poser: large-scale human motion capture by sparse inertial and lidar sensors. IEEE Trans Visualization Comput Graphics 29(5):2337–2347
Baumgartner T, Klatt S (2023) Monocular 3D human pose estimation for sports broadcasts using partial sports field registration. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 5108–5117
Loper M, Mahmood N, Black MJ (2014) Mosh: motion and shape capture from sparse markers. ACM Trans Graphics 33(6):1–13
Anguelov D, Srinivasan P, Koller D, Thrun S, Rodgers J, Davis J (2005) Scape: shape completion and animation of people. In: ACM SIGGRAPH 2005 Papers, pp 408–416
Mahmood N, Ghorbani N, Troje NF, Pons-Moll G, Black MJ (2019) Amass: Archive of motion capture as surface shapes. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 5442–5451
Pavlakos G, Choutas V, Ghorbani N, Bolkart T, Osman AA, Tzionas D, Black MJ (2019) 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 10975–10985
Omran M, Lassner C, Pons-Moll G, Gehler P, Schiele B (2018) Neural body fitting: unifying deep learning and model based human pose and shape estimation. In: 2018 International conference on 3D vision, IEEE, pp 484–494
Rockwell C, Fouhey DF (2020) Full-body awareness from partial observations. In: Proceedings of the European conference on computer vision, Springer, pp 522–539
Choutas V, Pavlakos G, Bolkart T, Tzionas D, Black MJ (2020) Monocular expressive body regression through body-driven attention. In: Proceedings of the European conference on computer vision, Springer, pp 20–40
Lassner C, Romero J, Kiefel M, Bogo F, Black MJ, Gehler PV (2017) 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 6050–6059
Kolotouros N, Pavlakos G, Black MJ, Daniilidis K (2019) 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 2252–2261
China: GB/T 38131-2019.anthropometric definitions and methods for garment 2019. In: Standards Press of China: Beijing
China: GB/T 16160-2017.acquisition method of datum points for clothing anthropometry 2019. In: Standards Press of China: Beijing
Sun X, Xiao B, Wei F, Liang S, Wei Y (2018) Integral human pose regression. In: Proceedings of the European conference on computer vision, pp 529–545
Von Marcard T, Henschel R, Black MJ, Rosenhahn B, Pons-Moll G (2018) Recovering accurate 3D human pose in the wild using imus and a moving camera. In: Proceedings of the European conference on computer vision, pp 601–617
Sengupta A, Budvytis I, Cipolla R (2020) Synthetic training for accurate 3D human pose and shape estimation in the wild
Zhou X, Zhu M, Leonardos S, Derpanis KG, Daniilidis K (2016) Sparseness meets deepness: 3D human pose estimation from monocular video. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 4966–4975
Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollár P, Zitnick CL (2014) Microsoft coco: common objects in context. In: Proceedings of the European conference on computer vision, Springer, pp 740–755
Sengupta A, Budvytis I, Cipolla R (2021) Hierarchical kinematic probability distributions for 3D human shape and pose estimation from images in the wild. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 11219–11229
Kolotouros N, Pavlakos G, Daniilidis K (2019) Convolutional mesh regression for single-image human shape reconstruction. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 4501–4510
Choi H, Moon G, Lee KM (2020) Pose2mesh: graph convolutional network for 3D human pose and mesh recovery from a 2D human pose. In: Proceedings of the European conference on computer vision, Springer, pp 769–787
Li Z, Liu J, Zhang Z, Xu S, Yan Y (2022) Cliff: carrying location information in full frames into human pose and shape estimation. In: Proceedings of the European conference on computer vision, Springer, pp 590–606
Acknowledgements
This work was supported by the Shandong Provincial Natural Science Foundation (ZR2021MF058).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
None.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Dong, Y., Yuan, Q., Peng, R. et al. An iterative 3D human body reconstruction method driven by personalized dimensional prior knowledge. Appl Intell 54, 738–748 (2024). https://doi.org/10.1007/s10489-023-05214-y
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-023-05214-y