Duc Van Tran
ABSTRACT
Nowadays, Human Reconstruction is an important part of 3D Reconstruction because it enables us to acquire human information. In reality, Human Reconstruction is applied more and more widely in various domains of people's life such as healthcare, education, sport, entertainment, fashion, anthropometry…especially in the Covid-19 pandemic situation. Technically, the digitalization of human shape and pose is being implemented by two main solutions. The first solution aims to re-create 3D shape and pose of people by using a set of 2D images from different view angles. The second method focuses on handling with the point cloud which is acquired from a set of depth cameras. Both of them have their own advantages and disadvantages. The current trend of 3D Human Reconstruction is to try recreating human shape and pose not only from various available sources (images, point cloud) but also from natural sources (surveillance camera). However, the accuracy of current solutions is significantly sensitive to the working environment. Therefore, this work gives an attempt to develop two human reconstruction methods and evaluate their performance in various conditions as synthetic, laboratory, and real-world environments. The results show a comparison of human reconstruction's accuracy due to the working environment and method of approach. In the synthetic environment, the accuracy is highest for both two methods because of the perfection of input. The accuracy of these methods is lower in the remaining environment. Besides, the result also proves that point cloud-based method is more sensitive than image-based method due to the limitation of hardware devices.
- Tianhao Zhao, King Ngi Ngan, Fellow, IEEE, Songnan Li, and Fanzi Wu. 2019. 3-D Reconstruction of Human Body Shape from a Single Commodity Depth Camera. IEEE Transactions on Multimedia. https://doi.org/10.1109/TMM.2018.2844087Google Scholar
- Haiyong Jiang, Jianfei Cai, Jianmin Zheng. 2019. Skeleton-aware 3D human shape reconstruction from point clouds. Proceedings: International Conference on Computer Vision, ICCV 2019, 5430-5440. https://ieeexplore.ieee.org/xpl/conhome/8972782/proceedingGoogle Scholar
- Nikos Kolotouros, Georgios Pavlakos, Michael J Black, Kostas Daniilidis. 2019. Learning to Reconstruct 3D Human Pose and Shape via Model-Fitting in the Loop. IEEE/CVF International Conference on Computer Vision (ICCV). DOI: 10.1109/ICCV.2019.00234Google ScholarCross Ref
- Brandon M. Smith, Visesh Chari, Amit Agrawal, James M. Rehg, Ram Sever. 2019. Towards Accurate 3D Human Body Reconstruction from Silhouettes. IEEE 2019 International Conference on 3D Vision (3DV). DOI: 10.1109/3DV.2019.00039Google ScholarCross Ref
- Loper, M., Mahmood, N., Romero, J.. Pons-Moll, G., Black, M.J. 2015. SMPL: A Skinned Multi-Person Linear Model. ACM Trans. Graphics (Proc. SIGGRAPH Asia), 34(6):248:1-248:16. DOI: 10.1145/2816795.2818013Google ScholarDigital Library
- Osman, A. A. A., Bolkart, T., Black, M. J. 2020. STAR: Sparse Trained Articulated Human Body Regressor. European Conference on Computer Vision (ECCV) , LNCS 12355, pages: 598-613. DOI: 10.1007/978-3-030-58539-6_36Google ScholarDigital Library
- Kolotouros, Nikos and Pavlakos, Georgios and Black, Michael J. and Daniilidis, Kostas. 2019. Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop. 2019 IEEE/CVF International Conference on Computer Vision (ICCV). DOI: 10.1109/ICCV.2019.00234Google Scholar
- Yui Shigeki, Fumio Okura, Ikuhisa Mitsugami, Yasushi Yagi. 2018. Estimating 3D human shape under clothing from a single RGB image. IPSJ Transactions on Computer Vision and Applications. https://doi.org/10.1186/s41074-018-0052-9Google Scholar
- Pavlakos, G., Choutas, V., Ghorbani, N., Bolkart, T., Osman, A. A. A., Tzionas, D., Black, M. J. 2019. Expressive Body Capture: 3D Hands, Face, and Body from a Single Image. Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pages: 10975-10985Google Scholar
- Kanazawa, A., Black, M. J., Jacobs, D. W., Malik, J. 2018. End-to-end Recovery of Human Shape and Pose. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages: 7122-7131, IEEE Computer Society.Google Scholar
- 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: Proc. European Conf. on Computer Vision (ECCV’16), 561–578.. Springer, Amsterdam.Google ScholarCross Ref
- Tran Van Duc, Ngo Hai Linh, Nguyen Tien Dat. 2020. Framework Development for 3D Human Shape Reconstruction from Security Camera. 2020 IEEE Eighth International Conference on Communication and Electronic (ICCE). DOI: 10.1109/ICCE48956.2021.9352148Google Scholar
- Kingma, Diedrik P. and Ba, Jimmy. 2014. Adam: A method for Stochastic Optimization. 3rd International Conference for Learning Representation. http://arxiv.org/abs/1412.6980Google Scholar
- Tsz-Ho Kwok, Kwok-Yun Yeung, and Charlie C.L. Wang. 2014. Volumetric template fitting for human body reconstruction from incomplete data. Journal of Manufacturing Systems. https://doi.org/10.1016/j.jmsy.2014.05.009Google Scholar
- A. C. Carrilho, M.Galo, R.C. dos Santos. 2018. STATISTICAL OUTLIER DETECTION METHOD FOR AIRBORNE LIDAR DATA. ISPRS TC I Midterm Symposium Innovative Sensing - From Sensors to Methods and Applications. DOI: 10.5194/isprs-archives-XLII-1-87-2018Google Scholar
- S. Rusinkiewicz, M. Levoy. 2001. Efficient variants of the ICP algorithm. Third International Conference on 3-D Digital Imaging and Modeling. DOI: 10.1109/IM.2001.924423Google ScholarCross Ref
- Brandon Smith, Visesh Chari, Amit Agrawal, James Rehg, Ram Sever. 2019 . Towards Accurate 3D Human Body Reconstruction from Silhouettes. IEEE 2019 International Conference on 3D Vision (3DV). DOI: 10.1109/3DV.2019.00039Google ScholarCross Ref
- Paul Besl, H.D. McKay. 1992. A method for registration of 3-D Shapes. IEEE Transaction on Pattern Analysis and Machine Intelligence. DOI; 10.1109/34.121791Google Scholar
- Yipin Yang, Yao Yu, Yu Zhou, Sidan Du, James Davis, Ruigang Yang. 2014. Semantic Parametric Reshaping of Human Body Models. IEEE Second International Conference on 3D Vision. DOI: 10.1109/3DV.2014.47Google ScholarDigital Library
- F6 Smart Scanner Document. https://mantis-vision.com/handheld-3d-scanners/Google Scholar
Recommendations
3D human body reconstruction based on SMPL model
AbstractRecovering 3D human pose and body shape from a monocular image is a challenging task in computer vision. In this paper, we present an optimization-based algorithm and an innovative framework to reconstruct 3D human body from a single monocular ...
High Quality Photometric Reconstruction Using a Depth Camera
CVPR '14: Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern RecognitionIn this paper we present a depth-guided photometric 3D reconstruction method that works solely with a depth camera like the Kinect. Existing methods that fuse depth with normal estimates use an external RGB camera to obtain photometric information and ...
HEI-Human: A Hybrid Explicit and Implicit Method for Single-View 3D Clothed Human Reconstruction
Pattern Recognition and Computer VisionAbstractSingle-view 3D clothed human reconstruction is a challenging task, not only because of the need to infer the complex global topology of human body but also due to the requirement to recover delicate surface details. In this paper, a method named ...
Comments