Here we provide evaluations of human shape estimation methods on the Human Bodies in the Wild (HBW) test images. Please see dataset page for more information on HBW and our github repo for the evaluation protocol.
| Method | Model | Height | Chest | Waist | Hips | P2P20K |
| SHAPY [7] | SMPL-X | 51 | 65 | 69 | 57 | 21 |
| TUCH [6] | SMPL | 58 | 89 | 75 | 57 | 26 |
| SPIN [5] | SMPL | 59 | 92 | 78 | 101 | 29 |
| Sengupta et al. [4] | SMPL | 82 | 133 | 107 | 63 | 32 |
| ExPose [3] | SMPL-X | 85 | 99 | 92 | 94 | 35 |
| STRAPS [2] | SMPL | 135 | 167 | 145 | 102 | 47 |
| SMPLR [1] | SMPL | 182 | 267 | 309 | 305 | 69 |
Evaluation on HBW Test Set orderd by P2P20K. All results in mm.
References
[7] Choutas Vasileios, Lea Müller, Chun-Hao P. Huang, Siyu Tang, Dimitrios Tzionas, and Michael J. Black. "Accurate 3D Body Shape Regression Using Metric and Semantic Attributes." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
[6] Lea Müller, Ahmed A. A. Osman, Siyu Tang, Chun-Hao P. Huang, and Michael J. Black. "On self-contact and human pose." In Computer Vision and Pattern Recognition (CVPR), 2021
[5] Nikos Kolotouros, Georgios Pavlakos, Michael J. Black, and Kostas Daniilidis. "Learning to reconstruct 3D human pose and shape via model-fitting in the loop." In International Conference on Computer Vision (ICCV), 2019
[4] Akash Sengupta, Ignas Budvytis, and Roberto Cipolla. "Hierarchical kinematic probability distributions for 3D human shape and pose estimation from images in the wild." In International Conference on Computer Vision (ICCV), 2021
[3] Vasileios Choutas, Georgios Pavlakos, Timo Bolkart, Dimitrios Tzionas, and Michael J. Black. "Monocular expressive body regression through body-driven attention." In European Conference on Computer Vision (ECCV), 2020
[2] Akash Sengupta, Ignas Budvytis, and Roberto Cipolla. "Synthetic training for accurate 3D human pose and shape estimation in the wild." In British Machine Vision Conference (BMVC), 2020
[1] Meysam Madadi, Hugo Bertiche, and Sergio Escalera. "SMPLR: Deep learning based SMPL reverse for 3D human pose and shape recovery." Pattern Recognition (PR), 2020.