3D human pose estimation; 3DBodyTex.Pose; synthetic data; in-the-wild
Résumé :
[en] In this paper, we propose 3DBodyTex.Pose, a dataset that addresses the task of 3D human pose estimation in-the-wild. Generalization to in-the-wild images remains limited due to the lack of adequate datasets. Existent ones are usually collected in indoor controlled environments where motion capture systems are used to obtain the 3D ground-truth annotations of humans.
3DBodyTex.Pose offers high quality and rich data containing 405 different real subjects in various clothing and poses, and 81k image samples with ground-truth 2D and 3D pose annotations.
These images are generated from 200 viewpoints among which 70 challenging extreme viewpoints. This data was created starting from high resolution textured 3D body scans and by incorporating various realistic backgrounds.
Retraining a state-of-the-art 3D pose estimation approach using data augmented with 3DBodyTex.Pose showed promising improvement in the overall performance, and a sensible decrease in the per joint position error when testing on challenging viewpoints. The 3DBodyTex.Pose is expected to offer the research community with new possibilities for generalizing 3D pose estimation from monocular in-the-wild images.
Disciplines :
Sciences informatiques
Auteur, co-auteur :
BAPTISTA, Renato ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2
SAINT, Alexandre Fabian A ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2
AL ISMAEIL, Kassem ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2
AOUADA, Djamila ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2
Co-auteurs externes :
no
Langue du document :
Anglais
Titre :
Towards Generalization of 3D Human Pose Estimation In The Wild
Date de publication/diffusion :
2020
Nom de la manifestation :
International Conference on Pattern Recognition (ICPR) Workshop on 3D Human Understanding
Date de la manifestation :
10-15 January 2021
Manifestation à portée :
International
Titre de l'ouvrage principal :
International Conference on Pattern Recognition (ICPR) Workshop on 3D Human Understanding, Milan 10-15 January 2021
Peer reviewed :
Peer reviewed
Projet FnR :
FNR10415355 - 3d Action Recognition Using Refinement And Invariance Strategies For Reliable Surveillance, 2015 (01/06/2016-31/05/2019) - Bjorn Ottersten
Chu, X., Yang, W., Ouyang, W., Ma, C., Yuille, A.L., Wang, X.: Multi-context attention for human pose estimation. In: CVPR (2017)
Demisse, G.G., Papadopoulos, K., Aouada, D., Ottersten, B.: Pose encoding for robust skeleton-based action recognition. In: CVPRW (2018)
D’Eusanio, A., Pini, S., Borghi, G., Vezzani, R., Cucchiara, R.: Manual annotations on depth maps for human pose estimation. In: Ricci, E., Rota Bulò, S., Snoek, C., Lanz, O., Messelodi, S., Sebe, N. (eds.) ICIAP 2019, Part I. LNCS, vol. 11751, pp. 233–244. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-30642-7 21
Greene, N.: Environment mapping and other applications of world projections. IEEE CG&A 6(11), 21–29 (1986)
Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3.6m: large scale datasets and predictive methods for 3D human sensing in natural environments. IEEE TPAMI 36(7), 1325–1339 (2014)
Johnson, S., Everingham, M.: Clustered pose and nonlinear appearance models for human pose estimation. In: BMVC, vol. 2, p. 5. Citeseer (2010)
von Marcard, 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: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018, Part X. LNCS, vol. 11214, pp. 614–631. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01249-6 37
Martinez, J., Hossain, R., Romero, J., Little, J.J.: A simple yet effective baseline for 3D human pose estimation. In: ICCV (2017)
Mehta, D., et al.: Monocular 3D human pose estimation in the wild using improved CNN supervision. In: 3DV (2017)
Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016, Part VIII. LNCS, vol. 9912, pp. 483–499. Springer, Cham (2016). https://doi.org/10. 1007/978-3-319-46484-8 29
Pavlakos, G., Zhu, L., Zhou, X., Daniilidis, K.: Learning to estimate 3D human pose and shape from a single color image. In: CVPR (2018)
Pavllo, D., Feichtenhofer, C., Grangier, D., Auli, M.: 3D human pose estimation in video with temporal convolutions and semi-supervised training. In: CVPR (2019)
Pini, S., D’Eusanio, A., Borghi, G., Vezzani, R., Cucchiara, R.: Baracca: a multimodal dataset for anthropometric measurements in automotive. In: International Joint Conference on Biometrics (IJCB) (2020)
Rogez, G., Weinzaepfel, P., Schmid, C.: LCR-Net++: multi-person 2D and 3D pose detection in natural images. IEEE TPAMI 42(5), 1146–1161 (2019)
Saint, A., et al.: 3DBodyTex: textured 3D body dataset. In: 3DV (2018)
Saint, A., Kacem, A., Cherenkova, K., Aouada, D.: 3DBooSTeR: 3D body shape and texture recovery. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12536, pp. 726–740. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-66096-3 49
Saint, A., et al.: SHARP 2020: the 1st shape recovery from partial textured 3D scans challenge results. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12536, pp. 741–755. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-66096-3 50
Saint, A., Shabayek, A.E.R., Cherenkova, K., Gusev, G., Aouada, D., Ottersten, B.: Bodyfitr: robust automatic 3D human body fitting. In: ICIP (2019)
Sigal, L., Balan, A.O., Black, M.J.: HumanEva: synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion. IJCV 87(1–2), 4 (2010)
Trumble, M., Gilbert, A., Malleson, C., Hilton, A., Collomosse, J.: Total capture: 3D human pose estimation fusing video and inertial sensors. In: BMVC, vol. 2, p. 3 (2017)
Varol, G., et al.: Learning from synthetic humans. In: CVPR (2017)
Yang, W., Ouyang, W., Wang, X., Ren, J., Li, H., Wang, X.: 3D human pose estimation in the wild by adversarial learning. In: CVPR (2018)
Zhou, X., Huang, Q., Sun, X., Xue, X., Wei, Y.: Towards 3D human pose estimation in the wild: a weakly-supervised approach. In: ICCV (2017)
Zhou, X., Sun, X., Zhang, W., Liang, S., Wei, Y.: Deep kinematic pose regression. In: Hua, G., Jégou, H. (eds.) ECCV 2016, Part III. LNCS, vol. 9915, pp. 186–201. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-49409-8 17
