H3WB: Human3.6M 3D WholeBody Dataset and Benchmark - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

H3WB: Human3.6M 3D WholeBody Dataset and Benchmark

Yue Zhu
  • Fonction : Auteur
  • PersonId : 1348230
Nermin Samet
  • Fonction : Auteur
  • PersonId : 1348231
David Picard

Résumé

We present a benchmark for 3D human whole-body pose estimation, which involves identifying accurate 3D keypoints on the entire human body, including face, hands, body, and feet. Currently, the lack of a fully annotated and accurate 3D whole-body dataset results in deep networks being trained separately on specific body parts, which are combined during inference. Or they rely on pseudo-groundtruth provided by parametric body models which are not as accurate as detection based methods. To overcome these issues, we introduce the Human3.6M 3D WholeBody (H3WB) dataset, which provides whole-body annotations for the Human3.6M dataset using the COCO Wholebody layout. H3WB comprises 133 whole-body keypoint annotations on 100K images, made possible by our new multi-view pipeline. We also propose three tasks: i) 3D whole-body pose lifting from 2D complete whole-body pose, ii) 3D whole-body pose lifting from 2D incomplete whole-body pose, and iii) 3D whole-body pose estimation from a single RGB image. Additionally, we report several baselines from popular methods for these tasks. Furthermore, we also provide automated 3D whole-body annotations of TotalCapture and experimentally show that when used with H3WB it helps to improve the performance. Code and dataset is available at https://github.com/wholebody3d/wholebody3d
Fichier principal
Vignette du fichier
Zhu_H3WB_Human3.6M_3D_WholeBody_Dataset_and_Benchmark_ICCV_2023_paper.pdf (3.77 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04443304 , version 1 (07-02-2024)

Licence

Paternité - Pas d'utilisation commerciale

Identifiants

Citer

Yue Zhu, Nermin Samet, David Picard. H3WB: Human3.6M 3D WholeBody Dataset and Benchmark. 2023 IEEE/CVF International Conference on Computer Vision, Oct 2023, Paris, France. ⟨10.1109/ICCV51070.2023.01845⟩. ⟨hal-04443304⟩
14 Consultations
19 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More