3DPW

doi:doi:10.57702/ftenjlve

3DPW

3D human pose and mesh estimation, the task of recon-structing human pose in 3D space given a 2D image of the person, is an ill-posed problem, and many data-driven ap-proaches using deep learning were recently proposed (Liu, Kortylewski, and Yuille 2023; Gholami et al. 2022a; Li et al. 2022). A dataset covering the distribution of possible human poses, global orientation, appearance, and other attributes would be large and difficult to capture in practice.

BibTex:

@dataset{Mohsen_Gholami_and_Rabab_Ward_and_Z_Jane_Wang_2024,
    abstract = {3D human pose and mesh estimation, the task of recon-structing human pose in 3D space given a 2D image of the person, is an ill-posed problem, and many data-driven ap-proaches using deep learning were recently proposed (Liu, Kortylewski, and Yuille 2023; Gholami et al. 2022a; Li et al. 2022). A dataset covering the distribution of possible human poses, global orientation, appearance, and other attributes would be large and difficult to capture in practice.},
    author = {Mohsen Gholami and Rabab Ward and Z. Jane Wang},
    doi = {10.57702/ftenjlve},
    institution = {No Organization},
    keyword = {'3D Human Pose Estimation', '3D human pose estimation', '3D pose', '3D pose estimation', '3D reconstruction', '3DPW', 'Human Mesh Recovery', 'Human Motion Capture', 'Human Motion Prediction', 'IMU-based Human Pose Estimation', 'Mesh Estimation', 'SMPL format', 'human body estimation', 'human body shape', 'human modeling', 'human motion capture', 'human motion prediction', 'human pose', 'motion sequences'},
    month = {dec},
    publisher = {TIB},
    title = {3DPW},
    url = {https://service.tib.eu/ldmservice/dataset/3dpw},
    year = {2024}
}