Almaarefa University
The authoritative source for research information and outputs is Elsevier Scopus, with researcher profile verification from the Deanship of Scientific Research.
ArticleOpen access20243 citation

TRI-POSE-Net: Adaptive 3D human pose estimation through selective kernel networks and self-supervision with trifocal tensors

Nabeel Ahmed Khan،Aisha Ahmed Alarfaj،Ebtisam Abdullah Alabdulqader،Nuha Zamzami،Muhammad Umer،Nisreen Innab ✉،Tai-hoon Kim ✉

PLoS ONE · vol. 19 (12) · e0310831-e0310831 · 2024

Abstract

Accurate and flexible 3D pose estimation for virtual entities is a strenuous task in computer vision applications. Conventional methods struggle to capture realistic movements; thus, creative solutions that can handle the complexities of genuine avatar interactions in dynamic virtual environments are imperative. In order to tackle the problem of precise 3D pose estimation, this work introduces TRI-POSE-Net, a model intended for scenarios with limited supervision. The proposed technique, which is based on ResNet-50 and includes integrated Selective Kernel Network (SKNet) blocks, has proven to be efficient for feature extraction customised specifically to pose estimation scenarios. Furthermore, trifocal tensors and their trio-view geometry allow us to generate 3D ground truth poses from 2D poses, resulting in more refined triangulations. Through the proposed approach, the 3D poses can be estimated from a single 2D RGB image. Moreover, the proposed approach was evaluated on the HumanEva-I dataset yielding a Mean-Per-Joint-Position-Error (MPJPE) of 47.6 under self-supervision and an MPJPE of 29.9 under full supervision. In comparison with the other works, the proposed work has performed well in the self-supervision paradigm.

Details

Journal
PLoS ONE
Publisher
Public Library of Science
Volume
19
Issue
12
Pages
e0310831-e0310831
ISSN
1932-6203
Year
2024
Language
en
License
public-domain
Open access
gold
Citations
3
Source
scopus

Topics

PoseComputer scienceArtificial intelligenceGround truthComputer visionAvatar

Human Pose and Action Recognition (Computer Science) · Face recognition and analysis (Computer Science) · 3D Shape Modeling and Analysis (Engineering)

Cite this

APA
Khan, N. A., Alarfaj, A. A., Alabdulqader, E. A., Zamzami, N., Umer, M., Innab, N., Kim, T. (2024). TRI-POSE-Net: Adaptive 3D human pose estimation through selective kernel networks and self-supervision with trifocal tensors. PLoS ONE, 19(12), e0310831-e0310831. https://doi.org/10.1371/journal.pone.0310831
Harvard
Khan, N. A., Alarfaj, A. A., Alabdulqader, E. A., Zamzami, N., Umer, M., Innab, N., Kim, T. 2024, 'TRI-POSE-Net: Adaptive 3D human pose estimation through selective kernel networks and self-supervision with trifocal tensors', PLoS ONE, vol. 19(12), e0310831-e0310831. Available at: https://doi.org/10.1371/journal.pone.0310831
Vancouver
Khan NA, Alarfaj AA, Alabdulqader EA, Zamzami N, Umer M, Innab N, Kim T. TRI-POSE-Net: Adaptive 3D human pose estimation through selective kernel networks and self-supervision with trifocal tensors. PLoS ONE. 2024;19(12), e0310831-e0310831.
BibTeX
@article{khan20241040,
  title = {TRI-POSE-Net: Adaptive 3D human pose estimation through selective kernel networks and self-supervision with trifocal tensors},
  author = {Nabeel Ahmed Khan and Aisha Ahmed Alarfaj and Ebtisam Abdullah Alabdulqader and Nuha Zamzami and Muhammad Umer and Nisreen Innab and Tai-hoon Kim},
  year = {2024},
  journal = {PLoS ONE},
  volume = {19},
  number = {12},
  pages = {e0310831-e0310831},
  publisher = {Public Library of Science},
  doi = {10.1371/journal.pone.0310831},
  url = {https://doi.org/10.1371/journal.pone.0310831}
}
RIS
TY  - JOUR
AU  - Nabeel Ahmed Khan
AU  - Aisha Ahmed Alarfaj
AU  - Ebtisam Abdullah Alabdulqader
AU  - Nuha Zamzami
AU  - Muhammad Umer
AU  - Nisreen Innab
AU  - Tai-hoon Kim
TI  - TRI-POSE-Net: Adaptive 3D human pose estimation through selective kernel networks and self-supervision with trifocal tensors
PY  - 2024
JO  - PLoS ONE
VL  - 19
IS  - 12
SP  - e0310831-e0310831
DO  - 10.1371/journal.pone.0310831
UR  - https://doi.org/10.1371/journal.pone.0310831
ER  - 

Related outputs