Metraipolis › archive › dc_ca662001dab3

TRI-POSE-Net: Adaptive 3D human pose estimation through selective kernel networks and self-supervision with trifocal tensors — Europe PMC PMID:39636815

Source: Europe PMC (en)
Original: https://europepmc.org/article/MED/39636815
DOI: 10.1371/journal.pone.0310831
License (as archived): CC0-1.0
Archived: 2026-10-08T05:11:07.898Z
SHA-256 of the archived text: abf1494378cc1a83004332b228fd5dd84f847a4495cd30292e2647040002f628
Stable URL of this page: https://metraipolis.com/documento/dc_ca662001dab3

How to cite

TRI-POSE-Net: Adaptive 3D human pose estimation through selective kernel networks and self-supervision with trifocal tensors — Europe PMC PMID:39636815 — Europe PMC (en), https://europepmc.org/article/MED/39636815 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ca662001dab3 (Metraipolis archive dc_ca662001dab3, sha256 abf1494378cc1a83004332b228fd5dd84f847a4495cd30292e2647040002f628)

BibTeX

@misc{dcca662001dab3,
  title = {TRI-POSE-Net: Adaptive 3D human pose estimation through selective kernel networks and self-supervision with trifocal tensors — Europe PMC PMID:39636815},
  howpublished = {Europe PMC (en)},
  url = {https://europepmc.org/article/MED/39636815},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ca662001dab3; sha256 abf1494378cc1a83004332b228fd5dd84f847a4495cd30292e2647040002f628},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: Europe PMC (en), https://europepmc.org/article/MED/39636815. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: statistica e scienza dei dati (ricerca Europe PMC «computer vision», solo open access).
Pubblicazione: PloS one, 2024 (prima pubblicazione 2024-12-05).
Identificativi: PMID 39636815 · PMCID PMC11620359 · DOI 10.1371/journal.pone.0310831.
Descrittori MeSH principali: Imaging, Three-Dimensional.
Pagina: https://europepmc.org/article/MED/39636815 — https://doi.org/10.1371/journal.pone.0310831. Autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza dell'articolo dichiarata da Europe PMC: CC0 (la versione è indicata dall'editore sulla pagina). Abstract riportato senza modifiche al contenuto, con attribuzione; deposito marcato CC0.
Letto il 2026-10-08T04:39:21.777Z tramite l'API REST ufficiale di Europe PMC (EMBL-EBI), nel rispetto del robots.txt e del crawl-delay.