EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

A Survey of the State of the Art in Monocular 3D Human Pose Estimation: Methods, Benchmarks, and Challenges

Yan Guo, Tianhan Gao, Aoshuang Dong, Xinbei Jiang iD, Zichen Zhu, Fuxin Wang

Sensors · 10.04.2025 · 25 (8) · 2409

DOI: 10.3390/s25082409 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Sensors, online erschienen am 10.04.2025. Verfasst von Yan Guo und 5 weiteren Autor:innen. Beteiligte Einrichtung: Software College, Northeastern University, Shenyang 110004, China. Hauptthemen laut MEDLINE: Imaging, Three-Dimensional. Die Arbeit wurde bisher 40-mal zitiert (Crossref) und nennt 153 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Three-dimensional human pose estimation (3D HPE) from monocular RGB cameras is a fundamental yet challenging task in computer vision, forming the basis of a wide range of applications such as action recognition, metaverse, self-driving, and healthcare. Recent advances in deep learning have significantly propelled the field, particularly with the incorporation of state-space models (SSMs) and diffusion models. However, systematic reviews that comprehensively cover these emerging techniques remain limited. This survey contributes to the literature by providing the first comprehensive analysis of recent innovative approaches, featuring diffusion models and SSMs within 3D HPE. It categorizes and analyzes various techniques, highlighting their strengths, limitations, and notable innovations. Additionally, it provides a detailed overview of commonly employed datasets and evaluation metrics. Furthermore, this survey offers an in-depth discussion on key challenges, particularly depth ambiguity and occlusion issues arising from single-view setups, thoroughly reviewing effective solutions proposed in recent studies. Finally, current applications and promising avenues for future research are highlighted to guide and inspire ongoing innovation in the area, with emerging trends such as integrating large language models (LLMs) to provide semantic priors and prompt-based supervision for improved 3D pose estimation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Imaging, Three-DimensionalHumansDeep LearningBenchmarkingAlgorithms

Stichwörter der Autor:innen

3D human pose estimationdeep learning-based pose estimationpose estimation surveysingle- and multi-person pose estimation

Autor:innen und Institutionen

  • Software College, Northeastern University, Shenyang 110004, China.

ORCID-Profile: Xinbei Jiang

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Guo, Y., Gao, T., Dong, A., Jiang, X., Zhu, Z., & Wang, F. (2025). A Survey of the State of the Art in Monocular 3D Human Pose Estimation: Methods, Benchmarks, and Challenges. Sensors, 25(8), 2409. https://doi.org/10.3390/s25082409

Vancouver

Guo Y, Gao T, Dong A, Jiang X, Zhu Z, Wang F. A Survey of the State of the Art in Monocular 3D Human Pose Estimation: Methods, Benchmarks, and Challenges. Sensors. 2025;25(8):2409. doi:10.3390/s25082409

BibTeX
@article{Guo2025,
  author = {Guo, Yan and Gao, Tianhan and Dong, Aoshuang and Jiang, Xinbei and Zhu, Zichen and Wang, Fuxin},
  title = {A Survey of the State of the Art in Monocular 3D Human Pose Estimation: Methods, Benchmarks, and Challenges},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {8},
  pages = {2409},
  doi = {10.3390/s25082409}
}
Kostenlos starten →