OVERVIEW AND CHALLENGES OF USING DEEP LEARNING FOR THREE-DIMENSIONAL ESTIMATION OF A PERSON'S POSTURE FROM A SINGLE IMAGE

O. A. Lyamtsev1,2, I. I. Maksimenko1,2

About the authors

O. A. Lyamtsev1,2, I. I. Maksimenko1,2

Лямцев Олег Алексеевич – стажер-исследователь ФГБНУ "Институт прикладной математики и механики", ул. Розы Люксембург, 74, Донецк, 283048, Россия, бакалавр кафедры компьютерных технологий ФГБОУ ВО «ДонГУ», ул. Университетская, 24, Донецк, 283001, Россия. Область научных интересов: компью- терное зрение, машинное обучение, нейронные сети. Число научных публикаций – 5.

Максименко Игорь Иванович – заведующий отделом теории управляющих систем ФГБНУ "Институт прикладной математики и механики", ул. Розы Люксембург, 74, Донецк, 283048, Россия, доцент кафедры компьютерных технологий физико- технического факультета ФГБОУ ВО «ДонГУ», ул. Университетская, 24, Донецк, 283001, Россия. Область научных интересов: теория автоматов, теория графов, системы искусственного интеллекта. Число научных публикаций – более 40.

Download PDF

UDC: 004.932.2
DOI: 10.24412/2413-7383-2025-4-39-49-59
Language: Russian

Abstract: The article considers the task of 3D human pose estimation from monocular image, provides a mathematical description, highlights the main approaches, problems in the task and their solutions, neural network architectures. Among neural network architectures, graph convolutional networks are the most popular, extracting local information from nearby joints and transformers, modeling global dependencies through the internal attention mechanism. Among the key problems in solving the task, we can distinguish: 1) depth uncertainty; 2) occlusion; 3) insufficient volume and diversity of training data.

Keywords: 3D human pose estimation, computer visi on, deep learning, neural networks, monocular image

References

1. El Kaid A. Baïna K. A Systematic Review of Recent Deep Learning Approaches for 3D Human Pose Estimation / A. El Kaid, K. Baïna // Journal of Imaging. – 2023. – P. 8-15. – DOI: 10.3390/jimaging9120275
2. Kiselev Yu.V. Bogomolov I.A. Rozaliev V.L. Baklan V.A. ANALYSIS OF APPROACHES, METHODS AND SOLUTIONS FOR DETECTING HUMAN POSTURE. CHOOSING A TOOL FOR THE TASK OF DETERMINING A PERSON'S EMOTIONAL STATE BY THEIR POSTURE // Modern high-tech technologies. – 2023. – No. 6. – pp. 41-47. – DOI: https://doi.org/10.17513/snt.39629
3. Shergin I.A. Ryzhov A.P. The problem of assessing human posture: tasks, methods, solutions. // Intelligent systems. Theory and applications. – 2024. – Pp. 69-84.
4. Gong W. Zhang X. Gonzàlez J. Sobral A. Bouwmans T. Tu C. Zahzah E. Human Pose Estimation from Monocular Images: A Comprehensive Survey / W. Gong, X. Zhang, J. Gonzàlez, A. Sobral, T. Bouwmans, C. Tu // Sensors. – 2016. – P. 13-18. – DOI: 10.3390/s16121966
5. Loper M. Mahmood N. Romero J. Pons-Moll G. Black M. J. SMPL: A Skinned Multi-Person Linear Model / M. Loper, N. Mahmood, J. Romero, G. Pons-Moll, M. J. Black. – 2015. – P.1-10. – DOI: 10.1145/3596711.3596800
6. Zheng C. Wu W. Chen C. Yang T. Zhu S. Shen J. Kehtarnavaz N. Shah M. Deep Learning-Based Human Pose Estimation: A Survey – 2023. – URL: https://arxiv.org/pdf/2012.13392 (accessed 15.09.2025).
7. Zhou L. Meng X. Liu Z. Wu M. Gao Z. Wang P. Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey / L. Zhou, X. Meng, Z. Liu, M. Wu, Z. Gao, P. Wang – 2023. – P. 4-10. – DOI: arXiv.2310.13039v1
8. Knap P. Human Modelling and Pose Estimation Overview / P. Knap. – 2024. – P. 1-4. – DOI: arXiv. 2406.19290v1
9. Cao Z. Hidalgo G. Simon T. Wei S. Sheikh Y. OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields / Z. Cao, G. Hidalgo, T. Simon, S. Wei, Y. Sheikh. – 2017. – P. 1-5. – DOI: arXiv:1812.08008 Л Лямцев О. А. Максименко И. И.
10. Pishchulin L. Insafutdinov E. Tang S. Andres B. Andriluka M. Gehler P. Schiele B. DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation / L. Pishchulin, E. Insafutdinov, S. Tang, B. Andres, M. Andriluka, P. Gehler, B. Schiele. – 2015. – P.1-15. – DOI: arXiv:1511.06645
11. Bazarevsky V. Grishchenko I. Raveendran K. Zhu T. Zhang F. Grundmann M. BlazePose: On-device Real-time Body Pose tracking / V. Bazarevsky, I. Grishchenko, K. Raveendran, T. Zhu, F. Zhang, M. Grundmann. – 2020. – P. 1-4. – DOI: arXiv:2006.10204
12. Shahjahan M. Hamza B. Flexible graph convolutional network for 3D human pose estimation / M. Shahjahan, B. Hamza. – 2024. – P. 1-7. – DOI: arXiv:2407.19077
13. Azizi N. Possegger H. Rodolà E. Bischof H. 3D Human Pose Estimation Using Möbius Graph Convolutional Networks / N. Azizi, H. Possegger, E. Rodolà. – 2022. – P. 1-13. – DOI: arXiv:2203.10554
14. Yang Z. Loo J. PyCAT4: A Hierarchical Vision Transformer-based Framework for 3D Human Pose Estimation – 2025. – URL: https://arxiv.org/pdf/2508.02806 (accessed 09/10/2025)
15. Zheng C. Zhu S. Mendieta M. Yang T. Chen C. Ding Z. 3D Human Pose Estimation with Spatial and Temporal Transformers / C. Zheng, S. Zhu, M. Mendieta, T. Yang, C. Chen, Z. Ding. – 2021. – P. 1-13. – DOI: arXiv:2103.10455v3
16. Birkl R. Wofk D. Muller M. MiDaS v3.1 – A Model Zoo for Robust Monocular Relative Depth Estimation – 2023. – URL: https://arxiv.org/pdf/2307.14460 (accessed 09/13/2025).
17. Wu C. Li J. Zhou J. Lin J. Gao K. Yan K. Qwen-Image Technical Report / C. Wu, J. Li, J. Zhou, J. Lin, K. Gao, K. Yan. – 2025. – P.1-23. – DOI: arXiv:2508.02324
18. Aouaidjiaa K. Lia A. Zhanga W. Zhanga C. 3D Human Pose Estimation via Spatial Graph Order Attention and Temporal Body Aware Transformer / K. Aouaidjiaa, A. Lia, W. Zhanga, C. Zhanga. – 2025. – P. 1-16. – DOI: arXiv.2505.01003v1
19. Mehraban S. Adeli V. Taati B. MotionAGFormer: Enhan cing 3D Human Pose Estimation with a Transformer - GCNFormer Network / S. Mehraban, V. Adeli, B. Taati. – 2023. – P. 1-11. – DOI: arXiv:2310.16288
20. Fu Y. Huang C. Li J. Kong H. Tian Y. Li H. Zhang Z. HDiffTG: A Lightweight Hybrid Diffusion-

Issue: 4(39)'2025
Section: ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING
How to cite: O. A. Lyamtsev1,2, I. I. Maksimenko1,2. OVERVIEW AND CHALLENGES OF USING DEEP LEARNING FOR THREE-DIMENSIONAL ESTIMATION OF A PERSON'S POSTURE FROM A SINGLE IMAGE // Problems of Artificial Intelligence. - 2025. - № 4 (39). - P. 49-59. - https://paijournal.guiaidn.ru/en/2025/4(39)-5.html

Back to issue 4(39)'2025