Two-Dimensional Human Pose Estimation with Deep Learning: A Review
Source abstract
Abstract
Two-dimensional human pose estimation (2D HPE) has become a fundamental task in computer vision, driven by growing demands in intelligent surveillance, sports analytics, and healthcare. The rapid advancement of deep learning has led to the development of numerous methods. However, the resulting diversity in research directions and model architectures has made systematic assessment and comparison difficult. This review presents a comprehensive overview of recent advances in 2D HPE, focusing on method classification, technical evolution, and performance evaluation. We classify mainstream approaches by task type (single-person vs. multi-person), output strategy (regression vs. heatmap), and architectural design (top-down vs. bottom-up) and analyze their respective strengths, limitations, and application scenarios. Additionally, we summarize commonly used evaluation metrics and benchmark datasets, such as MPII, COCO, LSP, OCHuman, and CrowdPose. A major contribution of this review is the detailed comparison of the top six models on each benchmark, highlighting their network architectures, input resolutions, evaluation results, and key innovations. In light of current challenges, we also outline future research directions, including model compression, occlusion handling, and cross-domain generalization. This review serves as a valuable reference for researchers seeking both foundational insights and practical guidance in 2D human pose estimation.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Human Pose and Action Recognition · Gait Recognition and Analysis · Anomaly Detection Techniques and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Science and Information Engineering, Kunsan National University, Gunsan 54150, Republic of Korea
References (76)
Show source-provided references
1. Sun, R., Lin, Z., Leng, S., Wang, A., and Zhao, L. (2025). An In-Depth Analysis of 2D and 3D Pose Estimation Techniques in Deep Learning: Methodologies and Advances. Electronics, 14.10.3390/electronics14071307 ↗
2. Deep convolutional neural networks for image classification: A comprehensive review10.1162/neco_a_00990 ↗
3. Kipf, T.N., and Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv.
4. Imagenet classification with deep convolutional neural networks
5. Generative adversarial nets
6. An adversarial human pose estimation network injected with graph structure10.1016/j.patcog.2021.107863 ↗
7. Pictorial structures for object recognition10.1023/B:VISI.0000042934.15159.49 ↗
8. Felzenszwalb, P., McAllester, D., and Ramanan, D. (2008, January 23–28). A discriminatively trained, multiscale, deformable part model. Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, AK, USA.10.1109/CVPR.2008.4587597 ↗
9. Cao, Z., Simon, T., Wei, S.E., and Sheikh, Y. (2017, January 21–26). Realtime multi-person 2D pose estimation using part affinity fields. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.143 ↗
10. He, K., Gkioxari, G., Dollár, P., and Girshick, R. (2017, January 22–29). Mask r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.322 ↗
11. Xiao, B., Wu, H., and Wei, Y. (2018, January 8–14). Simple baselines for human pose estimation and tracking. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01231-1_29 ↗
12. Deep high-resolution representation learning for visual recognition10.1109/TPAMI.2020.2983686 ↗
13. Associative embedding: End-to-end learning for joint detection and grouping
14. Cheng, B., Xiao, B., Wang, J., Shi, H., Huang, T.S., and Zhang, L. (2020, January 13–19). Higherhrnet: Scale-aware representation learning for bottom-up human pose estimation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.00543 ↗
15. Ma, X., Su, J., Wang, C., Ci, H., and Wang, Y. (2021, January 20–25). Context modeling in 3d human pose estimation: A unified perspective. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.00617 ↗
16. Li, Y., Zhang, S., Wang, Z., Yang, S., Yang, W., Xia, S.T., and Zhou, E. (2021, January 11–17). Tokenpose: Learning keypoint tokens for human pose estimation. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, BC, Canada.10.1109/ICCV48922.2021.01112 ↗
17. Yuan, Y., Fu, R., Huang, L., Lin, W., Zhang, C., Chen, X., and Wang, J. (2021). Hrformer: High-resolution transformer for dense prediction. arXiv.
18. Yu, C., Xiao, B., Gao, C., Yuan, L., Zhang, L., Sang, N., and Wang, J. (2021, January 20–25). Lite-hrnet: A lightweight high-resolution network. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.01030 ↗
19. Hou, T., Ahmadyan, A., Zhang, L., Wei, J., and Grundmann, M. (2020). MobilePose: Real-time pose estimation for unseen objects with weak shape supervision. arXiv.
20. Toshev, A., and Szegedy, C. (2014, January 23–28). Deeppose: Human pose estimation via deep neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.214 ↗
21. Carreira, J., Agrawal, P., Fragkiadaki, K., and Malik, J. (2016, January 27–30). Human pose estimation with iterative error feedback. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.512 ↗
22. Sun, X., Xiao, B., Wei, F., Liang, S., and Wei, Y. (2018, January 8–14). Integral human pose regression. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01231-1_33 ↗
23. Moon, G., Chang, J.Y., and Lee, K.M. (2019, January 15–20). Posefix: Model-agnostic general human pose refinement network. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00796 ↗
24. Joint training of a convolutional network and a graphical model for human pose estimation
25. Wei, S.E., Ramakrishna, V., Kanade, T., and Sheikh, Y. (2016, January 27–30). Convolutional pose machines. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.511 ↗
26. Newell, A., Yang, K., and Deng, J. (2016, January 11–14). Stacked hourglass networks for human pose estimation. Proceedings of the Computer Vision—ECCV 2016: 14th European Conference, Amsterdam, The Netherlands. Part VIII.10.1007/978-3-319-46484-8_29 ↗
27. Yang, W., Li, S., Ouyang, W., Li, H., and Wang, X. (2017, January 22–29). Learning feature pyramids for human pose estimation. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.144 ↗
28. Chu, X., Yang, W., Ouyang, W., Ma, C., Yuille, A.L., and Wang, X. (2017, January 21–26). Multi-context attention for human pose estimation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.601 ↗
29. Zhang, F., Zhu, X., Dai, H., Ye, M., and Zhu, C. (2020, January 13–19). Distribution-aware coordinate representation for human pose estimation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.00712 ↗
30. Huang, J., Zhu, Z., Guo, F., and Huang, G. (2020, January 13–19). The devil is in the details: Delving into unbiased data processing for human pose estimation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.00574 ↗
31. Li, K., Wang, S., Zhang, X., Xu, Y., Xu, W., and Tu, Z. (2021, January 20–25). Pose recognition with cascade transformers. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.00198 ↗
32. Wang, J., Long, X., Gao, Y., Ding, E., and Wen, S. (2020, January 23–28). Graph-pcnn: Two stage human pose estimation with graph pose refinement. Proceedings of the Computer Vision—ECCV 2020: 16th European Conference, Glasgow, UK. Part XI.10.1007/978-3-030-58621-8_29 ↗
33. Kocabas, M., Karagoz, S., and Akbas, E. (2018, January 8–14). Multiposenet: Fast multi-person pose estimation using pose residual network. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01252-6_26 ↗
34. Khirodkar, R., Chari, V., Agrawal, A., and Tyagi, A. (2021, January 20–25). Multi-instance pose networks: Rethinking top-down pose estimation. Proceedings of the IEEE/CVF International Conference on Computer Vision, Nashville, TN, USA.10.1109/ICCV48922.2021.00311 ↗
35. Vitpose: Simple vision transformer baselines for human pose estimation
36. Openpose: Realtime multi-person 2d pose estimation using part affinity fields10.1109/TPAMI.2019.2929257 ↗
37. Papandreou, G., Zhu, T., Chen, L.C., Gidaris, S., Tompson, J., and Murphy, K. (2018, January 8–14). Personlab: Person pose estimation and instance segmentation with a bottom-up, part-based, geometric embedding model. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01264-9_17 ↗
38. Li, M., Zhou, Z., Li, J., and Liu, X. (2018, January 20–24). Bottom-up pose estimation of multiple person with bounding box constraint. Proceedings of the 2018 24th International Conference on Pattern Recognition (ICPR), Beijing, China.10.1109/ICPR.2018.8546194 ↗
39. Towards multi-person pose tracking: Bottom-up and top-down methods
40. Li, J., Su, W., and Wang, Z. (2020, January 7–12). Simple pose: Rethinking and improving a bottom-up approach for multi-person pose estimation. Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA.10.1609/aaai.v34i07.6797 ↗
41. Geng, Z., Sun, K., Xiao, B., Zhang, Z., and Wang, J. (2021, January 20–25). Bottom-up human pose estimation via disentangled keypoint regression. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.01444 ↗
42. Shi, D., Wei, X., Li, L., Ren, Y., and Tan, W. (2022, January 18–24). End-to-end multi-person pose estimation with transformers. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.01079 ↗
43. Performance of optical flow techniques10.1007/BF01420984 ↗
44. Ferrari, V., Marin-Jimenez, M., and Zisserman, A. (2008, January 23–28). Progressive search space reduction for human pose estimation. Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, Alaska.10.1109/CVPR.2008.4587468 ↗
45. Articulated human detection with flexible mixtures of parts10.1109/TPAMI.2012.261 ↗
46. Andriluka, M., Pishchulin, L., Gehler, P., and Schiele, B. (2014, January 23–28). 2D human pose estimation: New benchmark and state of the art analysis. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.471 ↗
47. Sun, X., Shang, J., Liang, S., and Wei, Y. (2017, January 22–29). Compositional human pose regression. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.284 ↗
48. Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., and Zitnick, C.L. (2014, January 6–12). Microsoft coco: Common objects in context. Proceedings of the Computer Vision—ECCV 2014: 13th European Conference, Zurich, Switzerland. Part V.10.1007/978-3-319-10602-1_48 ↗
49. The pascal visual object classes VOC challenge10.1007/s11263-009-0275-4 ↗
50. Clustered pose and nonlinear appearance models for human pose estimation
51. Zhang, S.H., Li, R., Dong, X., Rosin, P., Cai, Z., Han, X., Yang, D., Huang, H., and Hu, S.M. (2019, January 15–20). Pose2seg: Detection free human instance segmentation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00098 ↗
52. Li, J., Wang, C., Zhu, H., Mao, Y., Fang, H.S., and Lu, C. (2019, January 15–20). Crowdpose: Efficient crowded scenes pose estimation and a new benchmark. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.01112 ↗
53. Geng, Y., Xu, W., Ma, B., Ma, Q., and Lin, D. (2023, January 18–22). Supplementary material for Human pose as compositional tokens [Supplemental material]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023), Vancouver, BC, Canada.10.1109/CVPR52729.2023.00071 ↗
54. Geng, Z., Wang, C., Wei, Y., Liu, Z., Li, H., and Hu, H. (2023, January 17–24). Human pose as compositional tokens. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.10.1109/CVPR52729.2023.00071 ↗
55. Cai, Y., Wang, Z., Luo, Z., Yin, B., Du, A., Wang, H., Zhang, X., Zhou, X., Zhou, E., and Sun, J. (2020, January 23–28). Learning delicate local representations for multi-person pose estimation. Proceedings of the Computer Vision—ECCV 2020: 16th European Conference, Glasgow, UK.10.1007/978-3-030-58580-8_27 ↗
56. Artacho, B., and Savakis, A. (2020, January 13–19). Unipose: Unified human pose estimation in single images and videos. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.00706 ↗
57. Li, W., Wang, Z., Yin, B., Peng, Q., Du, Y., Xiao, T., Yu, G., Lu, H., Wei, Y., and Sun, J. (2019). Rethinking on multi-stage networks for human pose estimation. arXiv.
58. Zhang, H., Ouyang, H., Liu, S., Qi, X., Shen, X., Yang, R., and Jia, J. (2019). Human pose estimation with spatial contextual information. arXiv.
59. Liu, H., Liu, F., Fan, X., and Huang, D. (2021). Polarized self-attention: Towards high-quality pixel-wise regression. arXiv.10.1016/j.neucom.2022.07.054 ↗
60. Towards high performance human keypoint detection10.1007/s11263-021-01482-8 ↗
61. Artacho, B., and Savakis, A. (2021). Omnipose: A multi-scale framework for multi-person pose estimation. arXiv.
62. Bulat, A., Kossaifi, J., Tzimiropoulos, G., and Pantic, M. (2020, January 16–20). Toward fast and accurate human pose estimation via soft-gated skip connections. Proceedings of the 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020), Buenos Aires, Argentina.10.1109/FG47880.2020.00014 ↗
63. Peng, X., Tang, Z., Yang, F., Feris, R.S., and Metaxas, D. (2008, January 23–28). Jointly optimize data augmentation and network training: Adversarial data augmentation in human pose estimation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, AK, USA.
64. Chou, C.J., Chien, J.T., and Chen, H.T. (2018, January 12–15). Self adversarial training for human pose estimation. Proceedings of the 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Honolulu, HI, USA.10.23919/APSIPA.2018.8659538 ↗
65. Zhou, M., Stoffl, L., Mathis, M.W., and Mathis, A. (2023, January 17–24). Rethinking pose estimation in crowds: Overcoming the detection information bottleneck and ambiguity. Proceedings of the IEEE/CVF International Conference on Computer Vision, Vancouver, BC, Canada.10.1109/ICCV51070.2023.01350 ↗
66. Jin, S., Li, S., Li, T., Liu, W., Qian, C., and Luo, P. (October, January 29). You only learn one query: Learning unified human query for single-stage multi-person multi-task human-centric perception. Proceedings of the Computer Vision—ECCV 2024: 18th European Conference, Milan, Italy.10.1007/978-3-031-72649-1_8 ↗
67. Wang, D., and Zhang, S. (2022, January 18–24). Contextual instance decoupling for robust multi-person pose estimation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.01078 ↗
68. Xie, Z., Geng, Z., Hu, J., Zhang, Z., Hu, H., and Cao, Y. (2023, January 18–22). Revealing the dark secrets of masked image modeling. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.10.1109/CVPR52729.2023.01391 ↗
69. Openpifpaf: Composite fields for semantic keypoint detection and spatio-temporal association10.1109/TITS.2021.3124981 ↗
70. Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., and Zagoruyko, S. (2020, January 23–28). End-to-end object detection with transformers. Proceedings of the Computer Vision—ECCV 2020: 16th European Conference, Glasgow, UK.10.1007/978-3-030-58452-8_13 ↗
71. He, K., Chen, X., Xie, S., Li, Y., Dollár, P., and Girshick, R. (2022, January 18–24). Masked autoencoders are scalable vision learners. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.01553 ↗
72. Xie, Z., Zhang, Z., Cao, Y., Lin, Y., Bao, J., Yao, Z., Dai, Q., and Hu, H. (2022, January 18–24). Simmim: A simple framework for masked image modeling. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.00943 ↗
73. He, K., Fan, H., Wu, Y., Xie, S., and Girshick, R. (2020, January 13–19). Momentum contrast for unsupervised visual representation learning. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.00975 ↗
74. Caron, M., Touvron, H., Misra, I., Jégou, H., Mairal, J., Bojanowski, P., and Joulin, A. (2021, January 20–25). Emerging properties in self-supervised vision transformers. Proceedings of the IEEE/CVF International Conference on Computer Vision, Nashville, TN, USA.10.1109/ICCV48922.2021.00951 ↗
75. Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., and Clark, J. (2021). Learning transferable visual models from natural language supervision. International Conference on Machine Learning, PmLR.
76. Oquab, M., Darcet, T., Moutakanni, T., Vo, H., Szafraniec, M., Khalidov, V., and Bojanowski, P. (2023). Dinov2: Learning robust visual features without supervision. arXiv.