Human Pose Estimation and Transformation

V. Shylaja; B. J. Sowmya; M. Priya; Chetan Shetty; Nikitha Shetty Mangalore

doi:10.2991/978-94-6463-978-0_6

<Previous Article In Volume

Next Article In Volume>

Human Pose Estimation and Transformation

Authors

V. Shylaja¹^{, *}, B. J. Sowmya¹, M. Priya², Chetan Shetty³, Nikitha Shetty Mangalore⁴

¹Dept. of Artificial Intelligence and Data Science, Ramaiah Institute of Technology, Bengaluru, Karnataka, India

²Dept. of Artificial Intelligence and Machine Learning, Ramaiah Institute of Technology, Bengaluru, Karnataka, India

³Data Scientist, British Telecom, London, United Kingdom

⁴IBM, London, England

^*Corresponding author. Email: shylajav@msrit.edu

Corresponding Author

V. Shylaja

Available Online 31 December 2025.

DOI: 10.2991/978-94-6463-978-0_6 How to use a DOI?
Abstract: Human pose estimation and image transformation are active areas of research in computer vision with far-reaching applications in animation, gaming, healthcare, and virtual reality. We present a user-friendly system integrating pose detection and AI-based image transformation by using recent deep learning models (Stable Diffusion XL, SDXL, ControlNet). The process begins by estimating human body keypoints (joints, limbs) on an image using a pre-trained model like MediaPipe and generating a pose map that provides a structural layout. ControlNet is utilized in collaboration with SDXL to avoid generating all the way photoreal image then just x6 sd xl Src (b) pose figure m s e Total and Real GAN 10 C E Hz 40Hz 20Hz SDXL Generator Fig poses, but still utilizing the target input pose maps using post processing for person pose manipulation while keeping the identity, clothes etc.
Open Access: Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume

Next Article In Volume>

Volume Title: Proceedings of the 1st Engineering Data Analytics and Management Conference (EAMCON 2025)
Series: Advances in Engineering Research
Publication Date: 31 December 2025
ISBN: 978-94-6463-978-0
ISSN: 2352-5401
DOI: 10.2991/978-94-6463-978-0_6 How to use a DOI?
Open Access: Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

ris enw bib

TY  - CONF
AU  - V. Shylaja
AU  - B. J. Sowmya
AU  - M. Priya
AU  - Chetan Shetty
AU  - Nikitha Shetty Mangalore
PY  - 2025
DA  - 2025/12/31
TI  - Human Pose Estimation and Transformation
BT  - Proceedings of the 1st Engineering Data Analytics and Management Conference (EAMCON 2025)
PB  - Atlantis Press
SP  - 51
EP  - 59
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-978-0_6
DO  - 10.2991/978-94-6463-978-0_6
ID  - Shylaja2025
ER  -

download .riscopy to clipboard