Authors : Dr. Suresh Babu Chandolu; Tejaswi Nandeti; Dimpul Deepthi Pippalla; Gundareddy Gali Reddy; Yallamalli Sasi Vadana Rao; Mohammad Raheem

Volume/Issue : Volume 10 - 2025, Issue 3 - March

---

Google Scholar : https://tinyurl.com/twsfzwfr

Scribd : https://tinyurl.com/4cjsr7xb

DOI : https://doi.org/10.38124/ijisrt/25mar2007

Google Scholar

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 15 to 20 days to display the article.

---

Abstract : This work presents a novel framework for personal image generation by transferring poses from a target image to a source image. Using a Pose Attention Transfer (PAT) network, our approach synthesizes realistic images of a person in the target pose while preserving identity and appearance details from the source image. The PAT network leverages attention mechanisms to focus on key regions, ensuring accurate pose transfer and high-quality texture preservation. Experimental results demonstrate that our method generates visually coherent and realistic images, outperforming existing state-of-the-art techniques. This framework has significant potential for virtual try-on, animation, and video synthesis applications.

Keywords : Pose Image Generation, Pose Attention Transfer Network (PATN), Generative Adversarial Network (GAN).

References :

1. Mihai Zanfir, Alin-Ionut Popa, Andrei Zanfir, and Cristian Sminchisescu. Human appearance transfer. In Proc. CVPR, pages 5391–5399, 2018.
2. Bo Zhao, Xiao Wu, Zhi-Qi Cheng, Hao Liu, and Jiashi Feng. Multi-view image generation from a single-view. CoRR, abs/1704.04886, 2017.
3. Liang Zheng, Liyue Shen, Lu Tian, Shengjin Wang, Jing dong Wang, and Qi Tian. Scalable person re-identification: A benchmark. In Proc. ICCV, pages 1116–1124, 2015.
4. Liang Zheng, Yi Yang, and Alexander G. Hauptmann. Person re-identification: Past, present and future. CoRR, abs/1610.02984, 2016.
5. Zhedong Zheng, Liang Zheng, and Yi Yang. Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. In Proc. ICCV, pages 3774–3782, 2017.
6. Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei A. Efros. Unpaired image-to-image translation using cycle consistent adversarial networks. In Proc. ICCV, pages 2242–2251, 2017.
7. Sergey Ioffe and Christian Szegedy. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Proc. ICML, pages 448–456, 2015.
8. Liqian Ma, Qianru Sun, Stamatios Georgoulis, Luc Van Gool, Bernt Schiele, and Mario Fritz. Disentangled person image generation. CoRR, abs/1712.02621, 2017.
9. Andrew L Maas, Awni Y Hannun, and Andrew Y Ng. Recti-fier nonlinearities improve neural network acoustic models. In Proc. ICML, volume 30, page 3, 2013.
10. Liang Mei, Jingen Liu, Alfred O. Hero III, and Silvio Savarese. Robust object pose estimation via statistical mani fold modeling. In Proc. ICCV, pages 967–974, 2011.
11. Mehdi Mirza and Simon Osindero. Conditional generative adversarial nets. CoRR, abs/1411.1784, 2014.
12. Vinod Nair and Geoffrey E. Hinton. Rectified linear units improve restricted boltzmann machines. In Proc. ICML, pages 807–814, 2010.
13. Natalia Neverova, Riza Alp Guler, and Iasonas Kokkinos.Dense pose transfer. arXiv preprint arXiv:1809.01995, 2018.
14. Augustus Odena, Christopher Olah, and Jonathon Shlens. Conditional image synthesis with auxiliary classifier gans. In Proc. ICML, pages 2642–2651, 2017.
15. Albert Pumarola, Antonio Agudo, Alberto Sanfeliu, and Francesc Moreno-Noguer. Unsupervised person image synthesis in arbitrary poses. In Proc. CVPR, pages 8620–8628, 2018.
16. Alec Radford, Luke Metz, and Soumith Chintala. Un supervised representation learning with deep convolu tional generative adversarial networks. arXiv preprint arXiv:1511.06434, 2015.
17. Amit Raj, Patsorn Sangkloy, Huiwen Chang, James Hays, Duygu Ceylan, and Jingwan Lu. Swapnet: Image based garment transfer. In Proc. ECCV, pages 679–695, 2018.
18. Aliaksandr Siarohin, Enver Sangineto, Stephane Lathuili ´ ere, ` and Nicu Sebe. Deformable gans for pose-based human image generation. CoRR, abs/1801.00055, 2018.
19. Zhen Zhu , Tengteng Huang, Baoguang Shi , Miao Yu , Bofei Wang and  Xiang Bai . Progressive Pose Attention Transfer for Person Image Generation.arXiv:1904.03349v3,2019.