- Version
- Download 57
- File Size 821.60 KB
- File Count 1
- Create Date 16/12/2023
- Last Updated 16/12/2023
Appearance and Pose-Conditioned Human photograph generation using Deformable GANs
Appearance and Pose-Conditioned Human photograph generation using Deformable GANs
Siddharth Panda1, Shivansh Charak2, Vaibhavee Gadhave3, V. Vanlalhruaitlunga4, Prof. Noshir Tarapore5
1LY B.Tech, Computer Engineering, Science & Technology, VishwakarmaUniversity, Pune.
2LY B.Tech, Computer Engineering, Science & Technology, VishwakarmaUniversity, Pune.
3LY B.Tech, Computer Engineering, Science & Technology, VishwakarmaUniversity, Pune.
4LY B.Tech, Computer Engineering, Science & Technology, VishwakarmaUniversity, Pune.
5LY Assistant Professor of Computer Engineering, Vishwakarma University, Pune
Abstract— In this study, we address the challenge of generating images of individuals based on pose and appearance data. Specifically, we take an image, xa, of an individual and a target pose, P (xb), extracted from another image, xb. We then generate a new image of the same individual in the target pose, P (xb), while preserving the visual details from xa.
To manage pixel-to-pixel misalignments caused by pose differences between P (xa) and P (xb), we incorporate deformable skip connections in our Generative Adversarial Network’s generator. Additionally, we propose a nearest-neighbour loss as an alternative to the standard L1 and L2 losses to match the texture of the generated image with the target image.
Our approach demonstrates competitive quantitative and qualitative results using standard datasets and protocols recently proposed for this task. We also carry out a comprehensive evaluation using off-the-shelf person-identification (Re-id) systems trained with person-generation-based augmented data, a key application for this task.
Our experiments reveal that our Deformable GANs can significantly boost Re-id accuracy, surpassing data-augmentation techniques specifically trained using Re-identification losses.
index Terms—Conditional GAN, Image Generation, Deformable Objects, Human Pose.
