A Robust Pose Transformational GAN for Pose Guided Person Image Synthesis
Abstract
Generating photorealistic images of human subjects in any unseen pose have crucial applications in generating a complete appearance model of the subject. However, from a computer vision perspective, this task becomes significantly challenging due to the inability of modelling the data distribution conditioned on pose. Existing works use a complicated pose transformation model with various additional features such as foreground segmentation, human body parsing etc. to achieve robustness that leads to computational overhead. In this work, we propose a simple yet effective pose transformation GAN by utilizing the Residual Learning method without any additional feature learning to generate a given human image in any arbitrary pose. Using effective data augmentation techniques and cleverly tuning the model, we achieve robustness in terms of illumination, occlusion, distortion and scale. We present a detailed study, both qualitative and quantitative, to demonstrate the superiority of our model over the existing methods on two large datasets.
- Publication:
-
arXiv e-prints
- Pub Date:
- January 2020
- DOI:
- 10.48550/arXiv.2001.01259
- arXiv:
- arXiv:2001.01259
- Bibcode:
- 2020arXiv200101259K
- Keywords:
-
- Computer Science - Computer Vision and Pattern Recognition;
- Computer Science - Machine Learning;
- Electrical Engineering and Systems Science - Image and Video Processing
- E-Print:
- Accepted in 7th National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG 2019)