Re-Identification Supervised Texture Generation

Jian Wang, Yunshan Zhong, Yachun Li, Chi Zhang, Yichen Wei; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 11846-11856

Abstract


The estimation of 3D human body pose and shape from a single image has been extensively studied in recent years. However, the texture generation problem has not been fully discussed. In this paper, we propose an end-to-end learning strategy to generate textures of human bodies under the supervision of person re-identification. We render the synthetic images with textures extracted from the inputs and maximize the similarity between the rendered and input images by using the re-identification network as the perceptual metrics. Experiment results on pedestrian images show that our model can generate the texture from a single image and demonstrate that our textures are of higher quality than those generated by other available methods. Furthermore, we extend the application scope to other categories and explore the possible utilization of our generated textures.

Related Material


[pdf]
[bibtex]
@InProceedings{Wang_2019_CVPR,
author = {Wang, Jian and Zhong, Yunshan and Li, Yachun and Zhang, Chi and Wei, Yichen},
title = {Re-Identification Supervised Texture Generation},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}