Unsupervised Disentangling of Appearance and Geometry by Deformable Generator Network
Abstract
We present a deformable generator model to disentangle the appearance and geometric information in purely unsupervised manner. The appearance generator models the appearance related information, including color, illumination, identity or category, of an image, while the geometric generator performs geometric related warping, such as rotation and stretching, through generating displacement of the coordinates of each pixel to obtain the final image. Two generators act upon independent latent factors to extract disentangled appearance and geometric information from image. The proposed scheme is general and can be easily integrated into different generative models. An extensive set of qualitative and quantitative experiments show that the appearance and geometric information can be well disentangled, and the learned geometric generator can be conveniently transferred to the other image datasets to facilitate knowledge transfer tasks.
Cite
Text
Xing et al. "Unsupervised Disentangling of Appearance and Geometry by Deformable Generator Network." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019. doi:10.1109/CVPR.2019.01060Markdown
[Xing et al. "Unsupervised Disentangling of Appearance and Geometry by Deformable Generator Network." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.](https://mlanthology.org/cvpr/2019/xing2019cvpr-unsupervised/) doi:10.1109/CVPR.2019.01060BibTeX
@inproceedings{xing2019cvpr-unsupervised,
title = {{Unsupervised Disentangling of Appearance and Geometry by Deformable Generator Network}},
author = {Xing, Xianglei and Han, Tian and Gao, Ruiqi and Zhu, Song-Chun and Wu, Ying Nian},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2019},
doi = {10.1109/CVPR.2019.01060},
url = {https://mlanthology.org/cvpr/2019/xing2019cvpr-unsupervised/}
}