PaintInStyle: One-Shot Discovery of Interpretable Directions by Painting
Abstract
The search for interpretable directions in latent spaces of pre-trained Generative Adversarial Networks (GANs) has become a topic of interest. These directions can be utilized to perform semantic manipulations on the GAN generated images. The discovery of such directions is performed either in a supervised way, which requires manual annotation or pre-trained classifiers, or in an unsupervised way, which requires the user to interpret what these directions represent. In this work, we propose a framework that finds a specific manipulation direction using only a single simple sketch drawn on an image. Our method finds directions consisting of channels in the style space of the StyleGAN2 architecture responsible for the desired edits and performs image manipulations comparable with state-of-the-art methods.
Cite
Text
Doner et al. "PaintInStyle: One-Shot Discovery of Interpretable Directions by Painting." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022. doi:10.1109/CVPRW56347.2022.00254Markdown
[Doner et al. "PaintInStyle: One-Shot Discovery of Interpretable Directions by Painting." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022.](https://mlanthology.org/cvprw/2022/doner2022cvprw-paintinstyle/) doi:10.1109/CVPRW56347.2022.00254BibTeX
@inproceedings{doner2022cvprw-paintinstyle,
title = {{PaintInStyle: One-Shot Discovery of Interpretable Directions by Painting}},
author = {Doner, Berkay and Balcioglu, Elif Sema and Barin, Merve Rabia and Kocasari, Umut and Tiftikci, Mert and Yanardag, Pinar},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2022},
pages = {2287-2292},
doi = {10.1109/CVPRW56347.2022.00254},
url = {https://mlanthology.org/cvprw/2022/doner2022cvprw-paintinstyle/}
}