CoralStyleCLIP: Co-Optimized Region and Layer Selection for Image Editing

Abstract

Edit fidelity is a significant issue in open-world controllable generative image editing. Recently, CLIP-based approaches have traded off simplicity to alleviate these problems by introducing spatial attention in a handpicked layer of a StyleGAN. In this paper, we propose CoralStyleCLIP, which incorporates a multi-layer attention-guided blending strategy in the feature space of StyleGAN2 for obtaining high-fidelity edits. We propose multiple forms of our co-optimized region and layer selection strategy to demonstrate the variation of time complexity with the quality of edits over different architectural intricacies while preserving simplicity. We conduct extensive experimental analysis and benchmark our method against state-of-the-art CLIP-based methods. Our findings suggest that CoralStyleCLIP results in high-quality edits while preserving the ease of use.

Cite

Text

Revanur et al. "CoralStyleCLIP: Co-Optimized Region and Layer Selection for Image Editing." Conference on Computer Vision and Pattern Recognition, 2023. doi:10.1109/CVPR52729.2023.01221

Markdown

[Revanur et al. "CoralStyleCLIP: Co-Optimized Region and Layer Selection for Image Editing." Conference on Computer Vision and Pattern Recognition, 2023.](https://mlanthology.org/cvpr/2023/revanur2023cvpr-coralstyleclip/) doi:10.1109/CVPR52729.2023.01221

BibTeX

@inproceedings{revanur2023cvpr-coralstyleclip,
  title     = {{CoralStyleCLIP: Co-Optimized Region and Layer Selection for Image Editing}},
  author    = {Revanur, Ambareesh and Basu, Debraj and Agrawal, Shradha and Agarwal, Dhwanit and Pai, Deepak},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2023},
  pages     = {12695-12704},
  doi       = {10.1109/CVPR52729.2023.01221},
  url       = {https://mlanthology.org/cvpr/2023/revanur2023cvpr-coralstyleclip/}
}