DemoCaricature: Democratising Caricature Generation with a Rough Sketch
Abstract
In this paper we democratise caricature generation empowering individuals to effortlessly craft personalised caricatures with just a photo and a conceptual sketch. Our objective is to strike a delicate balance between abstraction and identity while preserving the creativity and subjectivity inherent in a sketch. To achieve this we present Explicit Rank-1 Model Editing alongside single-image personalisation selectively applying nuanced edits to cross-attention layers for a seamless merge of identity and style. Additionally we propose Random Mask Reconstruction to enhance robustness directing the model to focus on distinctive identity and style features. Crucially our aim is not to replace artists but to eliminate accessibility barriers allowing enthusiasts to engage in the artistry.
Cite
Text
Chen et al. "DemoCaricature: Democratising Caricature Generation with a Rough Sketch." Conference on Computer Vision and Pattern Recognition, 2024. doi:10.1109/CVPR52733.2024.00824Markdown
[Chen et al. "DemoCaricature: Democratising Caricature Generation with a Rough Sketch." Conference on Computer Vision and Pattern Recognition, 2024.](https://mlanthology.org/cvpr/2024/chen2024cvpr-democaricature/) doi:10.1109/CVPR52733.2024.00824BibTeX
@inproceedings{chen2024cvpr-democaricature,
title = {{DemoCaricature: Democratising Caricature Generation with a Rough Sketch}},
author = {Chen, Dar-Yen and Bhunia, Ayan Kumar and Koley, Subhadeep and Sain, Aneeshan and Chowdhury, Pinaki Nath and Song, Yi-Zhe},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2024},
pages = {8629-8639},
doi = {10.1109/CVPR52733.2024.00824},
url = {https://mlanthology.org/cvpr/2024/chen2024cvpr-democaricature/}
}