Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2312.04364 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917621349220352 |
|---|---|
| author | Chen, Dar-Yen Bhunia, Ayan Kumar Koley, Subhadeep Sain, Aneeshan Chowdhury, Pinaki Nath Song, Yi-Zhe |
| author_facet | Chen, Dar-Yen Bhunia, Ayan Kumar Koley, Subhadeep Sain, Aneeshan Chowdhury, Pinaki Nath Song, Yi-Zhe |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_04364 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | DemoCaricature: Democratising Caricature Generation with a Rough Sketch Chen, Dar-Yen Bhunia, Ayan Kumar Koley, Subhadeep Sain, Aneeshan Chowdhury, Pinaki Nath Song, Yi-Zhe Computer Vision and Pattern Recognition 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. |
| title | DemoCaricature: Democratising Caricature Generation with a Rough Sketch |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2312.04364 |