Dar-Yen Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Dar-Yen Chen has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
Aneeshan Sain
1 shared publicationAyan Kumar Bhunia
SketchX CVSSP University of Surrey United Kingdom
1 shared publication- Pinaki Nath Chowdhury
SketchX CVSSP University of Surrey United Kingdom
1 shared publication Subhadeep Koley
1 shared publication- Yi-Zhe Song
University of Surrey
1 shared publication
Latest Publications
- Open Access
DemoCaricature: Democratising Caricature Generation with a Rough Sketch
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.
Open AccessDemoCaricature: Democratising Caricature Generation with a Rough Sketch
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.