MixSA: Training-free reference-based sketch extraction via Mixture-of-Self-Attention
Publication Type
Journal Article
Publication Date
9-2025
Abstract
Current sketch extraction methods either require extensive training or fail to capture a wide range of artistic styles, limiting their practical applicability and versatility. We introduce Mixture-of-Self-Attention (MixSA), a training-free sketch extraction method that leverages strong diffusion priors for enhanced sketch perception. At its core, MixSA employs a mixture-of-self-attention technique, which manipulates self-attention layers by substituting the keys and values with those from reference sketches. This allows for the seamless integration of brushstroke elements into initial outline images, offering precise control over texture density and enabling interpolation between styles to create novel, unseen styles. By aligning brushstroke styles with the texture and contours of colored images, particularly in late decoder layers handling local textures, MixSA addresses the common issue of color averaging by adjusting initial outlines. Evaluated with various perceptual metrics, MixSA demonstrates superior performance in sketch quality, flexibility, and applicability. This approach not only overcomes the limitations of existing methods but also empowers users to generate diverse, high-fidelity sketches that more accurately reflect a wide range of artistic expressions.
Keywords
Sketch extraction, image representations, image generation, image-to-image translation
Discipline
Graphics and Human Computer Interfaces | Software Engineering
Research Areas
Software and Cyber-Physical Systems
Publication
IEEE Transactions on Visualization and Computer Graphics
Volume
31
Issue
9
First Page
6208
Last Page
6222
ISSN
1077-2626
Identifier
10.1109/TVCG.2024.3502395
Publisher
Institute of Electrical and Electronics Engineers
Citation
YANG, Rui; WU, Xiaojun; and HE, Shengfeng.
MixSA: Training-free reference-based sketch extraction via Mixture-of-Self-Attention. (2025). IEEE Transactions on Visualization and Computer Graphics. 31, (9), 6208-6222.
Available at: https://ink.library.smu.edu.sg/sis_research/10533
Additional URL
https://doi.org/10.1109/TVCG.2024.3502395