Redirecting to original paper in 30 seconds...
Click below to go immediately or wait for automatic redirect
📄 Abstract
Abstract: Generating sketches guided by reference styles requires precise transfer of
stroke attributes, such as line thickness, deformation, and texture sparsity,
while preserving semantic structure and content fidelity. To this end, we
propose Stroke2Sketch, a novel training-free framework that introduces
cross-image stroke attention, a mechanism embedded within self-attention layers
to establish fine-grained semantic correspondences and enable accurate stroke
attribute transfer. This allows our method to adaptively integrate reference
stroke characteristics into content images while maintaining structural
integrity. Additionally, we develop adaptive contrast enhancement and
semantic-focused attention to reinforce content preservation and foreground
emphasis. Stroke2Sketch effectively synthesizes stylistically faithful sketches
that closely resemble handcrafted results, outperforming existing methods in
expressive stroke control and semantic coherence. Codes are available at
https://github.com/rane7/Stroke2Sketch.
Authors (5)
Rui Yang
Huining Li
Yiyi Long
Xiaojun Wu
Shengfeng He
Submitted
October 18, 2025
Key Contributions
Proposes Stroke2Sketch, a novel training-free framework for sketch generation that uses cross-image stroke attention to transfer stroke attributes (line thickness, deformation, texture) while preserving semantic structure. It also incorporates adaptive contrast enhancement and semantic-focused attention for better content preservation.
Business Value
Provides artists and designers with powerful, intuitive tools for generating high-quality sketches and stylized images, accelerating creative workflows and enabling new forms of digital art.