Redirecting to original paper in 30 seconds...

Click below to go immediately or wait for automatic redirect

arxiv_cv 80% Match Research Paper Computer vision researchers,Artists,Graphic designers,AI developers in creative tools 2 weeks ago

Stroke2Sketch: Harnessing Stroke Attributes for Training-Free Sketch Generation

generative-ai › diffusion
📄 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
arXiv Category
cs.CV
arXiv PDF Code

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.

View Code on GitHub