Stroke2Sketch: Harnessing Stroke Attributes for Training-Free Sketch Generation
This addresses the problem of style-guided sketch generation for artists and designers, though it appears incremental as it builds on existing attention mechanisms.
The paper tackles the problem of generating sketches guided by reference styles by transferring stroke attributes like line thickness and texture sparsity while preserving semantic structure, resulting in a training-free framework that outperforms existing methods in expressive stroke control and semantic coherence.
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.