.png){kind=icon}
.png){kind=icon}
Return
Sketch diffusion: A sketch-drawing optimization method via diffusion model
.png){kind=icon}
PRE
AI
DOI：10.1016/j.imavis.2026.106106.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Proposed novel feature extraction to separate content and sketch traits in portrait sketches. • Developed three-stage training with contrastive learning and feature loss. • Preserves sketches enhancing framework, overcoming current AI limitations in art guidance. • Built large-scale dataset to resolve scarcity and inconsistency in sketch research.