.png){kind=icon}
.png){kind=icon}
Return
A Multi-Style Yi Script Font Generation Method Based on a Diffusion Model Incorporating Multi-Channel Attention Mechanism
.png){kind=icon}
PRE
AI
L
L
W
L
Z
DOI：10.1142/S0218001426590123.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The core of font generation technology lies in preserving character structure and accurately transferring stylistic features. While extensive research has been conducted on Chinese character generation, studies on Yi script font generation remain in their infancy. This paper, therefore, proposes a framework that employs a multi-scale conditional diffusion model to generate Yi script fonts. A Multi-scale Content Perception (MCP) module is designed. This module employs a constructed channel-space dual-domain multi-scale attention coordination mechanism to hierarchically capture multi-scale spatial and content information of characters within images. To achieve cross-modal feature fusion for Yi characters, an Efficient Style Insertion (ESI) module was developed. This module employs a cross-attention mechanism integrating multi-head mechanisms and Efficient Channel Attention (ECA) to enable cross-modal interaction of font style features. It further introduces block-wise attention to overcome computational redundancy issues inherent in traditional cross-attention. Finally, comparative experiments across Yi font datasets - including the Public Standardized Yi Font File (PSFF-Yi) dataset, Self-Built Handwritten Yi (SBHW-Yi) dataset, and Ancient Manuscript Handwritten Yi (AMHW-Yi) dataset - demonstrate the feasibility of this approach.
Keywords:
Yi script font generation
multi-scale conditional diffusion model
attention coordination mechanism
cross-modal feature fusion
cross-attention mechanism
Journal
IF:
1.1
Papers:
161
Citations:
2.0K
Organization
Cited Papers