Scholarlink

<p>Modeling structured artistic images with complex patterns remains a challenge in style transfer. Thangka art, featuring intricate iconography and long-range spatial composition, serves as an ideal benchmark. We propose Dynamic Adaptive Convolution and Global Dependency Attention (DAG-Style Attention), an end-to-end framework. It features a Dynamic Adaptive Convolution (DAConv) module that dynamically allocates multi-scale kernels to extract features from complex, irregularly sized objects. Concurrently, the Global Dependency Perceptual Attention (GDPAttention) module models long-range semantic correlations to prevent structural distortion and ensure stylistic consistency. Experiments on Thangka and WikiArt datasets demonstrate our framework’s superiority. On 512 × 512 Thangka images, it achieves 14.186 dB PSNR and 0.517 SSIM, outperforming the strongest baseline (ASFNet) while exhibiting superior visual fidelity. Ultimately, this approach provides a robust tool for cultural heritage preservation via precise digital reconstructions.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

DAG-style attention: dynamic adaptive convolution and global dependency attention for Thangka artistic stylization

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月15日

查看全文
  • Yunbo Yang,
  • Nianyi Wang,
  • Zhen Wang,
  • Xinyang Zhang,
  • Mengyuan Zhang,
  • Yutong Wang

摘要

Modeling structured artistic images with complex patterns remains a challenge in style transfer. Thangka art, featuring intricate iconography and long-range spatial composition, serves as an ideal benchmark. We propose Dynamic Adaptive Convolution and Global Dependency Attention (DAG-Style Attention), an end-to-end framework. It features a Dynamic Adaptive Convolution (DAConv) module that dynamically allocates multi-scale kernels to extract features from complex, irregularly sized objects. Concurrently, the Global Dependency Perceptual Attention (GDPAttention) module models long-range semantic correlations to prevent structural distortion and ensure stylistic consistency. Experiments on Thangka and WikiArt datasets demonstrate our framework’s superiority. On 512 × 512 Thangka images, it achieves 14.186 dB PSNR and 0.517 SSIM, outperforming the strongest baseline (ASFNet) while exhibiting superior visual fidelity. Ultimately, this approach provides a robust tool for cultural heritage preservation via precise digital reconstructions.