Scholarlink

<p>Ancient murals, as valuable cultural heritage, preserve records of historical life and beliefs. To document and preserve these legacies, image segmentation algorithms are essential. This paper proposes a novel framework for fine-grained semantic segmentation of mythological figures and ornaments in murals, featuring an M-ViT Encoder and a Pyramid SCconv Decoder. The M-ViT Encoder incorporates a selective state-space model in the transformer units, mitigating correlations in sequential representations by building long-range dependencies, thus capturing local and global semantic information. The Pyramid SCconv Decoder reduces spatial and channel redundancy by applying separative transformations to encoder outputs, enhancing semantic feedback for fine-grained information separation. Experiments on fine-grained semantic segmentation of colored mural figures demonstrate that the proposed method outperforms other segmentation baselines, achieving 68.42% mIoU and 74.59% mAcc, and delivering state-of-the-art performance.</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

A Mamba based vision transformer for fine grained image segmentation of mural figures

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年5月22日

查看全文
  • Qi Zhang,
  • Guohua Geng,
  • Pengbo Zhou,
  • Longquan Yan,
  • Mingquan Zhou,
  • Zhaodi Li,
  • Yangyang Liu

摘要

Ancient murals, as valuable cultural heritage, preserve records of historical life and beliefs. To document and preserve these legacies, image segmentation algorithms are essential. This paper proposes a novel framework for fine-grained semantic segmentation of mythological figures and ornaments in murals, featuring an M-ViT Encoder and a Pyramid SCconv Decoder. The M-ViT Encoder incorporates a selective state-space model in the transformer units, mitigating correlations in sequential representations by building long-range dependencies, thus capturing local and global semantic information. The Pyramid SCconv Decoder reduces spatial and channel redundancy by applying separative transformations to encoder outputs, enhancing semantic feedback for fine-grained information separation. Experiments on fine-grained semantic segmentation of colored mural figures demonstrate that the proposed method outperforms other segmentation baselines, achieving 68.42% mIoU and 74.59% mAcc, and delivering state-of-the-art performance.