Scholarlink

<p>Digital restoration of ancient murals is crucial for preserving cultural heritage. However, existing methods often suffer from semantic distortion and stylistic inconsistencies when repairing large damaged areas. This paper proposes M3SFormer, an innovative restoration framework. Built on an enhanced P-VQVAE module, it employs continuous feature modeling without quantization to retain details. A new Semantic-Style Consistency Module (SSCM) integrates regional semantics with multi-scale style features, ensuring coherent outputs. Furthermore, the Flow-Guided Refinement Module (FGRM) reconstructs key textures through network guidance, improving visual quality. Experiments on multiple benchmarks show that M3SFormer surpasses mainstream methods across all metrics, with significant gains in PSNR, SSIM, and LPIPS. It also excels in reconstructing complex structures and preserving styles under high mask coverage, offering a reliable solution for high-quality digital mural preservation. The dataset and code are available at: <a href="https://github.com/LPDLG/M3SFormer">https://github.com/LPDLG/M3SFormer</a></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

M3SFormer: multi-stage semantic and style-fused transformer for mural image inpainting

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月28日

查看全文
  • Qiyao Hu,
  • Qinfan Ge,
  • Yihan Zhang,
  • Xianlin Peng,
  • Jiangpeng Wang,
  • Shuyi Qu,
  • Nana Chen

摘要

Digital restoration of ancient murals is crucial for preserving cultural heritage. However, existing methods often suffer from semantic distortion and stylistic inconsistencies when repairing large damaged areas. This paper proposes M3SFormer, an innovative restoration framework. Built on an enhanced P-VQVAE module, it employs continuous feature modeling without quantization to retain details. A new Semantic-Style Consistency Module (SSCM) integrates regional semantics with multi-scale style features, ensuring coherent outputs. Furthermore, the Flow-Guided Refinement Module (FGRM) reconstructs key textures through network guidance, improving visual quality. Experiments on multiple benchmarks show that M3SFormer surpasses mainstream methods across all metrics, with significant gains in PSNR, SSIM, and LPIPS. It also excels in reconstructing complex structures and preserving styles under high mask coverage, offering a reliable solution for high-quality digital mural preservation. The dataset and code are available at: https://github.com/LPDLG/M3SFormer