Scholarlink

<p>Ancient mural restoration is a challenging conditional image-generation problem because of large missing regions, semantic ambiguity, and strict demands for cultural and stylistic fidelity. We present DiffuMural, a multi-stage, condition-guided diffusion framework for high-fidelity mural inpainting. DiffuMural integrates structure-aware conditional modeling for spatial supervision, multi-scale collaborative diffusion for progressive, context-adaptive synthesis, and frequency-domain refinement to recover fine texture and chromatic detail. Trained end-to-end with multimodal spatial and structural conditioning, it leverages a dataset from 25 Tang-dynasty caves in Dunhuang’s Mogao Grottoes and produces 650,000 multi-scale samples. Evaluation combines standard metrics (PSNR, SSIM, FID, LPIPS), bespoke consistency indicators, and an expert humanistic assessment. DiffuMural outperforms the strongest baseline, yielding a PSNR gain of + 2.3 dB, SSIM + 0.013, FID − 2.5, and LPIPS − 0.035, while achieving a humanistic score of 96.7. The framework provides a scalable, deployable solution for AI-driven mural restoration in resource-constrained cultural heritage settings.</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

DiffuMural: a diffusion model for dunhuang murals restoration via multi-scale convergence and cooperative guidance

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月20日

查看全文
  • Puyu Han,
  • Yuhang Pan,
  • Erting Pan,
  • Qunchao Jin,
  • Juntao Jiang,
  • Zeyu Zhang,
  • Zhichen Liu,
  • Jiaju Kang,
  • Luqi Gong

摘要

Ancient mural restoration is a challenging conditional image-generation problem because of large missing regions, semantic ambiguity, and strict demands for cultural and stylistic fidelity. We present DiffuMural, a multi-stage, condition-guided diffusion framework for high-fidelity mural inpainting. DiffuMural integrates structure-aware conditional modeling for spatial supervision, multi-scale collaborative diffusion for progressive, context-adaptive synthesis, and frequency-domain refinement to recover fine texture and chromatic detail. Trained end-to-end with multimodal spatial and structural conditioning, it leverages a dataset from 25 Tang-dynasty caves in Dunhuang’s Mogao Grottoes and produces 650,000 multi-scale samples. Evaluation combines standard metrics (PSNR, SSIM, FID, LPIPS), bespoke consistency indicators, and an expert humanistic assessment. DiffuMural outperforms the strongest baseline, yielding a PSNR gain of + 2.3 dB, SSIM + 0.013, FID − 2.5, and LPIPS − 0.035, while achieving a humanistic score of 96.7. The framework provides a scalable, deployable solution for AI-driven mural restoration in resource-constrained cultural heritage settings.