# Ancient Mural Restoration

2 related articles

Subscribe to updates

researchsquare.com Oct 16, 2026
Mural restoration stops asking only where damage is: a continuous severity field lifts PSNR by 3.27 dB
Fading, stains and water marks on Dunhuang murals are semi-transparent damage that still leaves pigment and contours visible, yet a binary mask marks only where damage lies and cannot describe how severity varies inside that region. SC-PAD estimates a continuous terminal severity field from the degraded image and a coarse mask, reparameterizes a shared diffusion progress into pixel-wise local restoration progress, and drives image-space residual activation through a dynamic Alpha state with consistent endpoints and monotonic evolution. On a fixed 100-image test split, replacing the binary mask with predicted soft Alpha raised PSNR from 27.3421 dB to 30.6122 dB, while ground-truth Alpha added a further 3.2539 dB, marking severity estimation as the remaining bottleneck.
Fading, stains and water marks on Dunhuang murals are semi-transparent damage that still leaves pigment and contours visible, yet a binary mask marks only where damage lies and cannot describe how severity varies inside that region. SC-PAD estimates a continuous terminal severity field from the degraded image and a coarse mask, reparameterizes a shared diffusion progress into pixel-wise local restoration progress, and drives image-space residual activation through a dynamic Alpha state with consistent endpoints and monotonic evolution. On a fixed 100-image test split, replacing the binary mask with predicted soft Alpha raised PSNR from 27.3421 dB to 30.6122 dB, while ground-truth Alpha added a further 3.2539 dB, marking severity estimation as the remaining bottleneck.
Gansu Academy of Sciences Lanzhou University of Arts and Science Lanzhou University of Technology
Wu Yu（First author）Lei Zhang（Corresponding author）Erchao Li（Corresponding author）
SC-PAD Ancient Mural Restoration Diffusion Model Residual Diffusion Degradation Severity Estimation
researchsquare.com Oct 15, 2026
Mural restoration moves diffusion into the wavelet domain: 32.04 dB PSNR and inference cut from 35.31 to 9.56 seconds
Digital restoration of Dunhuang murals no longer denoises only in pixel space. Pixel-domain diffusion must handle global structure and local brushwork at once, which is costly and can drift in color and style. WDCRF first applies a 2D discrete wavelet transform to split a damaged mural into one low-frequency and three high-frequency subbands, then lets a conditional diffusion model rebuild all four coefficient sets directly in the wavelet domain, using the damaged coefficients themselves as the conditioning signal, and finally synthesizes the image by inverse wavelet transform. On the Dunhuang Mural dataset it reaches 32.04 dB PSNR and 0.922 SSIM, ahead of EdgeConnect, WaveDiff, PGRDiff and LRDiff; on DhMurals it reaches 18.95 dB PSNR and 0.7598 SSIM.
Digital restoration of Dunhuang murals no longer denoises only in pixel space. Pixel-domain diffusion must handle global structure and local brushwork at once, which is costly and can drift in color and style. WDCRF first applies a 2D discrete wavelet transform to split a damaged mural into one low-frequency and three high-frequency subbands, then lets a conditional diffusion model rebuild all four coefficient sets directly in the wavelet domain, using the damaged coefficients themselves as the conditioning signal, and finally synthesizes the image by inverse wavelet transform. On the Dunhuang Mural dataset it reaches 32.04 dB PSNR and 0.922 SSIM, ahead of EdgeConnect, WaveDiff, PGRDiff and LRDiff; on DhMurals it reaches 18.95 dB PSNR and 0.7598 SSIM.
Shaoxing University Nanfang College Guangzhou Beijing International Studies University
Shengdong Zhang（First author）Wenwen Sun（Corresponding author）Zhe Yuan（Corresponding author）
Wavelet-Diffusion Collaborative Restoration Framework Wavelet-Domain Diffusion Ancient Mural Restoration Conditional Diffusion Model Discrete Wavelet Transform

You’re all caught up

Mural restoration stops asking only where damage is: a continuous severity field lifts PSNR by 3.27 dB

Mural restoration moves diffusion into the wavelet domain: 32.04 dB PSNR and inference cut from 35.31 to 9.56 seconds