CMAMRNet: A Contextual Mask-Aware Network Enhancing Mural Restoration Through Comprehensive Mask Guidance


Yingtie Lei (University of Macau), Fanghai Yi (Guangdong University of Technology), Yihang Dong (University of Chinese Academy of Sciences), Weihuang Liu (University of Macau), Xiaofeng Zhang (Shanghai Jiao Tong University), Zimeng Li (Shenzhen Polytechnic University), Chi-Man Pun (University of Macau), Xuhang Chen (University of Macau)
The 35th British Machine Vision Conference
PDFPosterVideo (Right click to download)

Abstract

Murals, as invaluable cultural artifacts, face continuous deterioration from environmental factors and human activities. Digital restoration of murals faces unique challenges due to their complex degradation patterns and the critical need to preserve artistic authenticity. Existing learning-based methods struggle with maintaining consistent mask guidance throughout their networks, leading to insufficient focus on damaged regions and compromised restoration quality. We propose CMAMRNet, a Contextual Mask-Aware Mural Restoration Network that addresses these limitations through comprehensive mask guidance and multi-scale feature extraction. Our framework introduces two key component: (1) the Mask-Aware Up/Down-Sampler (MAUDS), which ensures consistent mask sensitivity across resolution scales through dedicated channel-wise feature selection and mask-guided feature fusion; and (2) the Co-Feature Aggregator (CFA), operating at both the highest and lowest resolutions to extract complementary features for capturing fine textures and global structures in degraded regions. Experimental results on benchmark datasets demonstrate that CMAMRNet outperforms state-of-the-art methods, effectively preserving both structural integrity and artistic details in restored murals. The code is available at https://github.com/CXH-Research/CMAMRNet.

Citation

@inproceedings{Lei_2025_BMVC,
author    = {Yingtie Lei and Fanghai Yi and Yihang Dong and Weihuang Liu and Xiaofeng Zhang and Zimeng Li and Chi-Man Pun and Xuhang Chen},
title     = {CMAMRNet: A Contextual Mask-Aware Network Enhancing Mural Restoration Through Comprehensive Mask Guidance},
booktitle = {36th British Machine Vision Conference 2025, {BMVC} 2025, Sheffield, UK, November 24-27, 2025},
publisher = {BMVA},
year      = {2025},
url       = {https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_59/paper.pdf}
}


Copyright © 2025 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection