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

TL;DR

CMAMRNet is a novel mural restoration network that employs comprehensive mask guidance and multi-scale feature extraction to improve restoration quality and preserve artistic authenticity.

Contribution

The paper introduces CMAMRNet, featuring the Mask-Aware Up/Down-Sampler and Co-Feature Aggregator, which enhance focus on damaged regions and capture fine textures and global structures.

Findings

Outperforms state-of-the-art methods on benchmark datasets.

Effectively preserves structural integrity and artistic details.

Demonstrates robustness across various degradation patterns.

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 components: (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~\href{https://github.com/CXH-Research/CMAMRNet}{https://github.com/CXH-Research/CMAMRNet}.