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

2025-08-09

AI Summary

Digital mural restoration confronts dual challenges: complex degradation patterns and strict artistic authenticity constraints. Existing methods suffer from inconsistent mask guidance, leading to insufficient attention to damaged regions and degraded restoration quality. To address this, we propose a Context-aware Comprehensive Mask-Guided Network (CMG-Net). Our method introduces a Mask-Aware Upsampling/Downsampling module and a Collaborative Feature Aggregator to ensure consistent mask sensitivity across multi-scale features. Furthermore, CMG-Net integrates channel-wise feature selection, mask-guided feature fusion, and multi-scale feature extraction to jointly recover global structure and fine-grained texture. Evaluated on standard benchmark datasets, CMG-Net achieves significant improvements over state-of-the-art methods, demonstrating superior structural integrity and enhanced fidelity of artistic details.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Multimodal Learning
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

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}.

Problem

• Digital mural restoration faces complex degradation challenges.
• Existing methods lack consistent mask guidance for damaged regions.
• CMAMRNet improves restoration with mask-aware multi-scale feature extraction.

Innovation

• Mask-Aware Up/Down-Sampler for consistent mask sensitivity
• Co-Feature Aggregator for multi-scale feature extraction
• Comprehensive mask guidance enhancing damaged region focus