Technology Category
Computer Vision: Diffusion Models for VisionMachine Learning: Large Multimodal Models (LMMs)Natural Language Processing: Safety and Robustness
High-Fidelity Mural Restoration via a Unified Hybrid Mask-Aware Transformer
🤖 AI Summary
Ancient murals frequently suffer from large-scale missing regions due to environmental erosion, aging, and human-induced damage, necessitating restoration methods that preserve both global structural coherence and local textural fidelity. To address this challenge, this work proposes a Hybrid Mask-Aware Transformer (HMAT) framework that innovatively integrates mask-aware dynamic filtering with a Transformer bottleneck architecture. A mask-conditioned style fusion module is introduced to dynamically guide the inpainting process, while a teacher-forced decoder equipped with hard-gated skip connections effectively safeguards intact regions of the original mural. Experimental results demonstrate that HMAT significantly outperforms state-of-the-art methods on the DHMural and Jiuse Deer datasets, achieving superior performance in terms of structural consistency and visual realism.
Technology Category
Application Category
📝 Abstract
Ancient murals are valuable cultural artifacts, but many have suffered severe degradation due to environmental exposure, material aging, and human activity. Restoring these artworks is challenging because it requires both reconstructing large missing structures and strictly preserving authentic, undamaged regions. This paper presents the Hybrid Mask-Aware Transformer (HMAT), a unified framework for high-fidelity mural restoration. HMAT integrates Mask-Aware Dynamic Filtering for robust local texture modeling with a Transformer bottleneck for long-range structural inference. To further address the diverse morphology of degradation, we introduce a mask-conditional style fusion module that dynamically guides the generative process. In addition, a Teacher-Forcing Decoder with hard-gated skip connections is designed to enforce fidelity in valid regions and focus reconstruction on missing areas.
We evaluate HMAT on the DHMural dataset and a curated Nine-Colored Deer dataset under varying degradation levels. Experimental results demonstrate that the proposed method achieves competitive performance compared to state-of-the-art approaches, while producing more structurally coherent and visually faithful restorations. These findings suggest that HMAT provides an effective solution for the digital restoration of cultural heritage murals.
Problem
Research questions and friction points this paper is trying to address.
mural restoration
cultural heritage
image inpainting
degradation
high-fidelity reconstruction
Innovation
Methods, ideas, or system contributions that make the work stand out.
Mask-Aware Transformer
Mural Restoration
Dynamic Filtering
Style Fusion
Teacher-Forcing Decoder
🔎 Similar Papers
No similar papers found.
