AI RESEARCH
High-Fidelity Mural Restoration via a Unified Hybrid Mask-Aware Transformer
arXiv CS.CV
•
ArXi:2604.03984v1 Announce Type: new 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.