Progressive enhancement and restoration for mural images under low-light and defected conditions based on multi-receptive field strategy

TL;DR

This paper introduces MER, a two-stage model that enhances and restores damaged ancient murals captured in low-light conditions, improving visual quality and facilitating batch restoration at archaeological sites.

Contribution

The paper presents a novel two-stage restoration model with automatic defect detection tailored for low-light, damaged murals, advancing digital restoration techniques.

Findings

Enhanced visual quality of mural images

Achieved superior metric evaluation results

Supported batch restoration at archaeological sites

Abstract

Ancient murals are valuable cultural heritage with great archaeological value. They provide insights into ancient religions, ceremonies, folklore, among other things through their content. However, due to long-term oxidation and inadequate protection, ancient murals have suffered continuous damage, including peeling and mold etc. Additionally, since ancient murals were typically painted indoors, the light intensity in images captured by digital devices is often low. The poor visibility hampers the further restoration of damaged areas. To address the escalating damage to ancient murals and facilitate batch restoration at archaeological sites, we propose a two-stage restoration model with automatic defect area detection strategy which called MER(Mural Enhancement and Restoration net) for ancient murals that are damaged and have been captured in low light. Our two-stage model not only enhances the visual quality of restored images but also achieves commendable results in relevant metric evaluations compared with other competitors. Furthermore, we have launched a website dedicated to the restoration of ancient mural paintings, utilizing the proposed model. Code is available at https://gitee.com/bbfan2024/MER.git.