A comprehensive dataset for digital restoration of Dunhuang murals

The MuralDH dataset is an invaluable digital resource developed for the
conservation and restoration of Dunhuang murals, which are
critical components of global cultural heritage facing threats from
degradation. This dataset comprises over 5000 high-resolution
images tailored to 512x512 pixels, emphasizing the preservation of mural
integrity and detail. It includes 1000 images with pixel-level
damage annotations for segmentation research and 500 images specially
processed for super-resolution studies, catering to a wide range
of digital restoration needs. While the primary focus of this work is the
dataset itself, we also introduce a supportive digital
restoration framework. This framework, which encompasses damage
segmentation, inpainting, and super-resolution techniques, serves
as a secondary validation of MuralDH’s utility and versatility. Through
MuralDH, technology revives ancient art, embodying the essence of
interdisciplinary innovation. By facilitating advanced research
in computer vision and artificial intelligence, MuralDH aims to
revolutionize the digital preservation practices for murals and
other cultural artifacts, demonstrating the critical role of
interdisciplinary collaboration in safeguarding our cultural legacy.

MuralDH数据集是为敦煌壁画保护与修复研发的珍贵数字资源。敦煌壁画作为全球文化遗产的核心组成部分，正面临着老化损毁的多重威胁。该数据集包含超过5000张分辨率适配512×512像素的高清图像，着重保障壁画原貌与细节的完整留存。其中涵盖1000张带有像素级损坏标注的图像，用于图像分割研究；另有500张经过特殊预处理的图像，适配超分辨率（Super-Resolution）研究场景，可满足多样化的数字修复研究需求。尽管本项工作的核心聚焦于数据集本身，研究团队同时推出了一套配套的数字修复框架。该框架涵盖损坏分割、图像补全（Inpainting）与超分辨率技术模块，可用于验证MuralDH数据集的实用性与多功能性。依托MuralDH数据集，科技得以重现古老艺术的光彩，彰显了跨学科创新的核心要义。通过推动计算机视觉与人工智能领域的前沿研究，MuralDH数据集旨在革新壁画及其他文化遗存的数字化保护实践，充分展现跨学科协作在守护人类文化遗产中的关键作用。

搜集汇总

背景与挑战

背景概述

MuralDH数据集是一个专为敦煌壁画数字修复设计的综合性资源，包含5000多张高分辨率图像，分为损坏标注、高质量图像和超分辨率研究三个子集。该数据集旨在支持计算机视觉和文化遗产保护的研究，并附带Python脚本和详细元数据，便于算法开发和测试。