A comprehensive dataset for digital restoration of Dunhuang murals

MuralDH Brief Summary The MuralDH dataset is a comprehensive collection of high-quality images for the digital restoration of Dunhuang murals. It includes over 5000 pre-processed images, curated to support research in digital art restoration, computer vision, and cultural heritage preservation. This dataset is divided into segments including damaged mural segmentation, high-resolution mural images, and images processed for super-resolution studies. The collection, designed to assist in the development and testing of digital restoration algorithms, aims to bridge traditional art with modern technology, ensuring the longevity and accessibility of these invaluable cultural treasures.Description of the Data and File Structure The dataset is structured as follows:Damaged Mural Segmentation Dataset: 1000 images annotated for specific types of damage such as cracks, flaking, and fading. Each file is named according to its specific damage type and contains annotations at the pixel level. High-Quality Mural Images: 500 images, each prepared for super-resolution processing. These are lower-resolution images that have been downscaled from the original high-resolution scans. Super-Resolution Dataset: A subset of the High-Quality Mural Images that have been further processed for super-resolution studies. Each image file is stored in PNG format, ensuring high-quality, lossless compression. Files are organized in folders corresponding to their dataset segment, and filenames follow a consistent naming convention to indicate their content and purpose.Missing data or incomplete images are marked with a specific code (e.g., NA for not available) in the accompanying metadata file. This file also provides a detailed description of each image, including its original location, the period it depicts, and any relevant historical or cultural notes.Sharing/Access Information The MuralDH dataset is hosted on Dryad but can also be accessed through the following link for direct download and further information:Data Derivation Sources This dataset was compiled from various sources, including digital archives and collaborations with cultural heritage organizations. Each image has been carefully selected and processed to meet the research needs while adhering to copyright and preservation guidelines.Code/Software The dataset comes with a set of Python scripts for basic image processing tasks, including image resizing, format conversion, and initial analysis.

MuralDH 数据集简要说明
MuralDH数据集是用于敦煌壁画数字化修复的高质量图像综合集合，包含超过5000张经过精心遴选与预处理的图像，旨在为数字艺术修复、计算机视觉以及文化遗产保护领域的研究提供支撑。本数据集分为多个细分板块，涵盖受损壁画分割数据集、高分辨率壁画图像集，以及用于超分辨率（Super-Resolution）研究的处理后图像集。该数据集旨在助力数字修复算法的开发与测试，搭建传统艺术与现代技术的桥梁，保障这些珍贵文化瑰宝的长久留存与可及性。

数据与文件结构说明
本数据集结构如下：
受损壁画分割数据集：包含1000张针对裂纹、剥落、褪色等特定损伤类型完成标注的图像，每个文件以其对应的损伤类型命名，并附带像素级标注信息。
高质量壁画图像集：共500张用于超分辨率处理的图像，均由原始高分辨率扫描图像下采样得到的低分辨率图像。
超分辨率数据集：该子集源自高质量壁画图像集，经过进一步处理以适配超分辨率研究需求。所有图像文件均采用PNG格式存储，以实现高质量无损压缩。
文件按照所属数据集细分板块组织于不同文件夹中，文件名遵循统一命名规范，可直观反映其内容与用途。
缺失数据或不完整图像会在配套元数据文件中以特定代码（如代表不可用的NA）标记，该元数据文件还会详细描述每张图像的原始存放位置、所描绘的历史时期，以及相关历史文化背景信息。

共享与获取说明
MuralDH数据集托管于Dryad平台，同时可通过以下链接直接下载并获取更多相关信息：

数据来源说明
本数据集整合自多个来源，包括数字档案库以及与文化遗产保护机构的合作项目。所有图像均经过严格筛选与预处理，以满足研究需求，同时严格遵循版权与文物保护相关规范。

代码与软件工具
本数据集附带一套用于基础图像处理任务的Python脚本，涵盖图像尺寸调整、格式转换以及初步分析等功能。

搜集汇总

背景与挑战

背景概述

该数据集是一个专门用于敦煌壁画数字修复的综合图像集合，包含超过5000张高质量预处理图像，分为损坏壁画分割、高质量壁画和超分辨率研究三个部分，旨在支持文化遗产保护、计算机视觉和数字艺术修复算法的开发与测试。数据集以PNG格式存储，附带元数据描述和Python处理脚本，由多个来源编译而成，并遵循版权和保存指南。