Tomb Murals Research Articles

Dadnet: dual-attention detection network for crack segmentation on tomb murals

Many tomb murals have punctate losses, cracks, and craquelure due to underground subsidence and changes in their physical support. Visual non-destructive detection techniques enable rapid assessment of how much tomb murals are affected by cracking, providing suggestions for their conservation. However, tomb murals are typically created by sketching outlines and then colored. Detailed sketches can easily interfere with crack detection work, requiring the use of deep learning network to better learn crack features and improve detection accuracy. At the same time the limited data of tomb mural presents a challenge to build a deep learning network. To address these issues, this paper introduces a novel dual-attention detection network (DADNet) for crack segmentation of tomb murals. In this work, a customized dataset is first constructed by collecting mural images from the Tang Dynasty tombs. Then the ConvNeXt framework serves as the basis for feature extraction, enhancing the process. Lastly, a dual-attention module utilizing neighborhood attention and biaxial attention is employed to accurately identify the crack regions. Neighborhood attention performs a local self-attention operation around the pixel point, addressing the limitations of self-attention. This approach significantly reduces computational demands as the image size increases. Biaxial attention performs attention calculations in the horizontal and vertical directions. This compensates for the limitation of neighborhood attention in capturing global dependencies. Our DADNet outperformed the competing methods, achieving the highest recorded scores of 78.95% for MIoU and 61.05% for the Jaccard index.

Image Restoration Technology of Tang Dynasty Tomb Murals Using Adversarial Edge Learning

The city of Xi’an, China houses a vast collection of valuable Tang dynasty (618 AD-907 AD) tomb murals that have experienced various degrees of damage over time due to weathering. This research proposes an adversarial edge learning-based mural restoration technique that provides a fast and accurate automatic repair of the murals. The method uses generative adversarial networks to learn how to repair the edge contour of a damaged mural and restore the missing content. The contour restoration network and mural restoration networks are trained and updated simultaneously to enhance the feature extraction and restoration coordination performance of the network. The experiments were conducted on a self-built Tang dynasty tomb mural painting restoration dataset and compared to several existing algorithms. The proposed algorithm showed a 1.3 increase in peak signal-to-noise ratio (PSNR) and a 1.43% increase in structural similarity (SSIM) value, providing a precise restoration of the structure and contour of the mural content. The algorithm successfully repaired damaged murals with fractures and small missing parts. The suggested method can be useful for both the technical repair and conservation of significant national visual cultural property and the digital restoration of historic murals.

Intangible heritage restoration of damaged tomb murals through augmented reality technology: A case study of Zhao Yigong Tomb murals in Tang Dynasty of China

Tomb murals are a precious amalgamation of tangible and intangible heritage, encapsulating profound historical significance and aesthetic value. While tangible heritage often gains more attention than intangible heritage in cultural protection, it is still imperative to acknowledge that intangible heritage complements and substantiates the historical, cultural and artistic context. Tomb murals contain intangible heritage elements such as religious practices, customs and artistic techniques. Tomb murals from the Tang Dynasty of China showcase the cultural richness of both tangible and intangible heritage. Nevertheless, there are many challenges to the protection of Tang Dynasty tomb murals. In light of these challenges, the current study aims to protect the intangible heritage embodied in Tang Dynasty tomb murals through augmented reality technology. A Tang Dynasty tomb, the Zhao Yigong Tomb, has been selected as the research object. Seven murals from this tomb were restored using a process involving two-dimensional and three-dimensional modelling combined with augmented reality (AR) technology. Throughout the restoration process, the current study explores the impact of religious customs associated with the Zhao Yigong Tomb on mural contents and artistic techniques. The scenes depicted in these seven murals were integrated into an on-cloud AR platform to establish an effective process for protecting intangible heritage in tomb murals and stimulate further research, design and development. This study identifies the target audience as researchers, educators and college students interested in history, art and culture. To evaluate the current study, researchers and educators with relevant working backgrounds and college student participants with different backgrounds and interests were invited to test the AR application in the field, followed by one-to-one interviews for a usability assessment. The usability assessment shows that the AR application is widely accepted. In addition to adding information interactively, it helps the audience to improve their understanding of Tang Dynasty art and culture.

Skeuomorphism, Miniaturization, and Architecture in the Tang Dynasty Tombs: An Examination of Their Manifestations

This study examines mimetic, miniature and architectural art in Tang dynasty tombs, focusing on the specific manifestations of these elements in tombs and their cultural significance. Analyses of excavated artefacts and murals from Tang dynasty tombs reveal the role of mimetic objects (e.g., pottery, gold and silverware, terracotta figurines and stone carvings) in reflecting the social status and cultural beliefs of the tomb owners. The article also explores the application of the concept of mimesis in tomb murals, which embodied the ancient Chinese concept of “life as death” by vividly depicting scenes of the tomb owner’s life before death. In addition, the architectural design of Tang Dynasty tombs, including above- and below-ground structures, siting methods, and construction techniques, is studied, demonstrating the importance of Tang Dynasty tombs in material culture and social beliefs. Through these analyses, this study aims to deepen the understanding of Tang Dynasty burial culture and reveal its unique value in ancient Chinese society.

STNet: Structure and texture-guided network for image inpainting

Generative Adversarial Network (GAN) has made great progress in image inpainting due to its strong generation capability. However, the previous methods based on GAN cannot understand the structure and texture of damaged images simultaneously, which leads to inconsistent structure and blurred details of inpainting results. To address this issue, we propose a Structure and Texture-guided Network for image inpainting (STNet), which consists of three networks, i.e. structure reconstruction network, texture reconstruction network, and image refinement network. STNet can restore the coherent structure and fine textures of damaged images in the first two networks, and fuse them to complete image inpainting in the last network. Experiments on three standard datasets CelebA, Places2, and Pairs StreetView show STNet is effective and outperforms other related methods. In particular, we also conducted experiments on the damaged images from tomb murals of Tang Dynasty in China, whose results also verify that our method can be applied to the restoration of historical relics. Our code is available at https://github.com/nwuAI/STNet.

Feature Separation and Fusion to Optimise the Migration Model of Mural Painting Style in Tombs

Tomb murals are different from cave temple murals and temple murals, as they are underground cultural relics, their painting style is unique, solemn, and austere, and the performance image is characterised by simple colours, low contrast, and fewer survivors. During the digital restoration process, it is important to have sufficient reference samples to ensure the accuracy of the restoration. In addition, the style of mural paintings in the tombs varies greatly from other styles of murals and types of word paintings. Therefore, learning the unique artistic style of tomb murals, providing stylistically consistent training samples for digital restoration, and overcoming the problems of dim lighting and complex surface granularity of tomb murals are all necessary for research. This paper proposes a generative adversarial network algorithm that separates and fuses style features to enhance the generative network’s ability to acquire image information. The algorithm extracts underlying and surface style feature details of the image to be tested and conducts fusion generation experiments. The generative network’s parsing layer modifies the input noise tensor and optimises the corresponding weights to prevent misalignment between drawing lines and fresco cracks. Finally, to optimise the fresco generation effect, we add the corresponding loss function in the discriminator. The tomb murals dataset was established for experiments and tests, and quantitatively and qualitatively analysed with other style migration models, and SSIM, FID, LPIPS and NIQE were used as evaluation indexes. The results were 0.97, 269.579, 0.425 and 3.250, respectively, and the effect of style migration of this paper’s method was significantly higher than that of the control group model.

Chinese Cultural and Artistic Interaction Based on the Liao Tomb Murals

Chinese Cultural and Artistic Interaction Based on the Liao Tomb Murals

Microorganism Distribution and Preservation Status of Mural Paintings in the Goguryeo Tombs in North Korea

The ancient Goguryeo tombs are spread throughout North Korea and China. The Goguryeo Kingdom was one of the most powerful Korean kingdoms that occupied half of Northeast China and the Korea n Peninsula from the 3rd century BC to the 7th century AD. In 2004, a t the 28<sup>th</sup> session of the World Heritage Committee, held in Suzhou, China, 63 of these tombs were designated as World Heritage Sites. Previously, international organizations such as UNESCO, ICCROM, and ICOMOS provided technical and expert training support for the conservation and management of such tombs. In 1998, at the request of North Korea, a series of investigations and conservation activities began on the tomb murals, and in 2000, international experts began investigating the scientific preservation status of the Yaksu‑ri tomb murals with the South Korean government’s assistance of $100,000 provided to UNESCO. From July 19<sup>th</sup> to 30<sup>th</sup>, 2005, the Goguryeo Relics North‑South Korea Joint Investigation Team, consisting of members of the Goguryeo Research Foundation in South Korea and the North Korean Academy of Social Sciences and Cultural Conservation Guidance, conducted its first joint investigation of the ruins since the two countries were divided. The 2006 Inter‑Korean Joint Goguryeo Mural Tomb Preservation Survey was the first time that South Korean conservation experts participated in scientifically investigating the preservation status and environment of mural tombs and mural pigment analysis. This was to secure comprehensive data on eight tombs. In 2007, additional support for the installation of the necessary measurement equipment was provided to continuously monitor the environments of the ancient tombs. Subsequently, no additional inter‑Korean joint investigation and research has been conducted. To provide scientific information on the distribution of microorganisms in the mural paintings of the tombs and to help establish a future joint preservation plan this study summarizes and reports on the “examination of a biological and environmental survey of the Goguryeo tomb mural paintings” from the results of the 2006 Inter-Korean Joint Goguryeo Mural Conservation Survey Report, jointly published by the Inter-Korean Historians Association and the National Research Institute of Cultural Heritage, which has not previously been presented at academic conferences.

Multidimensional knowledge discovery of cultural relics resources in the Tang tomb mural category

PurposeCurrently, the Tang tomb mural cultural relic resources are presented in a multi-source and heterogeneous manner, with a lack of effective organization and sharing between resources. Therefore, this study aims to propose a multidimensional knowledge discovery solution for Tang tomb mural cultural relic resources.Design/methodology/approachTaking the Tang tomb murals collected by the Shaanxi History Museum as an example, based on clarifying the relevant concepts of Tang tomb mural resources and considering both dynamic and static dimensions, a top-down approach was adopted to first construct an ontology model of Tang tomb mural type cultural relics resources. Then, the actual case data was imported into the Neo4J graph database according to the defined pattern hierarchy to complete the static organization of knowledge, and presented in a multimodal form in knowledge reasoning and retrieval. In addition, geographic information system (GIS) technology is used to dynamically display the spatiotemporal distribution of Tang tomb mural resources, and the distribution trend is analysed from a digital humanistic perspective.FindingsThe multi-dimensional knowledge discovery of Tang tomb mural cultural relics resources can help establish the correlation and spatiotemporal relationship between resources, providing support for semantic retrieval and navigation, knowledge discovery and visualization and so on.Originality/valueThis study takes the murals in the collection of the Shaanxi History Museum as an example, revealing potential knowledge associations in a static and intelligent way, achieving knowledge discovery and management of Tang tomb murals, and dynamically presents the spatial distribution of Tang tomb murals through GIS technology, meeting the knowledge presentation needs of different users and opening up new ideas for the study of Tang tomb murals.

Boutonniere Deformity Depicted in a Koguryo Tomb Mural of the Anak Area of North Korea.

Boutonniere Deformity Depicted in a Koguryo Tomb Mural of the Anak Area of North Korea.

Costume Digital Restoration of the Tomb Mural of YanFei

Costume Digital Restoration of the Tomb Mural of YanFei

문화콘텐츠 스토리텔링을 적용한 디지털 고구려박물관 전시

Using virtual spaces for exhibitions can help a museum move beyond various restrictions of physical space. One of the biggest advantages is that it can use space more freely, However, whether in a digital or a physical space, one must always focus on telling the story underlying the exhibition. After all, the success of the exhibition relies on what story is chosen and how it is told. Most of the artifacts and sites related to Koguryo are located in North Korea and China, which means it is difficult to create an on-site physical exhibition like those for Silla, a millennial kingdom, Gaya, the maritime kingdom, or Baekje, the center of the East Asian trades. Thus, it would be beneficial to actively adopt digital exhibition methods and create virtual spaces to showcase the history and culture of Koguryo. The exhibition space of the Digital Koguryo Museum can be divided into early, medium and late stages according to the development of Koguryo history. It is a good idea to divide the exhibition rooms by time by two or three, allowing visitors to know history and culture at the same time. The two exhibition rooms of the early period are the day of Yuhwa room, the day above the ondol. Visitors can understand the mythical thinking, Koguryo residential culture, and food culture at the beginning of the establishment of Koguryo through the two exhibition rooms. The two exhibition rooms in the middle period are the hoof of the horse and color skirt. Each exhibition room will help to understand the development of Koguryo's history, which has expanded the influence of Koguryo culture through the expansion of the area and to meet the gorgeous culture of Koguryo with a costume culture.. The three exhibition rooms in the latter period are blue dragon & white tiger, Cheonlijangseong and sky. Visitors can see that the four Deities tomb murals are deeply related to the development of the late political society. As a result of the power struggle over the construction of the Cheonlijiangseong, the dictatorship by Yeongaesomun was established, which deepened the conflict between the Chinese Tang Dynasty and Koguryo. The notion of Koguryo's sky can provide an opportunity to meet Koguryo's astronomical knowledge and the world of civilization.

Study on the Influence of Electron Beam Radiation Sterilization Method on Chinese Mural Pigment

Murals are one of the important cultural heritages of mankind. The microbial control of murals is an important subject in mural painting conservation. In recent years, electron beam radiation sterilization has attracted more and more attention in the field of cultural relic protection. Murals are immovable cultural relics, so conventional electron beam irradiation equipment can not be used. However, the development of small mobile electron beam irradiation equipment shows the potential of radiation’s application in the sterilization protection of immovable cultural relics such as murals. A feasibility study of radiation sterilization in mural paintings is needed to investigate the effect of sterilization and the influence of sterilization dose on the stability of mural painting pigments and bonding materials. In this paper, the radiation effects of typical bacteria in tomb murals and mineral pigment powder in ancient Chinese paintings were studied in a laboratory. Firstly, aeromonas hydrophila (Aer.h) and penicillium flavigenum (PNC) were selected as representative strains to determine the appropriate sterilization dose for murals. Then, the effects of radiation on seven kinds of ancient Chinese mineral pigments and white calcium carbonate in the ground layer were verified. The results are as follows: the radiation dose of 10 kGy can effectively remove the two typical strains. This sterilization dose will cause a color difference in calcium carbonate and lead white, while other color pigments are essentially stable. Based on the color difference and UV-vis intensities of the four white carbonate samples, the color change in two of them increased with increasing the dose up to 30 kGy, after which signs of saturation began to appear. X-ray diffraction (XRD), Raman spectra, X-ray photoelectron spectroscopy (XPS) and X-ray absorption near edge structure (XANES) spectra showed that the chemical structure of the samples did not change after irradiation. The formation of free radicals in treated samples was confirmed using an electron paramagnetic resonance (EPR) spectrum test. According to all characterization results, the color difference between the four white carbonate samples may be due to the combination of unpaired electrons and defects in the process of electron beam irradiation to form color centers. After forming the color center, the light absorption of the four samples changed. This is a reversible change, but the samples will take a long time to return to their original state. This study focuses on the influence of electron beam radiation on pigment composition, which is a preliminary exploration of whether radiation sterilization can be applied to the protection of ancient Chinese mural paintings, and the experimental results can provide basic data for later application.

Fragments Inpainting for Tomb Murals Using a Dual-Attention Mechanism GAN with Improved Generators

As the only underground mural in the collection, the tomb murals are subject to damage due to temperature, humidity, and foundation settlement changes. Traditional mural inpainting takes a long time and requires experts to draw it manually. Therefore, the need for digital inpainting is increasing to save time and costs. Due to the scarcity of samples and the variety of damage, the image features are scattered and partially sparse, and the colors are less vivid than in other images. Traditional deep learning inpainting causes information loss and generates irrational structures. The generative adversarial network is, recently, a more effective method. Therefore, this paper presents an inpainting model based on dual-attention multiscale feature aggregation and an improved generator. Firstly, an improved residual prior and attention mechanism is added to the generator module to preserve the image structure. Secondly, the model combines spatial and channel attention with multiscale feature aggregation to change the mapping network structure and improve the inpainting accuracy. Finally, the segmental loss function and its training method are improved.The experimental results show that the results of using signal-to-noise ratio (PSNR), structural similarity (SSIM), and mean square error (MSE) on epitaxial mask, crack mask, random small mask, and random large mask are better than other methods. It demonstrates the performance of this paper in inpainting different diseases of murals. It can be used as a reference for experts in manual inpainting, saving the cost and time of manual inpainting.

Antifungal, Antibacterial, and Interference Effects of Plant-Extracted Essential Oils Used for Mural Conservation at Buyeo Royal Tomb No. 1

Although subterranean tombs are largely protected from the external environment, the colonization of microorganisms threatens their conservation. Conventional biocides have negative effects on the environment, human health, and the sensitive materials in ancient tombs, especially painted murals. Therefore, we tested the biocidal effects of 11 plant-extracted essential oils (EOs) against two fungal strains and four bacterial strains isolated from Buyeo Royal Tomb No. 1, a World Heritage Site in South Korea. Oregano, clove bud, thyme, and cinnamon cassia EOs showed the highest antifungal and antibacterial activities. At concentrations suitable for practical application (3–10%), oregano and cinnamon cassia EOs exhibited the highest antifungal and antibacterial activities against the tested microbial strains. No variation in the surface properties and mineral composition was detected for the lithotype specimens (granite and gneiss) treated with the EOs at 1–10%. Low-concentration thyme and oregano EOs led to minimal color change in the painting layer specimens, whereas clove bud and cinnamon cassia EOs caused yellowing of the oyster shell white pigment at a concentration of 3–10%. Our results suggest that 3% oregano EO is a candidate biocide that could minimize the biological damage to and promote the conservation of ancient tomb murals.

A Spatial Study of the Relics of Chinese Tomb Murals

China has numerous relics from tomb murals. Over 70 years (1949–2019), 1495 relic sites were excavated. Distributed across more than two-thirds of China’s provincial administrative regions, the relics of tomb murals span from the Han Dynasty (206 BC–220 AD) to the Qing Dynasty (1644–1911). In previous studies, scholars focused on the qualitative analysis of tomb murals. In this paper, we applied GIS tools to visualize these relics and analyze their density values for the first time. In terms of academic standards, we propose the material distribution index, the regional distribution index, and the temporal distribution index for relics. The academic innovation of this paper is threefold. First, with regard to the distribution of relic sites, this paper draws a distribution map of the relic sites of Chinese tomb murals and explores the preliminary significance of these relic sites in the culture of the Yellow River basin and its ancient political center. Second, in terms of synchronic viewpoints, this paper designs a material distribution map and a kernel density distribution map based on the distribution map of relic sites. Third, from a diachronic viewpoint, this paper sketches the secondary-level distribution map of six historical periods for the overall kernel density distribution map of relic materials in nine provinces, whereby it outlines the general trend of the development of Chinese tomb murals and the contributions of nine provinces. In brief, with the use of the GIS tool, this paper obtains information on the distribution of relics and reveals the characteristics of tomb murals in terms of their regional and temporal distributions through the ranking of various density values. This paper aims to construct a frame of reference for testing traditional theoretical achievements from the two perspectives of information acquisition and theoretical analysis.

Rediscovery of Ancient Korean Philosophy-Focusing on Star Hole Dolmens, Bronze Mirrors, and Star Charts Carved in Tomb Murals

Rediscovery of Ancient Korean Philosophy-Focusing on Star Hole Dolmens, Bronze Mirrors, and Star Charts Carved in Tomb Murals

Analysis of Female Images in Tang Dynasty Tomb Murals in the Gyeonggi Region

Analysis of Female Images in Tang Dynasty Tomb Murals in the Gyeonggi Region

A Cross-cultural Comparison of Tomb Murals from the Etruscans and the Kingdom of Goguryeo

The Etruscan civilization on the Apennine Peninsula (ca. 900 - 27 B.C.) and the kingdom of Goguryeo on the Korean Peninsula (ca. 37 B.C. - 668) were separated by time and space. Nevertheless, they share an interesting aspect of their culture in common which is the creation of murals in the chambers of mounded tombs. These murals provide important insights into the lifeworld and the perceptions of the afterlife for both civilizations.
 The present study compares the themes of the murals from the Etruscans and the kingdom of Goguryeo in order to ascertain similarities and differences in their pictorial language. Whilst the differences may be simply explained by cultural differences, the similarities may point to commonly shared or universal values and modes of representation in early state formations. As can be demonstrated there is a range of themes that occur in both civilizations such as depictions of the tomb owners, banqueting scenes, hunting, processions and many more. The juxtaposition of the funerary art from both civilizations reveals also a few peculiarities which may be unique for each cultural sphere. In case of Goguryeo this is the depiction of star constellations and for the Etruscans the representation of sex scenes.
 It is being argued that the similarities in the scenes can be explained by common social and behavioral factors. These are for instance the performance of an ancestor cult, a strong affiliation to elite distinction and the creation of a group-related identity.

Unsupervised learning with a physics-based autoencoder for estimating the thickness and mixing ratio of pigments.

Layered surface objects represented by decorated tomb murals and watercolors are in danger of deterioration and damage. To address these dangers, it is necessary to analyze the pigments' thickness and mixing ratio and record the current status. This paper proposes an unsupervised autoencoder model for thickness and mixing ratio estimation. The input of our autoencoder is spectral data of layered surface objects. Our autoencoder is unique, to our knowledge, in that the decoder part uses a physical model, the Kubelka-Munk model. Since we use the Kubelka-Munk model for the decoder, latent variables in the middle layer can be interpretable as the pigment thickness and mixing ratio. We conducted a quantitative evaluation using synthetic data and confirmed that our autoencoder provides a highly accurate estimation. We measured an object with layered surface pigments for qualitative evaluation and confirmed that our method is valid in an actual environment. We also present the superiority of our unsupervised autoencoder over supervised learning.