Shaanxi History Museum

The Dunhuang Mogao Grottoes are among the most significant historical and cultural sites in China, with the Dunhuang Mural serving as key representative artifacts. Due to natural erosion, human activities, and other factors, it is crucial to protect these frescoes authentically and accurately to ensure their preservation. To address this, we propose a technological framework, 3DSynBrush, for high-quality 3D reconstruction of Chinese painting data. First, single elements are extracted from the mural through the Perspective-Driven Synthesis (PDS) Module, and a sparse perspective is generated. The sparse view is then passed through the Neural Rendering Synthesizer to obtain a continuous view image, which ultimately meets the input requirements of the Light Field Fusion Meshing Module to achieve 3D reconstruction. 3DSynBrush aims to reconstruct a realistic model of the scene depicted using only a single primary view of the fresco. Moreover, we develope a high-quality Chinese Mural Elements dataset, termed CME. Compared to current 3D reconstruction algorithms, 3DSynBrush produces visually coherent results while using only 40% of the vertices and triangles, thereby minimizing computational resources.

Large Language Models (LLMs) have recently emerged as a transformative technology for museums, enabling a shift from static content delivery toward interactive and intelligent systems. However, existing studies and deployments remain fragmented, with a lack of systematic analysis of how LLM capabilities align with the unique goals, constraints, and values of museum contexts. This gap motivates the need for a unified survey that views LLM-based systems not only as technical tools, but also as components embedded within cultural, educational, and institutional settings. This survey provides a comprehensive overview of how LLMs are being integrated into museums, covering both interactive intelligence for visitor-facing applications and backstage intelligence that supports curatorial and governance processes. By synthesizing prior work and emerging practices, we aim to offer valuable insights into research challenges, future directions, and practical considerations for developing LLM-enabled museum systems that are robust, responsible, and aligned with long-term cultural heritage objectives. CCS Concepts: • General and reference → Surveys and overviews; • Social and professional topics → Cultural characteristics; • Human-centered computing → Empirical studies in interaction design; • Computing methodologies → Artificial intelligence.

While Go embodies the profound cultural heritage of the Chinese nation, archaeological research on it remains limited, particularly concerning Go-related cultural artifacts. We employed a suite of analytical techniques—including high-depth-of-field 3D optical microscopy (OM), X-ray fluorescence spectrometry (XRF), X-ray diffraction (XRD), and confocal Raman microscopy—to examine three Go stones unearthed from the tomb of Fan Xiaocun (Northern Song Dynasty, 960–1127 CE). The analysis revealed distinct material and manufacturing characteristics: The white stone was crafted from shell material; The black stone, a carburized ceramic piece, was fired below 950 °C; The patterned stone, also ceramic, featured sunken relief carving and required firing temperatures exceeding 1200 °C. This study provides valuable references for research on Go history, Chinese sports/entertainment artifacts, and board game culture, while offering methodological insights for future investigations.

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.

As an important part of human cultural heritage, earthen sites are subject to damage caused by a variety of environmental factors, such as cracking, weathering, and flooding. Due to the low mechanical strength of earthen site materials, especially in humid environments, they are susceptible to hazards like moisture penetration, freeze–thaw cycles, and biological invasion. Superhydrophobic coatings show promising potential in the protection of earthen sites, with key properties that include waterproof performance, breathability, robustness, and transparency. By exploring various material systems and preparation methods, the current state of research on the protection of building materials with superhydrophobic materials has been demonstrated, highlighting advantages in the corrosion resistance, self-cleaning, frost prevention, anti-scaling, and other aspects. At the same time, it also points out the challenges faced in the practical application of earthen site protection and the prospects for future research. These include enhancing the bonding strength between the coating and soil particles, improving durability and breathability, and developing large-scale, low-cost, and efficient coating construction techniques.

Murals are an important part of human cultural heritage, reflecting the cultural characteristics of different periods and containing extremely high research value. However, for a long time, due to environmental factors such as humidity and temperature, as well as internal factors such as mural production materials and processes, mold has grown on murals, seriously affecting their aesthetics and preservation status. Mold disease labeling can detect mold growth and provide technical support for mold prevention and control. Traditional manual annotation methods are not only time-consuming and laborious, but also suffer from subjective errors and inconsistent annotation. Therefore, this article proposes a method for labeling fungal diseases in murals based on hyperspectral images, which can achieve automatic recognition and labeling of fungi on the surface of murals. This method first generates mold training samples based on hyperspectral image unmixing, and then proposes a mural mold labeling network framework based on a multi grouping strategy long short-term memory network and a multi-scale convolutional neural network (MGL-MC), effectively combining spatial and spectral information of mural hyperspectral images. The experiment shows that the method proposed in this article has a good effect on the recognition and labeling of mold on the surface of murals, and can improve the accuracy of mold detection.

Removing unwanted materials, such as organic coatings and soil, from the cultural relic surface is a complex and significant task in the field of cultural heritage conservation. Microemulsion-loaded gel can effectively and safely remove those organic coatings and soil. Here, we employed a simple solvent exchange strategy to prepare a microemulsion-loaded polyvinyl alcohol/polyethyleneimine (PVA/PEI) hydrogel. First, PVA and PEI were dissolved into DMSO to form a gel. Then, the gel was immersed into a microemulsion composed of water, ethyl acetate, propylene carbonate, sodium dodecyl sulfate, and 1-pentanol to exchange DMSO. Microemulsion-loaded PVA/PEI hydrogel can be synthesized by completely substituting DMSO. To investigate the microstructure, rheological properties, and mechanical properties of the gel, scanning electron microscopy, a rheometer, and a universal testing machine were used, respectively. Fourier transform infrared (FT-IR) analysis was conducted to explore the synthesis mechanism and confirm the successful loading of microemulsion within the microemulsion-loaded PVA/PEI hydrogel. Furthermore, FT-IR, a depth-of-field microscope, and a glossmeter were utilized to evaluate the cleaning efficiency of the microemulsion-loaded PVA/PEI hydrogel for removing animal glue and soil from the surfaces of cultural relics. Moreover, an X-ray fluorescence spectrometer was used to analyze the element component of the ancient coin. The application results showed that the microemulsion-loaded PVA/PEI hydrogel can effectively remove animal glue from an ancient wall painting surface. Moreover, it is capable of removing soil from an ancient coin surface as well, which helped to confirm the age of the coin. This offers a novel method to prepare microemulsion-loaded hydrogel and demonstrates great potential in the cleaning for cultural heritage.