Digital Restoration Research Articles

Inpainting of damaged temple murals using edge- and line-guided diffusion patch GAN

Mural paintings are vital cultural expressions, enriching our lives by beautifying spaces, conveying messages, telling stories, and evoking emotions. Ancient temple murals degrade over time due to natural aging, physical damage, etc. Preserving these cultural treasures is challenging. Image inpainting is often used for digital restoration, but existing methods typically overlook naturally degraded areas, using randomly generated binary masks or small, narrow regions for repair. This study proposes a novel architecture to reconstruct large areas of naturally degraded murals, maintaining intrinsic details, avoiding color bias, and preserving artistic excellence. The architecture integrates generative adversarial networks (GANs) and the diffusion model, including a whole structure formation network (WSFN), a semantic color network (SCN), and a diffusion mixture distribution (DIMD) discriminator. The WSFN uses the original image, a line drawing, and an edge map to capture mural details, which are then texturally inpainted in the SCN using gated convolution for enhanced results. Special attention is given to globally extending the receptive field for large-area inpainting. The model is evaluated using custom-degraded mural images collected from Tamil Nadu temples. Quantitative analysis showed superior results than state-of-the-art methods, with SSIM, MSE, PSNR, and LPIPS values of 0.8853, 0.0021, 29.8826, and 0.0426, respectively.

Digital Restoration and Innovative Design of Ancient Books Based on CAD and Big Data Technology

Digital Restoration and Innovative Design of Ancient Books Based on CAD and Big Data Technology

MDTNet: Partial transformer with degradation-aware module for restoring old photos with multiple degradations

Old photos preserve the memories of the old days and have special meanings in life. However, they often suffer from severe and complex degradations, such as cracks, dirt, and noise. Old photo restoration is thus a meaningful but challenging task. Most of the current deep learning methods to repair corrupted old photos focus on one single type of degradation or limited number of degradations. The lack of proper old photo datasets makes the digital restoration problem even more challenging. In this paper, we propose MDTNet, which is a novel transformer-based method for restoring old photos with multiple degradations. MDTNet is an efficient end-to-end transformer architecture with only a single encoder and a decoder to complete the restoration. Specifically, a novel partial transformer encoder is designed with partial multi-head self-attention to extract local-global context information from the valid masked area, which represents the unbroken area. In addition, a degradation-aware module is proposed in the decoder to automatically learn different degradation information, to improve the effect of multiple degradation restoration. Moreover, a synthetic old photo dataset — the SynOld dataset — was built, which simulates the multiple degradations of real old photos. Experimental results show that the proposed method outperforms the state-of-the-art methods on both public datasets and the custom-developed dataset. The code is available at https://github.com/YuanZhaoc/MDTNet.

A study on the digital restoration of an ancient city based on historic building information modeling of wooden architectural heritage: focusing on Suwon Hwaseong

This study describes the process of digitally reconstructing the ancient Korean city of Suwon Hwaseong in 3D utilizing Historic Building Information Modeling (HBIM) resources to accurately represent its wooden architectural heritage. Previous 3D reconstructions of cultural heritage have often prioritized appearance or remained partially disassembled. However, our reconstruction method offers a comprehensive representation of the appearance and the internal structure of wooden architectural heritage, which can be suitable for restoration maintenance. To ensure accuracy in digital restoration, we collected and utilized administrative records and historical materials, including the geography, fortress walls, folk houses, and Haenggung (the temporary palace of the Joseon Dynasty)—drawing from the archive of the Korean Cultural Heritage Service’s management records and the 1796 manuscript “Uigwe: Royal Protocols of the Hwaseong Fortress” which documents the construction of the ancient city of Suwon Hwaseong. Extensive architectural records were used to generate HBIM data, which digitized historical records, documents, and drawings to accurately represent the complex layout of the wooden architectural heritage. For the folk houses that lacked design records and the fortress walls that retained their original shape, we performed a digital restoration-based façade modeling. These elements of the ancient city of Suwon Hwaseong were assembled into a 3D model using Unreal Engine (version 5.1.1) to digitally reconstruct the city and enhance its visual representation. The digital restoration content, which utilizes visual effects and precise rendering from a game engine, can be used for the restoration, repair, and maintenance of both appearance and internal structures.

The Transformative Role of Digital Tools in Comic Book Preservation

Traditionally viewed as static repositories, archives are now seen as dynamic entities capable of continuous reconfiguration and reinterpretation. This study examines how digital practices in comic book archiving maintain historical and emotional integrity, while making these artefacts relevant to contemporary audiences. This paper explores the theories of Wolfgang Ernst, Michel Foucault, Lev Manovich, and others in order to explain digital archiving as a dynamic and interpretive act that shapes historical narratives and cultural memory. Digital restoration of comic books focuses on preserving the original aesthetic and historical context, while recoloring revitalizes visual elements to enhance appeal. Reimagining involves comprehensive reinterpretation and aligns with new media theories in order to offer fresh perspectives on historical narratives. The discussion shows how these practices democratize access to cultural heritage, transforming archives into active sites of cultural engagement and potentiality. By balancing technical precision and interpretive insight, digital artists and archivists aim at ensuring that comic books remain vibrant and meaningful cultural treasures for future generations.

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.

From Traditional Perspectives to Design Innovation

This paper elaborates on the process of digital restoration and redesign of the konghou depicted in the murals of Mogao Grottoes' Cave 465 from a product design perspective. Through an in-depth analysis of the konghou's form, precise application of digital technology, and the clever integration of modern design concepts, this study not only achieves effective protection and inheritance of ancient cultural heritage but also explores innovative applications of traditional cultural elements in contemporary product design. This research is significant for promoting the digital preservation of cultural heritage and fostering the fusion of tradition and modernity.

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 512 × 512 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.

Enhancing point cloud registration with transformer: cultural heritage protection of the Terracotta Warriors

Point cloud registration technology, by precisely aligning repair components with the original artifacts, can accurately record the geometric shape of cultural heritage objects and generate three-dimensional models, thereby providing reliable data support for the digital preservation, virtual exhibition, and restoration of cultural relics. However, traditional point cloud registration methods face challenges when dealing with cultural heritage data, including complex morphological and structural variations, sparsity and irregularity, and cross-dataset generalization. To address these challenges, this paper introduces an innovative method called Enhancing Point Cloud Registration with Transformer (EPCRT). Firstly, we utilize local geometric perception for positional encoding and combine it with a dynamic adjustment mechanism based on local density information and geometric angle encoding, enhancing the flexibility and adaptability of positional encoding to better characterize the complex local morphology and structural variations of artifacts. Additionally, we introduce a convolutional-Transformer hybrid module to facilitate interactive learning of artifact point cloud features, effectively achieving local–global feature fusion and enhancing detail capture capabilities, thus effectively handling the sparsity and irregularity of artifact point cloud data. We conduct extensive evaluations on the 3DMatch, ModelNet, KITTI, and MVP-RG datasets, and validate our method on the Terracotta Warriors cultural heritage dataset. The results demonstrate that our method has significant performance advantages in handling the complexity of morphological and structural variations, sparsity and irregularity of relic data, and cross-dataset generalization.

Achieving new excellence in an augmented reality dental education system

Background/purposeSimEx-Plus (EPED. Inc) was already a mature augmented reality (AR) dental training simulator that allowed students to have a high quality dental education practice. Now the EPCAD software has been further developed into a comprehensive computer-aided design software. It helps relevant professionals learn how to create digital fixed prosthesis in a virtual environment. This study used the newly developed EPCAD software that was integrated within the SimEx-Plus to design dental restorations then digital output milling restorations. We hope that the SimEx-Plus AR dental training simulator can achieve the multi-purpose function in one machine. Materials and methodsA right maxillary central incisor was prepared in the standard dental model. The restorations were designed by EPCAD software integrated with the SimEx-Plus and milled by a 4-axis dental milling machine (N4+, vhf camfacture AG). The internal gap of the restoration was evaluated. ResultsThe internal gaps of the crowns set on the right maxillary central incisor were among 68.27–89.80 μm. The different setting for digital output did not influence the internal gap (P 0.05, One-Way ANOVA). However, the internal gap on the palatal side was larger than that on the labial, mesial, distal, and incisal surfaces (P < 0.05, One-Way ANOVA). ConclusionThe new software EPCAD that was integrated within the SimEx-Plus AR dental training simulator could design restorations, and the designed restorations had good internal gap for clinical use. The professionals can learn tooth preparation and digital restoration fabrication by the SimEx-Plus AR dental training system.

Digital Documentation and Architectural Heritage Restoration with 3-D Geometry: The Ambulatory of the Cathedral of Santiago de Compostela

ABSTRACT The SFM photogrammetry (Structure from Motion) is a technique developed in the field of computer vision that allows obtaining 3D models from images taken from different angles. Despite its extensive development, this technique faces methodological challenges when applied to complex heritage environments. Typically, heritage restoration documentation focuses on the initial and final stages when works have not yet begun or have already concluded, and the object of study is free of obstacles and workers, with its use in intermediate stages being uncommon. The aim of this article is to present geometric documentation using SFM-MVS photogrammetry across multiple stages of the roof restoration of the Cathedral of Santiago de Compostela (Spain), showcasing an expert application of this technique in a real working scenario with multiple challenges, adapting to complex scenes without interfering with project timelines and providing high-quality outcomes at a low cost, even in areas temporarily obscured by scaffolding or plastic coverings. It provides essential data for geometric assistance in restoration design, adaptation, and stakeout. Moreover, continuous 3D documentation enables the creation of 3D stop-motion models, offering an innovative perspective for understanding and communicating a wide range of restoration and construction projects.

Transforming Color: A Novel Image Colorization Method

This paper introduces a novel method for image colorization that utilizes a color transformer and generative adversarial networks (GANs) to address the challenge of generating visually appealing colorized images. Conventional approaches often struggle with capturing long-range dependencies and producing realistic colorizations. The proposed method integrates a transformer architecture to capture global information and a GAN framework to improve visual quality. In this study, a color encoder that utilizes a random normal distribution to generate color features is applied. These features are then integrated with grayscale image features to enhance the overall representation of the images. Our method demonstrates superior performance compared with existing approaches by utilizing the capacity of the transformer, which can capture long-range dependencies and generate a realistic colorization of the GAN. Experimental results show that the proposed network significantly outperforms other state-of-the-art colorization techniques, highlighting its potential for image colorization. This research opens new possibilities for precise and visually compelling image colorization in domains such as digital restoration and historical image analysis.

Digital restoration of the snout of Khirtharia inflata (Raoellidae, Artiodactyla) from the middle Eocene of northwest Himalaya

Digital restoration of the snout of Khirtharia inflata (Raoellidae, Artiodactyla) from the middle Eocene of northwest Himalaya

Digital 3D models for medieval heritage: diachronic analysis and documentation of its architecture and paintings

In this paper, we discuss the requirements and technical challenges within the EHEM project, Enhancement of Heritage Experiences: The Middle Ages, an ongoing research program for the acquisition, analysis, documentation, interpretation, digital restoration, and communication of medieval artistic heritage. The project involves multidisciplinary teams comprising art historians and visual computing experts. Despite the vast literature on digital 3D models in support of Cultural Heritage, the field is so rich and diverse that specific projects often imply distinct, unique requirements which often challenge the computational technologies and suggest new research opportunities. As good representatives of such diversity, we describe the three monuments that serve as test cases for the project, all of them with a rich history of architecture and paintings. We discuss the art historians’ view of how digital models can support their research, the expertise and technological solutions adopted so far, as well as the technical challenges in multiple areas spanning geometry and appearance acquisition, color analysis and digital restitution, as well as the representation of the profound transformations due to the alterations suffered over the centuries.

Virtual sketching-based dental anatomy module improves learners' abilities to use computer-aided design to create dental restorations and prostheses.

Dental anatomy education for dental technology students should be developed in alignment with digital dental laboratory practices. We hypothesized that a virtually assisted sketching-based dental anatomy teaching module could improve students' acquisition of skills essential for digital restoration design. The second-year dental technology curriculum included a novel virtual technology-assisted sketching-based module for dental anatomy education. Pre- and post-course assessments evaluated students' skill sets and knowledge bases. Computer-aided design (CAD) scores were analyzed after one year to assess how the skills students developed through this module impacted their subsequent CAD performance. Participants who undertook the dental sketching-based teaching module demonstrated significantly improved theoretical knowledge of dental anatomy, dental aesthetic perception, and spatial reasoning skills. A partial least squares structural equation model indicated that the positive effects of this module on subsequent CAD performance were indirectly mediated by dental aesthetic perception, spatial reasoning, and practice time. A virtually assisted sketching-based dental anatomy teaching module significantly improved students' acquisition of skills and knowledge and positively mediated dental technology students' CAD performance.

Digital Virtual Simulation for Cultural Clothing Restoration: Case Study of Tang Dynasty Mural ‘Diplomatic Envoys’ from Crown Prince Zhang Huai’s Tomb

The advent of 3D virtual presentation technology for clothing has led to the gradual popularisation of digital virtual clothing in the modern fashion industry. However, there remains a gap between the application of this technology and the integration of cultural attributes in the field of digital communication of traditional cultural clothing. Consequently, the objective of this paper is to propose the establishment of a fusion system integrating archaeological research on traditional culture with emerging virtual presentation technology. This paper draws inspiration from the replicability and easy dissemination of digital products to combine cultural archaeology and digital technology. The aim is to provide ideas for the diversity of dissemination of cultural heritage. The research object is Diplomatic Envoys, a Chinese mural painting of the Tang Dynasty that depicts friendly exchanges between countries. The research is divided into two research stages. A CLO3D software-based digital restoration test was conducted to reproduce the costumes of officials and foreign envoys depicted in the Tang Dynasty mural. The FAHP model was employed to verify the accuracy of the restoration results. The experiment demonstrated that the digitally reconstructed clothing exhibited a high degree of similarity to the unearthed mural figure clothing object. Furthermore, the restoration result passed the credibility verification, resulting in a ‘credible’ outcome. The application of digital virtual simulation clothing restoration methods offers two key advantages. Firstly, in comparison with traditional clothing restoration methods, digital restoration enables the rapid assessment of the resulting clothing effect, thereby reducing the likelihood of secondary damage to cultural relics due to manual errors. Secondly, the benefits of digital technology facilitate the convenient storage, replication, and dissemination of clothing data information. Data can not only be extended to online exhibition halls but also to game animation, clothing production, and other fields for the purposes of creative redesign and information dissemination. Furthermore, these benefits can penetrate the education industry to disseminate information to the public through all-round display models and explanations.

Digital reconstruction of partially lost altarpieces. The case of the Rosary's altarpiece of Sant Pere Màrtir de Manresa

An important challenge of Digital Cultural Heritage is to contribute to the recovery of artworks with their original shape and appearance. Many altarpieces, which are very relevant Christian art elements, have been damaged and/or partly or fully lost. Therefore, the only way to recover them is to carry out their digital reconstruction. Although the procedure that we present here is valid for any altarpiece with similar characteristics, and even for other akin elements, our test bench is the altarpieces that were damaged or destroyed or that disappeared during the Spanish Civil War (1936–1939) in Catalonia, where most suffered these effects. The first step of our work has been the classification of these artworks into different categories on the basis of their degree of destruction and of the available visual information related to each one. This article proposes, for the first time to our knowledge, a workflow for the virtual reconstruction, through photogrammetry, digital modeling, and digital color restoration, of whole altarpieces partially preserved with very little visual information. Our case study is the Rosary’s altarpiece of Sant Pere Màrtir de Manresa church. Currently, this altarpiece is partially preserved in fragments in the Museu Comarcal de Manresa (Spain). But it cannot be reassembled physically owing to the lack of space (actually the church does not exist anymore) and the cost of such an operation. Thus, there is no other solution than the digital one to contemplate and study the altarpiece as a whole. The reconstruction that we provide allows art historians and the general public to virtually see the altarpiece complete and assembled as it was until 1936. The results obtained also allow us to see in detail the reliefs and ornaments of the altarpiece with their digitally restored color.

An intelligent lithology recognition system for continental shale by using digital coring images and convolutional neural networks

Lithology identification is a critical component of reservoir evaluation and hydrocarbon development. However, the continental shale rocks, characterized by complex lithologies and developed laminations, present new challenges to traditional lithology identification techniques. In this study, we develop a centimeter-level intelligent identification system for continental shale lithology, leveraging digital image preprocessing and deep learning methods. Specifically, we construct a dataset from 400 m of drilling cores, encompassing 24 types of lithology and 152 lithological transitions. The downsampling and oversampling methods are employed to balance the dataset. The digital image denoising and restoration techniques are then utilized to enhance rock image features. Different neural network models are examined to obtain the optimum predictive results. The results indicate that data balancing improves the TOP1 and TOP5 accuracies by 10% and 5%, respectively. Gaussian low-pass filter denoising, in comparison to other methods, increases the TOP1 and TOP5 accuracies by 2%, establishing it as the superior denoising technique for lithology recognition. Considering both computational efficiency and prediction accuracy, EfficientNet emerges as the most effective model for continental shale image recognition. The optimized model attains up to 60% TOP1 and 95% TOP5 across 22 categories in drilling core samples. This study delves into the intelligent identification of macroscopic drilling core images of continental shale, and the findings can offer technical support for the interpretation and evaluation of continental shale reservoirs.

Digital restoration and 3D visualisation of the early Neolithic pottery from Ryńsk, Poland

The archaeological site of Ryńsk in north-central Poland produced sound evidence of long-distance journeys of people and pottery from the 6th millennium BC in Central Europe by yielding a sophisticated ceramic footed bowl that can be traced to the Carpathian Basin region. Archaeology indicates that the earliest ceramic vessels had a different functional, social and ritual role, but it is difficult to convey information on the significant role of pottery in ancient societies in a way that would pique the interest of the general public. This paper presents the digital restoration and 3D visualisation of the footed bowl from Ryńsk and other accompanying ceramics that may assist in feeding the historical imagination and education about the ancient pottery making of the LBK people and can be used to provide a wider audience with new forms of engagement and interaction with the archaeological heritage of the region.

Creation of Historical Building Information Modelling (HBIM) Library, A Case Study of Registered House (No:56), Akçakoca

Building Information Modelling (BIM) is a methodology created by adapting information technologies to the construction industry, creating 3D parametric and object-based models, and adding time and cost data to the models. In recent years, the creation of digital cultural heritage is a current field in terms of protecting cultural heritage and transferring it to future generations. Development of technology and the increase in opportunities, destinations that cannot be physically visited due to access difficulties or pandemics are trying to transfer their cultural richness to digital environments. For this purpose, Historical Building Information Modelling (HBIM), which is the version of BIM applied to historical buildings, emerges as an important tool. The digitalization of cultural heritage structures by modelling is a process that requires intensive labour due to the lack of uniform details, and the fact that they were made with different construction techniques at different times and periods. For this reason, this process will be improved with the creation, dissemination, classification, and accessibility of parametric object libraries with HBIM. In this direction, the research method; is based on the analysis and synthesis of the literature review and case study in particular on modelling and library studies as a case study. As a field study, it was created in three dimensions with HBIM on a registered civil architecture example that has lost its originality in Düzce province, Akçakoca district, and the building and library elements were modelled and transferred to BIM. The original state of the building has been created to be experienced interactively. As a result, the building and its elements are defined by parametric objects. With the development of the HBIM library, the elements of the structures of similar typology become digitally accessible and digital legacies are created much more easily and effectively. HBIM studies create a comprehensive three-dimensional data set in digital documentation, restitution periods and restoration studies.