A Novel Flexible Identity-Net with Diffusion Models for Painting-Style Generation DOI Open Access
Yifei Zhao, Ziqi Liang,

Yingrui Qiu

et al.

Published: Aug. 28, 2024

Art's unique style and creativity are essential in defining a work's identity, conveying emotions, shaping audience perception. Recent advancements diffusion models have revolutionized art design, animation, gaming, particularly generating original artwork visual identities. However, traditional creative processes face challenges such as slow innovation, high costs, limited scalability. Consequently, deep learning has emerged promising solution for enhancing painting-style design. In this paper, we present the Painting-Style Design Assistant Network (PDANet), groundbreaking network architecture designed advanced transformation. Our work is supported by Painting-42 dataset, meticulously curated collection of 4,055 artworks from 42 illustrious Chinese painters, capturing aesthetic nuances painting offering invaluable design references. Additionally, introduce lightweight Identity-Net, to enhance large-scale text-to-image (T2I) aligning internal knowledge with external control signals. This innovative Identity-Net seamlessly integrates image prompts into U-Net encoder, enabling generation diverse consistent images. Through extensive quantitative qualitative evaluations, our approach demonstrated superior performance compared existing methods, producing high-quality, versatile content broad applicability across various domains. not only advances field AI-driven but also offers new paradigm future

Language: Английский

Digitalizing cultural heritage through metaverse applications: challenges, opportunities, and strategies DOI Creative Commons
Dipima Buragohain,

Yahui Meng,

Chaoqun Deng

et al.

Heritage Science, Journal Year: 2024, Volume and Issue: 12(1)

Published: Aug. 13, 2024

Abstract Preservation and accessibility of cultural heritage have become essential with the rapid advancements globalization modernization endeavors constantly threatening historical artifacts sites across world. The advent metaverse, its immersive interactive capabilities, presents a novel approach to safeguarding promoting heritage. current study aims explore potential metaverse applications in digitalizing heritage, encompassing virtual reconstructions, educational outreach, global accessibility, sustainability. It conducts systematic literature review using PRISMA guidelines collect, screen, evaluate existing research enquiries into investigating practices technologies digitalization preservation. also case investigate challenges opportunities associated preservation tangible intangible assets, including issues authenticity, representation, Furthermore, it evaluates impact on public engagement education. findings provide valuable insights developing innovative strategies for preserving digital age while highlighting best optimizing

Language: Английский

Citations

15
What influences user continuous intention of digital museum: integrating task-technology fit (TTF) and unified theory of acceptance and usage of technology (UTAUT) models DOI Creative Commons

Feiyu Zheng,

Shan Wu, Ren Liu

et al.

Heritage Science, Journal Year: 2024, Volume and Issue: 12(1)

Published: July 24, 2024

Abstract Digital museums play a crucial role in facilitating users' access to and exploration of digital cultural heritage resources. However, exploring the factors influencing user engagement with these from experience perspective remains essential. This study evaluates driving continuous behavioral intention towards museum Beijing’s central axis, integrating new task-technology fit (TTF) unified theory acceptance use technology (UTAUT) models, introducing perceived enjoyment, design aesthetics, value as additional variables. Analyzing survey data (n = 377) utilizing structural equation modeling (SEM), identifies following key findings: (1) task characteristics significantly impact TTF; (2) performance expectancy, effort all positively intention; (3) technological were observed expectancy; but (4) TTF social influence did not have no significant intention. These findings offer valuable insights into heritage, offering practical guidance for future development optimization museums, highlighting specific implications suggestions enhancing experience.

Language: Английский

Citations

6
Three-Dimensional Documentation and Virtual Web Navigation System for the Indoor and Outdoor Exploration of a Complex Cultural Heritage Site DOI Open Access
Manuela Aricò, Gino Dardanelli, M. La Guardia

et al.

Electronics, Journal Year: 2024, Volume and Issue: 13(14), P. 2833 - 2833

Published: July 18, 2024

The spread of new survey strategies for the documentation and 3D reconstruction complex cultural heritage sites enables implementation virtual web navigation systems that are useful their fruition. In particular, remote indoor/outdoor exploration enhances our knowledge sites, even in inaccessible or difficult-to-visit states. However, data acquisition remains a challenge, these datasets is often limited to property software implementations. This work describes construction an visualization system based on WebGL open-source technology site. case study regards “Santa Maria della Grotta” Marsala (Italy), which composed church located mostly underground connected human-dug hypogea site Punic necropolis. aim was obtain detailed indoor outdoor spaces through integration mobile laser scanning aerial photogrammetry survey, develop provides users with simple, web-browser-based visualization, enabling dissemination monuments’ economically sustainable solution technologies.

Language: Английский

Citations

5
The Ontological Multiplicity of Digital Heritage Models: A Case Study of Yunyan Temple, Sichuan Province, China DOI Creative Commons
Jie Tan, Xin Guo,

Haijing Huang

et al.

Buildings, Journal Year: 2025, Volume and Issue: 15(2), P. 178 - 178

Published: Jan. 9, 2025

This paper investigates the ontological multiplicity of digital heritage objects within context a twin project focused on Yunyan Temple, Sichuan Province, China—a site threatened by natural disasters. The employs laser scanning and photogrammetry to generate high-resolution 3D models at varying levels detail. study analyzes how these support diverse analytical tasks ranging from geomorphological analysis structural assessments spatial sequence analysis. We present novel four-layer data integration service platform architecture designed manage complex relationships arising this multiplicity. includes temporal database iterative refinements conservation strategies based ongoing monitoring. findings highlight dynamic role in knowledge production offer practical implications for design, management, development adaptive cultural heritage.

Language: Английский

Citations

0
ECHO-M: Towards an Ethical Framework for Selecting Cultural Heritage Objects for Digitization in Metaverse DOI
Khouloud Boukadi, Najla Fattouch, Makram Mestiri

et al.

Lecture notes on data engineering and communications technologies, Journal Year: 2025, Volume and Issue: unknown, P. 365 - 376

Published: Jan. 1, 2025

Language: Английский

Citations

0
Enhanced and Combined Representations in Extended Reality through Creative Industries DOI Creative Commons
Eleftherios Anastasovitis, Μanos Roumeliotis

Applied System Innovation, Journal Year: 2024, Volume and Issue: 7(4), P. 55 - 55

Published: June 26, 2024

The urgent need for research and study with nondestructive noninvasive methods the preservation of cultural heritage led to development application methodologies multi-level digitization elements. Photogrammetry three-dimensional scanning offer photorealistic accurate digital representations, while X-rays computed tomography reveal properties characteristics internal invisible structure objects. However, investigation access these datasets are, in several cases, limited due increased computing resources special knowledge required their processing analysis. evolution immersive technologies creative industry video games offers unique user experiences. Game engines are ideal platform host easy-to-use applications that combine heterogeneous data simultaneously integrating emerging technologies. This article seeks shed light on how representations 3D imaging can be harmoniously combined a virtual space and, through simple interactions, provide holistic enhanced experience end users. builds previous concerning museum Antikythera Mechanism describes conceptual framework design an affordable display tool space. Our solution was validated by 62 users who participated tests evaluations. results show proposed methodology met its objectives. Apart from heritage, specific could easily extended adapted training purposes wide field application, such as education, health, engineering, industry, more.

Language: Английский

Citations

1
The Usage of Virtual and Augmented Reality in Underwater Archeology DOI Creative Commons
Kinga Korniejenko, Bartosz Kontny

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(18), P. 8188 - 8188

Published: Sept. 11, 2024

Currently, virtual and augmented reality (VR AR) technologies are becoming more widely used in various fields of human activity, including archeology. The aim this article is to analyze the possibilities using VR AR broadly understood activities related underwater This work a review presents current applications archeology based on case studies. paper development technologies, field archaeology, generally describes process creating for purposes, with particular emphasis data collection methods. Then, areas application these were presented barriers their use discussed. most important part discussion selected ends summary state developing

Language: Английский

Citations

1
Exploring Controllable Ability through Text-to-Image Diffusion Model for Painting-Style Design DOI Open Access
Yifei Zhao, Ziqi Liang,

Yingrui Qiu

et al.

Published: Aug. 15, 2024

Painting style and creativity are fundamental to art, defining a work’s uniqueness expression. They embody an artist’s personality, convey emotions, establish identity, shape audience perception, adding depth value the work. Recently, diffusion models have gained popularity in art design, animation, gaming, especially original painting creation, poster visual identity development. Traditional creative processes, while demanding unique imagination creativity, often face challenges such as slow innovation, high reliance on manual efforts, costs, limitations scalability. Consequently, exploring painting-style design through deep learning has emerged promising trend. In this paper, we introduce novel network architecture, Painting-Style Design Assistant Network (PDANet), for transformation. To support this, curated Painting-42 dataset, comprising 4,055 works by 42 renowned Chinese painters. PDANet leverages dataset capture aesthetic intricacies of painting, offering rich references. Furthermore, propose lightweight Identity-Net large-scale text-to-image (T2I) models, which aligns internal knowledge with external control signals, thereby enhancing capabilities existing T2I models. The trainable feeds image prompts into U-Net encoder generate diverse stable images. Both quantitative qualitative analyses demonstrate that our approach outperforms current methods, delivering high-quality generated content wide-ranging applicability.

Language: Английский

Citations

0
A Novel Flexible Identity-Net with Diffusion Models for Painting-Style Generation DOI Open Access
Yifei Zhao, Ziqi Liang,

Yingrui Qiu

et al.

Published: Aug. 28, 2024

Art's unique style and creativity are essential in defining a work's identity, conveying emotions, shaping audience perception. Recent advancements diffusion models have revolutionized art design, animation, gaming, particularly generating original artwork visual identities. However, traditional creative processes face challenges such as slow innovation, high costs, limited scalability. Consequently, deep learning has emerged promising solution for enhancing painting-style design. In this paper, we present the Painting-Style Design Assistant Network (PDANet), groundbreaking network architecture designed advanced transformation. Our work is supported by Painting-42 dataset, meticulously curated collection of 4,055 artworks from 42 illustrious Chinese painters, capturing aesthetic nuances painting offering invaluable design references. Additionally, introduce lightweight Identity-Net, to enhance large-scale text-to-image (T2I) aligning internal knowledge with external control signals. This innovative Identity-Net seamlessly integrates image prompts into U-Net encoder, enabling generation diverse consistent images. Through extensive quantitative qualitative evaluations, our approach demonstrated superior performance compared existing methods, producing high-quality, versatile content broad applicability across various domains. not only advances field AI-driven but also offers new paradigm future

Language: Английский

Citations

0