Painting Authorship and Forgery Detection Challenges with AI Image Generation Algorithms: Rembrandt and 17th Century Dutch Painters as a Case Study

Fraile-Narváez, Marcelo; Sagredo-Olivenza, Ismael; McGowan, Nadia.

doi:10.9781/ijimai.2022.11.005

Cited by 7 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, the field of AI art has seen a remarkable surge in innovation and public interest. The AI art landscape is enriched by artworks such as "The Next Rembrandt," a painting generated using data from Rembrandt's entire body of work [35], and "Sunspring," a short film scripted by an AI [22]. Extensive reviews already exist on AI/ML art in general [9,24], artificial life/genetic art [70,85], robotic art [71], and artists' account on how they work with ML [23].…”

Section: Ambiguity In Ai Art Theoriesmentioning

confidence: 99%

Machine Learning Processes As Sources of Ambiguity: Insights from AI Art

Sivertsen,

Salimbeni,

Løvlie

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

Ongoing efforts to turn Machine Learning (ML) into a design material have encountered limited success. This paper examines the burgeoning area of AI art to understand how artists incorporate ML in their creative work. Drawing upon related HCI theories, we investigate how artists create ambiguity by analyzing nine AI artworks that use computer vision and image synthesis. Our analysis shows that, in addition to the established types of ambiguity, artists worked closely with the ML process (dataset curation, model training, and application) and developed various techniques to evoke the ambiguity of processes. Our finding indicates that the current conceptualization of ML as a design material needs to reframe the ML process as design elements, instead of technical details. Finally, this paper offers reflections on commonly held assumptions in HCI about ML uncertainty, dependability, and explainability, and advocates to supplement the artifact-centered design perspective of ML with a process-centered one.CCS Concepts: • Human-centered computing → HCI theory, concepts and models; • Applied computing → Media arts.

show abstract

Section: Ambiguity In Ai Art Theoriesmentioning

confidence: 99%

Machine Learning Processes As Sources of Ambiguity: Insights from AI Art

Sivertsen,

Salimbeni,

Løvlie

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

“…On the one hand, it provides a different way of creating from traditional artistic expressions and explores new areas such as digital media, interactive art, and virtual reality. On the other hand, it has triggered a series of debates between creativity and artificial intelligence [9]. Through in-depth research, this paper hopes to explore the characteristics of AI painting, analyze the potential value and challenges for art design, and provide useful suggestions for design practice.…”

Section: Introductionmentioning

confidence: 99%

“…Weiwei Lu, Ruixing Qi and Yuhui Li. Applied Mathematics and Nonlinear Sciences, 9(1) (2024)[1][2][3][4][5][6][7][8][9][10][11][12][13][14] …”

mentioning

confidence: 99%

Artistic characterization of AI painting based on generative adversarial networks

Lu,

Qi,

2024

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

Combined with the creation process of AI painting art, it analyzes the artistic design characteristics of AI paintings formed by generative adversarial networks. It utilizes a convolutional neural network to extract the artistic characteristics of AI paintings and combines the error of feature loss to calculate the features, which ensures the stable operation of the generative adversarial network model. To achieve the style migration of AI painting artworks, the Cycle GAN model was designed on this basis. Comparing the features of both AI paintings of generative adversarial networks and paintings of human artists, the perceptual complexity is taken as the dependent variable, and a regression model is established to analyze and calculate the complexity features of AI paintings, as well as to analyze the color matching art of AI paintings by combining the beauty calculation method. According to the comparison results, the AI paintings have a score of 3.71 for inspirational, 3.69 for aesthetic value, 3.52 for compositional rationality, and 3.38 for breakthrough. The AI paintings have a high level of thought and inspirational value.

show abstract

“…Jun Yan, Hanwen Fan, Yanhua Yang and Feng Miao. Applied Mathematics and Nonlinear Sciences, 9(1) (2024)[1][2][3][4][5][6][7][8][9][10][11][12][13][14] …”

mentioning

confidence: 99%

Research on Visual Design of AI Painting Based on SolidWorks Technology

Yan,

Fan,

Yang

et al. 2024

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

AI technology has become a new creative tool, which brings infinite possibilities for painting creation. In this paper, we first parameterize the design of the painting through SolidWorks software and construct a semantic text with the design parameters obtained. Secondly, the text is inputted into the text-image similarity model based on a graph convolutional network, and the Stanford CoreNLP tool is used to perform dependency parsing on the input text and feature extraction on the textual semantic and spatial relation maps through two GCN networks. Finally, the visual parameters and visual comfort of the AI drawing samples are examined. The results show that the maximum difference between the cumulative scores comparing the reference image and the AI output image is 0.41, and this value is less than 1, which indicates that the AI drawing achieves the visual effect of quantifying the image quality. The efficiency and quality of drawing output can be improved through this study, which has both theoretical and practical significance.

show abstract

Painting Authorship and Forgery Detection Challenges with AI Image Generation Algorithms: Rembrandt and 17th Century Dutch Painters as a Case Study

Cited by 7 publications

References 0 publications

Machine Learning Processes As Sources of Ambiguity: Insights from AI Art

Machine Learning Processes As Sources of Ambiguity: Insights from AI Art

Artistic characterization of AI painting based on generative adversarial networks

Research on Visual Design of AI Painting Based on SolidWorks Technology

Contact Info

Product

Resources

About