Computer Vision in Tactical AI Art
Dejan Grba
AI art comprises a spectrum of creative endeavors that emerge from and respond to the development of artificial intelligence (AI), the expansion of AI-powered economies, and their influence on culture and society. Within this repertoire, the relationship between the cognitive value of human vision and the wide application range of computer vision (CV) technologies opens a sizeable space for exploring the problematic sociopolitical aspects of automated inference and decision-making in modern AI. In this paper, I examine the art practices critically engaged with the notions and protocols of CV. After identifying and contextualizing the CV-related tactical AI art, I discuss the features of exemplar artworks in four interrelated subject areas. Their topical imbrications, common critical points, and shared pitfalls plot a wider landscape of tactical AI art, allowing me to detect factors that affect its poetic cogency, social responsibility, and political impact, some of which exist in the theoretical premises of digital art activism. Along these lines, I outline the routes for addressing the challenges and advancing the field.
Art Notions in the Age of (Mis)anthropic AI
Dejan Grba
In this paper, I take the cultural effects of generative artificial intelligence (generative AI) as a context for examining a broader perspective of AI's impact on contemporary art notions. After the introductory overview of generative AI, I summarize the distinct but often confused aspects of art notions and review the principal lines in which AI influences them: the strategic normalization of AI through art, the representation of AI art in the artworld, academia, and AI research, and the mutual permeability of art and kitsch in the digital culture. I connect these notional factors with the conceptual and ideological substrate of the computer science and AI industry, which blends the machinic agency fetishism, the equalization of computers and humans, the sociotechnical blindness, and cyberlibertarianism. The overtones of alienation, sociopathy, and misanthropy in the disparate but somehow coalescing philosophical premises, technical ideas, and political views in this substrate remain underexposed in AI studies so, in the closing discussion, I outline their manifestations in generative AI and introduce several viewpoints for a further critique of AI's cultural zeitgeist. They add a touch of skepticism to pondering how technological trends change our understanding of art and in which directions they stir its social, economic, and political roles.
Fine-T2I: An Open, Large-Scale, and Diverse Dataset for High-Quality T2I Fine-Tuning
Xu Ma, Yitian Zhang, Qihua Dong
et al.
High-quality and open datasets remain a major bottleneck for text-to-image (T2I) fine-tuning. Despite rapid progress in model architectures and training pipelines, most publicly available fine-tuning datasets suffer from low resolution, poor text-image alignment, or limited diversity, resulting in a clear performance gap between open research models and enterprise-grade models. In this work, we present Fine-T2I, a large-scale, high-quality, and fully open dataset for T2I fine-tuning. Fine-T2I spans 10 task combinations, 32 prompt categories, 11 visual styles, and 5 prompt templates, and combines synthetic images generated by strong modern models with carefully curated real images from professional photographers. All samples are rigorously filtered for text-image alignment, visual fidelity, and prompt quality, with over 95% of initial candidates removed. The final dataset contains over 6 million text-image pairs, around 2 TB on disk, approaching the scale of pretraining datasets while maintaining fine-tuning-level quality. Across a diverse set of pretrained diffusion and autoregressive models, fine-tuning on Fine-T2I consistently improves both generation quality and instruction adherence, as validated by human evaluation, visual comparison, and automatic metrics. We release Fine-T2I under an open license to help close the data gap in T2I fine-tuning in the open community.
Artificial intelligence in fine arts: A systematic review of empirical research
Atte Oksanen, Anica Cvetkovic, Nalan Akin
et al.
99 sitasi
en
Computer Science
Transformation of Beauty in Digital Fine Arts Aesthetics: An Artpreneur Perspective
Tri Aru Wiratno, Brigitta Callula
The evolving nature of beauty in digital fine arts aesthetics signifies profound shifts within contemporary social and cultural contexts. Technological advancements have enabled artists to explore new mediums, creating works that reflect and respond to current societal issues. This study examines the paradigm shift in digital fine arts, focusing on the interpretation and manifestation of beauty in digital creations. It explores the interplay between digital aesthetics and societal realities, providing insights into the transformation of beauty in the digital age. An interdisciplinary approach is utilized, incorporating textual analysis of relevant literature, participatory observation at art exhibitions and online platforms, and a comprehensive literature review. These methods trace the evolution of beauty in digital fine arts and analyze how artists incorporate visual, auditory, and interactive elements. The research demonstrates that technological progress has significantly impacted the creation and perception of beauty in fine arts. This transformation includes broader definitions of aesthetics, integrating multisensory experiences and community participation. Digital fine arts now serve as a dynamic medium that reflects diverse social, political, and cultural themes. The transformation of beauty in this field underscores the complex relationships among art, technology, and society. Digital artworks provide innovative aesthetic experiences and mirror contemporary social dynamics. Despite concerns regarding the authenticity and preservation of digital art, its role in expanding artistic expression and fostering innovation is undeniable
Proceedings of The third international workshop on eXplainable AI for the Arts (XAIxArts)
Corey Ford, Elizabeth Wilson, Shuoyang Zheng
et al.
This third international workshop on explainable AI for the Arts (XAIxArts) brought together a community of researchers in HCI, Interaction Design, AI, explainable AI (XAI), and digital arts to explore the role of XAI for the Arts. Workshop held at the 17th ACM Conference on Creativity and Cognition (C&C 2025), online.
The Directorial Practices of Participation in Contemporary Theatrical Performance
Saif Qusay Yass, Farhan Omran Musa
The twentieth century has produced most of the concepts in constructive criticism of scientific, philosophical and artistic experiences that came under the name of post-modernism, and the term (participation in the theatrical presentation) is one of the modern terms that came from the experiences of directors who rebelled against the realistic trend in art, including (Brecht, Artaud and many others), and through the research, the researcher concluded that participation, although it is a modern term, has deep roots in theatrical experiences throughout the historical ages since the time of the Greeks until now, and that post-modern directors tried to reach through making approaches with some historical experiences and theatrical philosophy for their directing style for the participatory theatrical presentation, and as a result, the researcher took in the theoretical framework the first topic (the space of the participatory presentation of the theater throughout the ages) and the second topic (the directorial works of the participation of the most prominent theatrical directors), and in the third procedural chapter he took the work of a multinational group (Belgian - Turkish ) With a presentation entitled (Gilgamesh) in which the director employed the participatory method and communicative interaction in terms of the spatial environment and the role of the recipient in the theatrical performance, and after that I reached the most prominent results and conclusions that had a positive effect in the participatory work of the theatrical performance .
Spatial Distribution Characteristics and Sustainable Inheritance Strategies of National Traditional Fine Arts Intangible Cultural Heritage in China
Z. Cai, Keke Cai, Tao Huang
et al.
A total of 417 intangible cultural heritage objects (ICHOs) are intertwined with traditional Chinese art, showcasing China’s rich historical heritage and distinctive creative allure. However, ICHOs currently grapple with a significant succession quandary due to modernization endeavors and the impacts of globalization. Hence, this study scrutinizes the spatial distribution of ICHO projects and inheritors and examines methodologies for inheriting these 417 ICHOs, employing approaches such as the closest neighbor index, Moran’s I index, kernel density estimation, geographic concentration analysis, and imbalance index assessment. Research indicates that ICHOs exhibit a spatial aggregation pattern, yet there is no substantial spatial correlation observed in their distribution. The national distribution highlights two core density zones: Beijing and Shanghai. In China, ICHO programs display uneven distribution across various types, levels, regions, and cultural zones. Regarding the ethnic composition of projects and inheritors, ICHO projects predominantly focus on the Han ethnic group, with a scattering of minority representations. Minority ICHO projects and inheritors are concentrated in central and eastern areas, while Han ICHO projects and inheritors are concentrated in central and western regions. Among the 148 ICHO projects lacking inheritors, 203 have one inheritor, and only 66 have several inheritors. Shanghai serves as the core density zone for 269 ICHO projects with inheritors, while Beijing holds that status for 148 ICHO projects without inheritors. Out of the 148 ICHO projects lacking inheritors, 115 belong to the Han ethnic group, with 33 split among 16 different ethnic minorities, and 2 have no inheritors. These disparities underscore the uneven distribution of ICHO projects and the critical issue of inheritance. This study identified education, tourism, digital communication, incentivizing inheritors, and international cooperation as potential strategies for preserving ICHA. Moreover, a sustainable inheritance pathway integrating government, education, tourism, and media is imperative for the effective perpetuation of ICHOs’ legacy.
Integrating sustainability into graphic and industrial design education: A fine arts perspective
Obinna Donald, Joshua Alahira, Zamathula Queen
et al.
The integration of sustainability principles into graphic and industrial design education has become increasingly imperative in response to global environmental challenges. This paper explores the incorporation of sustainable practices within design education, particularly from the perspective of fine arts pedagogy. By examining the intersection of sustainability and design education, this study identifies key strategies and methodologies to infuse sustainable principles into the curriculum. Drawing from fine arts perspectives, it delves into the importance of interdisciplinary collaboration, experiential learning, and critical thinking in fostering sustainable design practices among students. Furthermore, the paper investigates the role of design educators in cultivating a mindset of environmental responsibility and ethical design practices. It explores the challenges and opportunities associated with integrating sustainability into traditional design curricula, emphasizing the need for innovative approaches that blend theory with hands-on application. Through case studies and best practices, this research highlights successful initiatives and projects that demonstrate the effective integration of sustainability into graphic and industrial design education. These examples showcase how incorporating sustainability principles not only enhances the ecological footprint of design processes but also promotes social responsibility and cultural awareness. Overall, this paper contributes to the ongoing discourse on sustainability in design education by offering practical insights and recommendations for educators, institutions, and policymakers. It underscores the transformative potential of integrating sustainability into graphic and industrial design education, envisioning a future where designers play a proactive role in shaping a more sustainable and equitable world.
ECO-INNOVATIVE GRAPHIC DESIGN PRACTICES: LEVERAGING FINE ARTS TO ENHANCE SUSTAINABILITY IN INDUSTRIAL DESIGN
Joshua Alahira, Nwakamma Ninduwezuor-Ehiobu, Kehinde Andrew Olu-lawal
et al.
The intersection of graphic design and sustainability presents a dynamic arena for eco-innovative practices, particularly in the realm of industrial design. This review explores the integration of fine arts principles within graphic design to enhance sustainability initiatives in industrial design processes. The essence lies in leveraging the creative potential of graphic design to foster ecologically conscious solutions, thus contributing to the broader ethos of sustainable development. Eco-innovative graphic design practices encompass a range of strategies aimed at minimizing environmental impact while maximizing aesthetic and functional value. Drawing inspiration from fine arts disciplines, such as painting, sculpture, and photography, designers infuse their work with elements that reflect ecological awareness and responsibility. By integrating themes of nature, conservation, and sustainable living into visual communication, graphic designers play a pivotal role in raising awareness and inspiring action towards sustainable practices. In the context of industrial design, the collaboration between graphic designers and product developers yields innovative solutions that prioritize environmental sustainability. Through thoughtful consideration of materials, production processes, and end-of-life disposal, eco-innovative graphic design practices contribute to the creation of products that are both visually compelling and ecologically sound. Whether through the use of recycled materials, minimalist packaging designs, or biodegradable components, graphic designers harness their artistic prowess to redefine the parameters of sustainable design. Moreover, eco-innovative graphic design practices extend beyond the realm of physical products to encompass digital experiences and branding initiatives. Through digital platforms, designers have the opportunity to promote sustainability messaging, advocate for environmental causes, and encourage behavior change towards more eco-conscious consumption patterns. In conclusion, the integration of fine arts principles within graphic design serves as a catalyst for enhancing sustainability in industrial design. By leveraging creativity, innovation, and visual communication, designers have the power to shape a more sustainable future where ecological considerations are central to the design process. Embracing eco-innovative graphic design practices is not merely a stylistic choice but a conscientious commitment towards harmonizing human creativity with the imperatives of environmental stewardship. Keywords: Eco-Innovative, Graphic Design, Fine Arts, Industrial Design, Sustainability, Review.
THE ROLE OF FINE ARTS IN PROMOTING SUSTAINABILITY WITHIN INDUSTRIAL AND GRAPHIC DESIGN: A CROSS-DISCIPLINARY APPROACH
Joshua Alahira, Emmanuel Chigozie Ani, Nwakamma Ninduwezuor-Ehiobu
et al.
In contemporary design discourse, the intersection of fine arts with industrial and graphic design emerges as a pivotal avenue for promoting sustainability. This paper explores the evolving relationship between fine arts and design disciplines, highlighting their collaborative potential in addressing environmental challenges. By adopting a cross-disciplinary approach, it investigates how incorporating principles of fine arts into industrial and graphic design practices can foster sustainable solutions. The paper begins by contextualizing the current environmental crisis and the imperative for sustainable design interventions. It then delves into the fundamental principles of fine arts, emphasizing its emphasis on creativity, expression, and aesthetic sensibility. Through a comparative analysis, it elucidates how these principles can complement the technical aspects of industrial and graphic design to imbue products and visuals with sustainability-driven narratives. Furthermore, the paper examines case studies and examples where fine arts techniques and philosophies have been integrated into design processes to enhance sustainability. These include practices such as upcycling, biomimicry, and eco-conscious visual communication strategies. Additionally, it explores the role of fine arts education in nurturing a mindset that prioritizes environmental stewardship within design professionals. The findings suggest that by embracing a cross-disciplinary approach that embraces fine arts principles, designers can transcend traditional boundaries to create innovative, sustainable solutions. This synthesis of art and design not only enriches the aesthetic appeal of products and visuals but also instills a deeper consciousness of environmental responsibility. Ultimately, this paper advocates for a holistic integration of fine arts within industrial and graphic design practices as a means to promote sustainability in the face of global challenges. Keywords: Fine Arts, Graphic Design, Cross-Disciplinary, Industrial, Sustainability, Reviews.
The ‘Assetization’ of Art on an Institutional Level—Fractional Ownership Implemented in the Royal Museum of Fine Arts Antwerp
Syra Kalbermatten
This article explores the innovative collaboration between the Rubey platform and the Royal Museum of Fine Arts, Antwerp. Through the tokenization of the artwork Carnaval de Binche by James Ensor, this platform made it possible for interested investors to purchase blockchain-registered Art Security Tokens within this artwork and become co-owners of it—at least from an economic perspective. Although fractional ownership platforms for art have been established before, this is the first time an art investment opportunity like this has materialized itself in an explicit partnership with a museum. The tokenized artwork will be held on public display within the Royal Museum of Fine Arts Antwerp, for a period of ten years—a significant departure from the usual practice of storing such pieces in a storage vault—before it will be sold again. This article contextualizes this practice within both the ‘assetization’ of art that has increased in recent decades and the financial challenges facing Belgian—more broadly speaking, European—public museums. Based on a limited number of interviews with the stakeholders and desk research, this article subsequently explores the more practical benefits and concerns of a collaboration like this and presents an analysis of this practice drawing upon publications within the field of economic sociology. Since we find ourselves only at the beginning of this partnership, some questions will be raised for further research.
Proceedings of The second international workshop on eXplainable AI for the Arts (XAIxArts)
Nick Bryan-Kinns, Corey Ford, Shuoyang Zheng
et al.
This second international workshop on explainable AI for the Arts (XAIxArts) brought together a community of researchers in HCI, Interaction Design, AI, explainable AI (XAI), and digital arts to explore the role of XAI for the Arts. Workshop held at the 16th ACM Conference on Creativity and Cognition (C&C 2024), Chicago, USA.
Art2Mus: Bridging Visual Arts and Music through Cross-Modal Generation
Ivan Rinaldi, Nicola Fanelli, Giovanna Castellano
et al.
Artificial Intelligence and generative models have revolutionized music creation, with many models leveraging textual or visual prompts for guidance. However, existing image-to-music models are limited to simple images, lacking the capability to generate music from complex digitized artworks. To address this gap, we introduce $\mathcal{A}\textit{rt2}\mathcal{M}\textit{us}$, a novel model designed to create music from digitized artworks or text inputs. $\mathcal{A}\textit{rt2}\mathcal{M}\textit{us}$ extends the AudioLDM~2 architecture, a text-to-audio model, and employs our newly curated datasets, created via ImageBind, which pair digitized artworks with music. Experimental results demonstrate that $\mathcal{A}\textit{rt2}\mathcal{M}\textit{us}$ can generate music that resonates with the input stimuli. These findings suggest promising applications in multimedia art, interactive installations, and AI-driven creative tools.
An Art-centric perspective on AI-based content moderation of nudity
Piera Riccio, Georgina Curto, Thomas Hofmann
et al.
At a time when the influence of generative Artificial Intelligence on visual arts is a highly debated topic, we raise the attention towards a more subtle phenomenon: the algorithmic censorship of artistic nudity online. We analyze the performance of three "Not-Safe-For-Work'' image classifiers on artistic nudity, and empirically uncover the existence of a gender and a stylistic bias, as well as evident technical limitations, especially when only considering visual information. Hence, we propose a multi-modal zero-shot classification approach that improves artistic nudity classification. From our research, we draw several implications that we hope will inform future research on this topic.
ARTS: Semi-Analytical Regressor using Disentangled Skeletal Representations for Human Mesh Recovery from Videos
Tao Tang, Hong Liu, Yingxuan You
et al.
Although existing video-based 3D human mesh recovery methods have made significant progress, simultaneously estimating human pose and shape from low-resolution image features limits their performance. These image features lack sufficient spatial information about the human body and contain various noises (e.g., background, lighting, and clothing), which often results in inaccurate pose and inconsistent motion. Inspired by the rapid advance in human pose estimation, we discover that compared to image features, skeletons inherently contain accurate human pose and motion. Therefore, we propose a novel semiAnalytical Regressor using disenTangled Skeletal representations for human mesh recovery from videos, called ARTS. Specifically, a skeleton estimation and disentanglement module is proposed to estimate the 3D skeletons from a video and decouple them into disentangled skeletal representations (i.e., joint position, bone length, and human motion). Then, to fully utilize these representations, we introduce a semi-analytical regressor to estimate the parameters of the human mesh model. The regressor consists of three modules: Temporal Inverse Kinematics (TIK), Bone-guided Shape Fitting (BSF), and Motion-Centric Refinement (MCR). TIK utilizes joint position to estimate initial pose parameters and BSF leverages bone length to regress bone-aligned shape parameters. Finally, MCR combines human motion representation with image features to refine the initial human model parameters. Extensive experiments demonstrate that our ARTS surpasses existing state-of-the-art video-based methods in both per-frame accuracy and temporal consistency on popular benchmarks: 3DPW, MPI-INF-3DHP, and Human3.6M. Code is available at https://github.com/TangTao-PKU/ARTS.
Multi-task real-robot data with gaze attention for dual-arm fine manipulation
Heecheol Kim, Yoshiyuki Ohmura, Yasuo Kuniyoshi
In the field of robotic manipulation, deep imitation learning is recognized as a promising approach for acquiring manipulation skills. Additionally, learning from diverse robot datasets is considered a viable method to achieve versatility and adaptability. In such research, by learning various tasks, robots achieved generality across multiple objects. However, such multi-task robot datasets have mainly focused on single-arm tasks that are relatively imprecise, not addressing the fine-grained object manipulation that robots are expected to perform in the real world. This paper introduces a dataset of diverse object manipulations that includes dual-arm tasks and/or tasks requiring fine manipulation. To this end, we have generated dataset with 224k episodes (150 hours, 1,104 language instructions) which includes dual-arm fine tasks such as bowl-moving, pencil-case opening or banana-peeling, and this data is publicly available. Additionally, this dataset includes visual attention signals as well as dual-action labels, a signal that separates actions into a robust reaching trajectory and precise interaction with objects, and language instructions to achieve robust and precise object manipulation. We applied the dataset to our Dual-Action and Attention (DAA), a model designed for fine-grained dual arm manipulation tasks and robust against covariate shifts. The model was tested with over 7k total trials in real robot manipulation tasks, demonstrating its capability in fine manipulation.
On undying classicism and subverters of foundations
Елена Багина
Directions (styles) in culture have different reserves of strength and different inertia. Among them there is a unique one capable of revival. It is classicism, which is characterized by a timeless understanding of the laws of harmony and beauty based on the forms and images of ancient art of Greece and Rome. Classicist thinking and classicism did not leave European culture in the 20th and 21st centuries, but its forms changed. The grafting of art nouveau, avant-garde and postmodernism into classical art and architecture did not pass without a trace. Antagonists shook the established norms and left, while classical art and architecture expanded the range of creative possibilities and revived, preserving the basic principles.
Examination of 21st Century Skills and Technological Competences of Students of Fine Arts Faculty
O. Ozturk
In this study, 21st century skills and technological tendencies of the students of the Faculty of Fine Arts were examined with a relational approach in terms of some variables. With this aim, the 21st century skills and technological competences of the students of the Faculty of Fine Arts were compared in terms of gender and grade level variables. In this respect, this study is a comparative relational survey research. The study was carried out with 198 students studying fine arts at different universities in Turkey. The 21st century skills scale and the technological susceptibility scale were used as data collection tools. In the study, t-test for independent groups, one-way analysis of variance and correlation analysis techniques were used for data analysis. In the study, it was found that the 21st century skills of fine arts students were relatively high, while their technological susceptibility was moderate. It was found that the 21st century skills and technological predispositions of the participant students differed in terms of gender and grade level. Finally, a positive, significant and high-level relationship was found between the 21st century skills and technological predispositions of the students of the Faculty of Fine Arts.
The Investigation of Creativity Levels of Fine Arts Faculty Students
M. Ozturk, Mehmet Susuz
The aim of this study is to examine the creativity of university students studying in the field of fine arts in terms of demographic and school factors. In this context, the Kaufman creativity areas of the participant students were examined through a comparative approach on the basis of the comparative relational survey research model. The study group of this research consists of 241 Fine Arts Faculty students. Kaufman Creativity Fields Scale was used to collect research data. According to the analysis of the data, the academic creativity of the participating students was low, their mechanical creativity was at a medium level, and their artistic creativity was at a high level. In addition, significant differences were found in the creativity areas and levels of the students according to gender, department type, class and achievement levels. It was observed in the research that the academic creativity of the participating students was low. In this context, activities and practices for students' skills such as research, problem solving, and using the scientific method in original processes can be included in all departments of the relevant faculties.