Hasil untuk "Aesthetics"

N. Tractinsky, Adi Katz, D. Ikar

Ariane L. Bedimo-Rung, A. Mowen, D. Cohen

Miriam Doh, Aditya Gulati, Corinna Canali et al.

This paper examines algorithmic lookism-the systematic preferential treatment based on physical appearance-in text-to-image (T2I) generative AI and a downstream gender classification task. Through the analysis of 26,400 synthetic faces created with Stable Diffusion 2.1 and 3.5 Medium, we demonstrate how generative AI models systematically associate facial attractiveness with positive attributes and vice-versa, mirroring socially constructed biases rather than evidence-based correlations. Furthermore, we find significant gender bias in three gender classification algorithms depending on the attributes of the input faces. Our findings reveal three critical harms: (1) the systematic encoding of attractiveness-positive attribute associations in T2I models; (2) gender disparities in classification systems, where women's faces, particularly those generated with negative attributes, suffer substantially higher misclassification rates than men's; and (3) intensifying aesthetic constraints in newer models through age homogenization, gendered exposure patterns, and geographic reductionism. These convergent patterns reveal algorithmic lookism as systematic infrastructure operating across AI vision systems, compounding existing inequalities through both representation and recognition. Disclaimer: This work includes visual and textual content that reflects stereotypical associations between physical appearance and socially constructed attributes, including gender, race, and traits associated with social desirability. Any such associations found in this study emerge from the biases embedded in generative AI systems-not from empirical truths or the authors' views.

Aviv L. Cohav, A. Xinran Gong, J. Taery Kim et al.

Dog guides offer an effective mobility solution for blind or visually impaired (BVI) individuals, but conventional dog guides have limitations including the need for care, potential distractions, societal prejudice, high costs, and limited availability. To address these challenges, we seek to develop a robot dog guide capable of performing the tasks of a conventional dog guide, enhanced with additional features. In this work, we focus on design research to identify functional and aesthetic design concepts to implement into a quadrupedal robot. The aesthetic design remains relevant even for BVI users due to their sensitivity toward societal perceptions and the need for smooth integration into society. We collected data through interviews and surveys to answer specific design questions pertaining to the appearance, texture, features, and method of controlling and communicating with the robot. Our study identified essential and preferred features for a future robot dog guide, which are supported by relevant statistics aligning with each suggestion. These findings will inform the future development of user-centered designs to effectively meet the needs of BVI individuals.

Miguel Carrasco, César González-Martín, José Aranda et al.

Visual attention mechanisms play a crucial role in human perception and aesthetic evaluation. Recent advances in Vision Transformers (ViTs) have demonstrated remarkable capabilities in computer vision tasks, yet their alignment with human visual attention patterns remains underexplored, particularly in aesthetic contexts. This study investigates the correlation between human visual attention and ViT attention mechanisms when evaluating handcrafted objects. We conducted an eye-tracking experiment with 30 participants (9 female, 21 male, mean age 24.6 years) who viewed 20 artisanal objects comprising basketry bags and ginger jars. Using a Pupil Labs eye-tracker, we recorded gaze patterns and generated heat maps representing human visual attention. Simultaneously, we analyzed the same objects using a pre-trained ViT model with DINO (Self-DIstillation with NO Labels), extracting attention maps from each of the 12 attention heads. We compared human and ViT attention distributions using Kullback-Leibler divergence across varying Gaussian parameters (sigma=0.1 to 3.0). Statistical analysis revealed optimal correlation at sigma=2.4 +-0.03, with attention head #12 showing the strongest alignment with human visual patterns. Significant differences were found between attention heads, with heads #7 and #9 demonstrating the greatest divergence from human attention (p< 0.05, Tukey HSD test). Results indicate that while ViTs exhibit more global attention patterns compared to human focal attention, certain attention heads can approximate human visual behavior, particularly for specific object features like buckles in basketry items. These findings suggest potential applications of ViT attention mechanisms in product design and aesthetic evaluation, while highlighting fundamental differences in attention strategies between human perception and current AI models.

Zhilin Zhang, Xiang Zhang, Jiaqi Wei et al.

Multi-agent systems built upon large language models (LLMs) have demonstrated remarkable capabilities in tackling complex compositional tasks. In this work, we apply this paradigm to the paper-to-poster generation problem, a practical yet time-consuming process faced by researchers preparing for conferences. While recent approaches have attempted to automate this task, most neglect core design and aesthetic principles, resulting in posters that require substantial manual refinement. To address these design limitations, we propose PosterGen, a multi-agent framework that mirrors the workflow of professional poster designers. It consists of four collaborative specialized agents: (1) Parser and Curator agents extract content from the paper and organize storyboard; (2) Layout agent maps the content into a coherent spatial layout; (3) Stylist agents apply visual design elements such as color and typography; and (4) Renderer composes the final poster. Together, these agents produce posters that are both semantically grounded and visually appealing. To evaluate design quality, we introduce a vision-language model (VLM)-based rubric that measures layout balance, readability, and aesthetic coherence. Experimental results show that PosterGen consistently matches in content fidelity, and significantly outperforms existing methods in visual designs, generating posters that are presentation-ready with minimal human refinements.

Hovhannes Margaryan, Bo Wan, Tinne Tuytelaars

This paper introduces a novel approach to aesthetic quality improvement in pre-trained text-to-image diffusion models when given a simple prompt. Our method, dubbed Prompt Embedding Optimization (PEO), leverages a pre-trained text-to-image diffusion model as a backbone and optimizes the text embedding of a given simple and uncurated prompt to enhance the visual quality of the generated image. We achieve this by a tripartite objective function that improves the aesthetic fidelity of the generated image, ensures adherence to the optimized text embedding, and minimal divergence from the initial prompt. The latter is accomplished through a prompt preservation term. Additionally, PEO is training-free and backbone-independent. Quantitative and qualitative evaluations confirm the effectiveness of the proposed method, exceeding or equating the performance of state-of-the-art text-to-image and prompt adaptation methods.

Luca Diotallevi

The aim of the paper is to deal with the question of the form of Catholic places of worship in the current secularization process phase, and with special reference to the Italian case and once assumed a sociological perspective. First of all, the relevance of the artifacts for the sociological understanding of secularization will be highlighted. The next step will be dedicated to the reciprocal and very important relationships between the form of the place of worship and the type of social order. These relationships will be illustrated by focusing on the relationship between the religious dimension of Catholicism and some different variants of secularization. Having elaborated on this basis a typology of forms of the religious dimension of Catholicism, it will show and discuss how the solution of some architectural questions can influence the success or the demise of one or an other among different forms that the religious dimension of Catholicism can assume copying with the secularization process current phase.

Sara Çebi

The research examines the use of waste materials as a teaching resource in art classes. Third year students of Trabzon University Faculty of Fine Arts and Design, Department of Painting collected and sorted textile wastes randomly thrown into the environment and transformed these materials into artworks by wood printing method in the school's printing workshop. In this study, which adopted exploratory, experimental and descriptive research methods, 12 artworks were analyzed. The study reveals the effects of instructional resources on classroom atmosphere, student performance and shows that improper management of textile waste contributes to environmental pollution with aims to draw attention to the effects of textile waste for increase environmental aesthetics and awareness in society. Within the scope of the Applied Workshop II course, students transformed textile wastes collected from the environment into works of art with wood printing method. Students were informed about the wood printing technique and the place of recycling in art, and in the light of this information, they transformed fabric wastes into artistic compositions. This process contributed to the students' practical application of their theoretical knowledge and environmental awareness. The works were designed according to the color element and the principle of balance. Artists use colors to describe and depict the subject. The principle of balance is important for a work to be clear and harmonious. Students were asked to create their compositions according to these elements. Students were encouraged to participate in comments and criticism and a program was organized to discuss art production together.

Fan Yang, Jianan Wei, Xuejun Zhao et al.

Abstract BackgroundMobile phone apps powered by artificial intelligence (AI) have emerged as powerful tools to address mental health challenges faced by children. ObjectiveThis study aimed to comprehensively review AI-driven apps for child mental health, focusing on their availability, quality, readability, characteristics, and functions. MethodsThis study systematically analyzed AI-based mobile apps for child mental health. Quality was evaluated using the Mobile Application Rating Scale, which assessed various dimensions of app quality, including subjective quality, engagement, functionality, aesthetics, and information. An automatic readability index calculator was implemented to assess readability by using the count of words, syllables, and sentences to generate a score indicative of the reading difficulty level. Content analysis was conducted to examine the apps’ availability, characteristics, and functionality. ResultsOut of 369 apps initially identified, 27 met the eligibility criteria for inclusion. The quality of the apps was assessed using Mobile Application Rating Scale, with an average score of 3.45 out of 5 (SD 0.5), indicating a need for quality improvement. The readability analysis revealed suboptimal scores, with an average grade level of 6.62 (SD 2.2) for in-app content and 9.93 (SD 2.6) for app store descriptions. These results, combined with a monotonous user interface, suggest that many apps lack a child-friendly design, potentially hindering their usability and engagement for young users. Content analysis categorized the apps into 3 functional groups—chatbot-based apps (15 apps), journal logging apps (9 apps), and psychotherapeutic treatment apps (3 apps). While 20 out of 27 apps (74%) used clinically validated technologies, rigorous clinical tests of the apps were often missing, with only 2 apps undergoing clinical trials. Of the 27 apps analyzed, only 7 (26%) were free to use, while the majority, 20 apps, required a subscription or one-time payment. Among the paid apps, the average cost was US $20.16 per month, which may pose a financial barrier and limit accessibility for some users, particularly those from lower-income households. ConclusionsAI-based mental health apps hold significant potential to address the unique challenges of child mental health but face critical limitations in design, accessibility, and validation. To fully realize their benefits, future research and development should focus on integrating child-centric design principles, ensuring affordability, and prioritizing rigorous clinical testing. These efforts are essential to harness the power of AI technologies in creating equitable, effective, and engaging solutions for improving child mental health outcomes.

Christopher Griffin

Sylvia Wynter seeks nothing less than a redescription of the human, an ecumenical self-representation that would overcome the violent exclusions of coloniality and overturn the reign of Man. Given that our present concept of representation sustains the universalising overrepresentation of Man, what transformations are required for this new image of the human to surface? What are the epistemological implications for radical aesthetics today? This article brings Wynter into dialogue with Jacques Derrida to address these questions through the examination of colonial narratives and counternarratives; namely, David Lloyd’s reading of the Kantian-Hegelian dialectic of consciousness, and Annalee Newitz’s speculative fiction Autonomous.

DONG Zhe, LI Qiaoqiao, YANG Jiegang, FU Yuchuan, LI Jian

Objective To evaluate the clinical efficacy of costal cartilage septal-columellar composite grafts in refining nasal tip aesthetics for secondary unilateral cleft lip nasal deformities, and to provide a reference for clinical treatment. Methods This study has been approved by the institutional medical ethics committee and informed consent was obtained from the patients. A total of 31 patients underwent surgery with a costal cartilage strut-septum complex stent graft. The follow-up period was a minimum of 6 months. Anteroposterior, lateral, and supine photos of the patient were taken before and after the operation. The following measurements were obtained: nasal tip projection (NTP), nasofrontal angle (NFA), nasolabial angle (NLA), nasal tip alar angle (NAA), and nasal tip tangent angle (NTA). Nostril-related indices [nostril area (S), nostril height (h₁), nostril width (w), and nasal sill height (h₂)]) were measured before and after surgery, and cleft/non-cleft side ratios were calculated. Satisfaction with nasal tip aesthetics was investigated using the visual analogue scale (VAS). All measurements were made using preoperative photographs and the most recent follow-up photographs of the patients. Results The follow-up period ranged from 6 to 49 months, with an average of 28 months. All patients underwent healing by first intention. Compared with preoperative measurements, postoperative NTP (preoperative 0.48 <i>vs</i>. postoperative 0.55), NLA (preoperative 83.98&#x00B0; <i>vs</i>. postoperative 100.80&#x00B0;), and NAA (preoperative 160.30&#x00B0; <i>vs</i>. postoperative 168.40&#x00B0;) were significantly increased (<i>P </i>&lt; 0.05). NFA (preoperative 139.20&#x00B0; <i>vs</i>. postoperative 133.50&#x00B0;,<i> P </i>&lt; 0.05) and NTA (preoperative 43.76&#x00B0; <i>vs</i>. postoperative 35.80&#x00B0;, <i>P</i> = 0.062) were decreased. On the cleft versus non-cleft sides, the ratios of S (preoperative 1.10 <i>vs</i>. postoperative 0.94, <i>P </i>&lt; 0.05), w (preoperative 1.10 <i>vs</i>. postoperative 1.02, <i>P</i> = 0.194), h₁ (preoperative 0.71 <i>vs</i>. postoperative 0.90, <i>P </i>&lt; 0.05), and h₂ (preoperative 0.53 <i>vs</i>. postoperative 0.79, <i>P</i> = 0.065) were all near 1. Satisfaction with postoperative results was fairly high. Conclusion The costal cartilage strut-septum complex stent can effectively correct the deflection and collapse of the nasal tip in patients with unilateral cleft lip nose deformity. The postoperative long-term effect is relatively stable.

Zeyu Liu, Weicong Liang, Yiming Zhao et al.

Recently, Glyph-ByT5 has achieved highly accurate visual text rendering performance in graphic design images. However, it still focuses solely on English and performs relatively poorly in terms of visual appeal. In this work, we address these two fundamental limitations by presenting Glyph-ByT5-v2 and Glyph-SDXL-v2, which not only support accurate visual text rendering for 10 different languages but also achieve much better aesthetic quality. To achieve this, we make the following contributions: (i) creating a high-quality multilingual glyph-text and graphic design dataset consisting of more than 1 million glyph-text pairs and 10 million graphic design image-text pairs covering nine other languages, (ii) building a multilingual visual paragraph benchmark consisting of 1,000 prompts, with 100 for each language, to assess multilingual visual spelling accuracy, and (iii) leveraging the latest step-aware preference learning approach to enhance the visual aesthetic quality. With the combination of these techniques, we deliver a powerful customized multilingual text encoder, Glyph-ByT5-v2, and a strong aesthetic graphic generation model, Glyph-SDXL-v2, that can support accurate spelling in 10 different languages. We perceive our work as a significant advancement, considering that the latest DALL-E3 and Ideogram 1.0 still struggle with the multilingual visual text rendering task.

Colin Conwell, Christopher Hamblin, Chelsea Boccagno et al.

When we experience a visual stimulus as beautiful, how much of that experience derives from perceptual computations we cannot describe versus conceptual knowledge we can readily translate into natural language? Disentangling perception from language in visually-evoked affective and aesthetic experiences through behavioral paradigms or neuroimaging is often empirically intractable. Here, we circumnavigate this challenge by using linear decoding over the learned representations of unimodal vision, unimodal language, and multimodal (language-aligned) deep neural network (DNN) models to predict human beauty ratings of naturalistic images. We show that unimodal vision models (e.g. SimCLR) account for the vast majority of explainable variance in these ratings. Language-aligned vision models (e.g. SLIP) yield small gains relative to unimodal vision. Unimodal language models (e.g. GPT2) conditioned on visual embeddings to generate captions (via CLIPCap) yield no further gains. Caption embeddings alone yield less accurate predictions than image and caption embeddings combined (concatenated). Taken together, these results suggest that whatever words we may eventually find to describe our experience of beauty, the ineffable computations of feedforward perception may provide sufficient foundation for that experience.

Junwen He, Yifan Wang, Lijun Wang et al.

Text logo design heavily relies on the creativity and expertise of professional designers, in which arranging element layouts is one of the most important procedures. However, this specific task has received limited attention, often overshadowed by broader layout generation tasks such as document or poster design. In this paper, we propose a Vision-Language Model (VLM)-based framework that generates content-aware text logo layouts by integrating multi-modal inputs with user-defined constraints, enabling more flexible and robust layout generation for real-world applications. We introduce two model techniques that reduce the computational cost for processing multiple glyph images simultaneously, without compromising performance. To support instruction tuning of our model, we construct two extensive text logo datasets that are five times larger than existing public datasets. In addition to geometric annotations (\textit{e.g.}, text masks and character recognition), our datasets include detailed layout descriptions in natural language, enabling the model to reason more effectively in handling complex designs and custom user inputs. Experimental results demonstrate the effectiveness of our proposed framework and datasets, outperforming existing methods on various benchmarks that assess geometric aesthetics and human preferences.

Jia-Wei Liao, Winston Wang, Tzu-Sian Wang et al.

With the success of Diffusion Models for image generation, the technologies also have revolutionized the aesthetic Quick Response (QR) code generation. Despite significant improvements in visual attractiveness for the beautified codes, their scannabilities are usually sacrificed and thus hinder their practical uses in real-world scenarios. To address this issue, we propose a novel training-free Diffusion-based QR Code generator (DiffQRCoder) to effectively craft both scannable and visually pleasing QR codes. The proposed approach introduces Scanning-Robust Perceptual Guidance (SRPG), a new diffusion guidance for Diffusion Models to guarantee the generated aesthetic codes to obey the ground-truth QR codes while maintaining their attractiveness during the denoising process. Additionally, we present another post-processing technique, Scanning Robust Manifold Projected Gradient Descent (SR-MPGD), to further enhance their scanning robustness through iterative latent space optimization. With extensive experiments, the results demonstrate that our approach not only outperforms other compared methods in Scanning Success Rate (SSR) with better or comparable CLIP aesthetic score (CLIP-aes.) but also significantly improves the SSR of the ControlNet-only approach from 60% to 99%. The subjective evaluation indicates that our approach achieves promising visual attractiveness to users as well. Finally, even with different scanning angles and the most rigorous error tolerance settings, our approach robustly achieves over 95% SSR, demonstrating its capability for real-world applications. Our project page is available at https://jwliao1209.github.io/DiffQRCoder.

Yuk Hui

This article aims to reconstruct Simondon’s concept of technophany, which disperses throughout different writings that appeared posthumously and suggest how elaborating this concept could be understood as a significant philosophical task today. Technophany, namely the manifestation of technicity, is central to Simondon’s thought on techno-aesthetics and, more importantly, his intellectual project of reintegrating technology into culture. However, when we place Simondon’s concept of technophany in today’s context, namely the convergence of technology, art and design since the second half of the 20th century, we see that technophanies are becoming more or less ordinary marketing phenomena of the tech industry. Then, could the concept of technophany still take up this task of reconciling technology and culture? Or, instead, is it reduced to a mere economic category, and Simondon’s techno-aesthetics is only a forerunner of today’s industrial marketing strategies? In order to respond to these questions, this article returns to the source of Simondon’s concept of technicity. It shows that there is an intimacy between technophany and Mircea Eliade’s concept of hierophany, and indeed, Simondon’s genesis of technicity vividly mirrors Eliade’s analysis of sacrality and its crisis in modern times. The concept of technophany acquires a new meaning, and it refuses to be a mere phenomenon of publicity as one might easily misread it. Technophany has the task of occupying the “no man’s land” between technicity and sacrality. However, what exactly does it mean? Through the reconstruction of the concept of technophany in Simondon’s thought, this article hopes to examine the limit of the concept and, at the same time, reconceptualise and prolong it.

Oscar Barnay

The article aims to highlight the particularities of photomontage as a representation of the architectural project, using photography as a supporting image. It develops an image analysis of a photomontage produced by the architects Lacaton & Vassal in the context of the competition for the construction of the FRAC Grand-Large, in Dunkirk, France, 2009. Through this examination, the following issues are addressed: the indiciality of the photographs used as a support for the photomontages, the way in which the image registers deployed by a photomontage can be presented as embodiments of an architectural project. Thus, the images become both representations and metaphors of the project, capable of serving the architects’ purpose.

Mark Harris

Thomas Crow’s book The Artist in the Counterculture: Bruce Conner to Mike Kelley and Other Tales from the Edge reappraises West Coast art as enmeshed in the counterculture. The first five of its twelve chapters discuss Bruce Conner’s development as a multimedia artist in San Franscisco and Los Angeles producing assemblages, films, drawings, magazine illustrations, and light shows for rock concerts. The next five chapters expand Crow’s argument by appraising anti-war manifestations, Black and Latino protest work, Land Art, and West Coast conceptual practices as aspects of the counterculture. Moving forward to the late 1970s, the final two chapters review first Conner’s reemergence as a photographer documenting California punk bands and then Mike Kelley’s transplanting of Detroit’s alternative rock idealism to fuel the development of his own radical art practices.

Manu Thundathil, Ali Reza Nazmi, Bahareh Shahri et al.

Biobased composites, which are considered a sustainable alternative to plastics, are yet to create a significant influence on product design and manufacturing. A key reason for this is perceptual handicaps associated with biobased composites and this study was aimed at understanding the mechanisms behind biocomposite perception, in the context of digital visuals. This study of digital biocomposite visuals demonstrated that material perception is influenced by the visual characteristics of the material. Data analysis of the perceptual attributes of the materials pointed towards clear ‘clustering’ of the materials against these attributes. Analysis shows that visual features like fibres and surface appearance may impact aesthetic and functional evaluation and there is no effect on age, gender or polymer type. We also propose a reference framework to categorise biobased composites based on visual order.