Hasil untuk "Aesthetics"

Christine M. Hoehner, Laura K Brennan Ramirez, M. Elliott et al.

Yan WU, Suke WU, Zhiqiang ZHAO

ObjectiveThe low-altitude economy covers low-altitude manufacturing, flight operations, support services and comprehensive service industries, and has the characteristics of spatially three-dimensional, regional dependence, digital ecology, industrial integration and radiation driving. With the continuous development of digitization and informatization, these characteristics increasingly affect the interaction between low-altitude activities and urban and natural environments, which provides new ideas for the development of landscape architecture, and the coordinated development of the two is an important issue in the transformation of landscape architecture.MethodsThe knowledge map method was used to analyze the research status of environmental low-altitude economy at home and abroad. By combing and reading relevant literature at home and abroad, the research trends of low-altitude economy in logistics, aviation, ecological monitoring and other fields were systematically analyzed by reviewing literature research, case studies and comparative analysis. ResultsBy analyzing the domestic and foreign research, the internal mechanism of the cross research between landscape architecture and low-altitude economy is revealed four aspects. In the aspect of technology application, low-altitude aircraft tend to be transformed from perception tools to "design intelligence" which can guide ecological design and space construction. In the aspect of spatial planning, landscape architecture will realize the spatial transformation from plane extension to three-dimensional reconstruction under the development of low-altitude economy. In the aspect of ecological impact, the research focus has changed from identifying environmental risks by using low-altitude facilities to systematic assessment and control of ecology. In the aspect of humanistic experience, the combination of low-altitude economy and cultural narrative has further stimulated the vitality of landscape architecture discipline. It is found that under the influence of low-altitude economy, the development of landscape architecture faces some new problems, such as imperfect policies and regulations, insufficient adaptability of spatial planning system, systematic lack of ecological protection, technical bottleneck restriction, homogenization dilemma of cultural and tourism integration, including lack of unified standards for low-altitude facility design, traditional two-dimensional planning being difficult to meet the needs of air-space coordination, ecological destruction caused by noise and habitat disturbance, lack of ecological protection system, etc. There are technical bottlenecks in data processing and flight stability; homogenization of tourism products, focusing on tourism over cultural innovation. In order to promote the coordinated development of the two, this paper puts forward the implementation path of the integration of low-altitude economy and landscape architecture: to ensure the adaptation of policies and regulations, to improve policies and regulations and technical standards, to formulate low-altitude greening design and ecological evaluation standards, and to lay a foundation for the integration of landscape architecture and low-altitude economy; Conduct spatial value evaluation, clarify the use, development subject and income distribution mechanism of each low-altitude area, promote the market-oriented operation of public resources, and use unmanned aerial vehicles to carry out ecological background analysis and evaluate the ecological carrying capacity of low-altitude activities; Conduct functional compound planning, make landscape architecture break through the limitation of traditional ground perspective, bring low-altitude airspace into the vertical space system of landscape architecture, add low-altitude related infrastructure in the garden, and realize efficient coordinated utilization of airspace and ground resources; In ecological service monitoring, we should increase the investment in R&D of UAV technology, low-altitude aircraft noise reduction technology, flight safety guarantee technology, etc., improve the intelligent level of landscape architecture monitoring and management, and establish a new ecological assessment mode; Promote the integrated development of culture and tourism, break through the homogenization dilemma from three dimensions of cultural empowerment, spatial differentiation and experience depth, and integrate garden cultural elements into low-altitude experience links, to improve the overall operation effect. ConclusionBased on the research, we have drawn conclusions in three aspects. 1) The global low-altitude economy industry will become the next development hotspot, and it should accelerate the integration with transportation logistics, cultural tourism and other formats, expand more application scenarios, promote the integration of landscape architecture and related industries, and activate the new vitality of landscape architecture. 2) Green space and parks in cities will become important carriers for low-altitude transportation in the future, and planning and design of low-altitude composite public space will be the focus of research, and research will move from two-dimensional garden aesthetic space to three-dimensional traffic spatial pattern. 3) The development of unmanned aerial vehicle and related technologies provide refined intelligent solutions for intelligent garden management, and low-altitude monitoring data provide new tools for ecological value assessments of gardens, significantly improve ecological monitoring and management levels.

Mengtian Li, Yuwei Lu, Feifei Li et al.

Cinematic camera control relies on a tight feedback loop between director and cinematographer, where camera motion and framing are continuously reviewed and refined. Recent generative camera systems can produce diverse, text-conditioned trajectories, but they lack this "director in the loop" and have no explicit supervision of whether a shot is visually desirable. This results in in-distribution camera motion but poor framing, off-screen characters, and undesirable visual aesthetics. In this paper, we introduce VERTIGO, the first framework for visual preference optimization of camera trajectory generators. Our framework leverages a real-time graphics engine (Unity) to render 2D visual previews from generated camera motion. A cinematically fine-tuned vision-language model then scores these previews using our proposed cyclic semantic similarity mechanism, which aligns renders with text prompts. This process provides the visual preference signals for Direct Preference Optimization (DPO) post-training. Both quantitative evaluations and user studies on Unity renders and diffusion-based Camera-to-Video pipelines show consistent gains in condition adherence, framing quality, and perceptual realism. Notably, VERTIGO reduces the character off-screen rate from 38% to nearly 0% while preserving the geometric fidelity of camera motion. User study participants further prefer VERTIGO over baselines across composition, consistency, prompt adherence, and aesthetic quality, confirming the perceptual benefits of our visual preference post-training.

Jianglin Lu, Simon Jenni, Kushal Kafle et al.

Text-to-image retrieval is a fundamental task in vision-language learning, yet in real-world scenarios it is often challenged by short and underspecified user queries. Such queries are typically only one or two words long, rendering them semantically ambiguous, prone to collisions across diverse visual interpretations, and lacking explicit control over the quality of retrieved images. To address these issues, we propose a new paradigm of quality-controllable retrieval, which enriches short queries with contextual details while incorporating explicit notions of image quality. Our key idea is to leverage a generative language model as a query completion function, extending underspecified queries into descriptive forms that capture fine-grained visual attributes such as pose, scene, and aesthetics. We introduce a general framework that conditions query completion on discretized quality levels, derived from relevance and aesthetic scoring models, so that query enrichment is not only semantically meaningful but also quality-aware. The resulting system provides three key advantages: 1) flexibility, it is compatible with any pretrained vision-language model (VLMs) without modification; 2) transparency, enriched queries are explicitly interpretable by users; and 3) controllability, enabling retrieval results to be steered toward user-preferred quality levels. Extensive experiments demonstrate that our proposed approach significantly improves retrieval results and provides effective quality control, bridging the gap between the expressive capacity of modern VLMs and the underspecified nature of short user queries. Our code is available at https://github.com/Jianglin954/QCQC.

Yuhang Zhao, Xuehua Zhao, Qiucen Guo et al.

Understanding water-related ecosystem services (WESs) and their interrelationships is crucial for effective watershed management. In this study, five key WESs in a watershed were quantified, and their socio-ecological drivers were identified at both grid scale and sub-watershed scale. Trade-offs and synergies were assessed, and WES bundles were delineated across multiple levels to inform spatial planning and management strategies. The results show that: (1) At both scales, the water yield (WY), water conservation (WC), and soil conservation (SC) first decreased then increased, rising by 23.1 %, 9.7 % and 46.5 %, respectively. Water purification (WP) showed a slight and continuous increase, with a 4.6 % increase over 10 years, while landscape aesthetics (LA) decreased steadily, with a cumulative reduction of 21.3 %. (2) The spatio-temporal dynamics of WES pairs at the two scales exhibited distinct synergies and trade-offs. The inter-relationships at the sub-watershed scale were consistently more pronounced than those at the grid scale, both in terms of the overall situation and geographical distribution. Specifically, WC-SC, WY-WP, WC-LA, and SC-LA pairs generally showed synergies, while WC-WP, SC-WP, and WP-LA showed trade-offs. Other WES pairs’ relationships were less significant at both scales. WY-WC and WY-LA relationships improved over time, with synergistic areas up by 6 % and 22 % respectively. Conversely, WY-WP, WC-SC, and WC-LA deteriorated, with areas down by 22 %, 24 %, and 13 %. WY-SC, WC-WP, SC-WP, SC-LA, and WP-LA pairs fluctuated more. (3) Multi-level clustering reveals that clusters less influenced by climate change and human activities are suitable for macro-level management, while those with greater spatio-temporal variability require differentiated management approaches. These findings integrate multi-level and spatio-temporal WES knowledge into watershed planning to support sustainable water resource management.

Riley Grossman, Michael Smith, Cristian Borcea et al.

The main goal of this paper is to study how often cookie banners that comply with the General Data Protection Regulation (GDPR) contain aesthetic manipulation, a design tactic to draw users' attention to the button that permits personal data sharing. As a byproduct of this goal, we also evaluate how frequently the banners comply with GDPR and the recommendations of national data protection authorities regarding banner designs. We visited 2,579 websites and identified the type of cookie banner implemented. Although 45% of the relevant websites have fully compliant banners, we found aesthetic manipulation on 38% of the compliant banners. Unlike prior studies of aesthetic manipulation, we use a computer vision model for salient object detection to measure how salient (i.e., attention-drawing) each banner element is. This enables the discovery of new types of aesthetic manipulation (e.g., button placement), and leads us to conclude that aesthetic manipulation is more common than previously reported (38% vs 27% of banners). To study the effects of user and/or website location on cookie banner design, we include websites within the European Union (EU), where privacy regulation enforcement is more stringent, and websites outside the EU. We visited websites from IP addresses in the EU and from IP addresses in the United States (US). We find that 13.9% of EU websites change their banner design when the user is from the US, and EU websites are roughly 48.3% more likely to use aesthetic manipulation than non-EU websites, highlighting their innovative responses to privacy regulation.

Oliver Mel Allen, Yi Zu, Milo Z. Trujillo et al.

In this work we collected and analyzed social media posts to investigate aesthetic-based radicalization where users searching for Cottagecore content may find Tradwife content co-opted by white supremacists, white nationalists, or other far-right extremist groups. Through quantitative analysis of over 200,000 Tumblr posts and qualitative coding of about 2,500 Tumblr posts, we did not find evidence of a explicit radicalization. We found that problematic Tradwife posts found in the literature may be confined to Tradwife-only spaces, while content in the Cottagecore tag generally did not warrant extra moderation. However, we did find evidence of a mainstreaming effect in the overlap between the Tradwife and Cottagecore communities. In our qualitative analysis there was more interaction between queer and Tradwife identities than expected based on the literature, and some Tradwives even explicitly included queer people and disavowed racism in the Tradwife community on Tumblr. This could be genuine, but more likely it was an example of extremists re-branding their content and following platform norms to spread ideologies that would otherwise be rejected by Tumblr users. Additionally, through temporal analysis we observed a change in the central tags used by Tradwives in the Cottagecore tag pre- and post- 2021. Initially these posts focused on aesthetics and hobbies like baking and gardening, but post-2021 the central tags focused more on religion, traditional gender roles, and homesteading, all markers of reactionary ideals.

Walter Didimo, Fabrizio Montecchiani, Tommaso Piselli

Our work contributes to the fast-growing literature on the use of Large Language Models (LLMs) to perform graph-related tasks. In particular, we focus on usage scenarios that rely on the visual modality, feeding the model with a drawing of the graph under analysis. We investigate how the model's performance is affected by the chosen layout paradigm, the aesthetics of the drawing, and the prompting technique used for the queries. We formulate three corresponding research questions and present the results of a thorough experimental analysis. Our findings reveal that choosing the right layout paradigm and optimizing the readability of the input drawing from a human perspective can significantly improve the performance of the model on the given task. Moreover, selecting the most effective prompting technique is a challenging yet crucial task for achieving optimal performance.

Jinjin Zhang, Qiuyu Huang, Junjie Liu et al.

Ultra-high-resolution image synthesis holds significant potential, yet remains an underexplored challenge due to the absence of standardized benchmarks and computational constraints. In this paper, we establish Aesthetic-4K, a meticulously curated dataset containing dedicated training and evaluation subsets specifically designed for comprehensive research on ultra-high-resolution image synthesis. This dataset consists of high-quality 4K images accompanied by descriptive captions generated by GPT-4o. Furthermore, we propose Diffusion-4K, an innovative framework for the direct generation of ultra-high-resolution images. Our approach incorporates the Scale Consistent Variational Auto-Encoder (SC-VAE) and Wavelet-based Latent Fine-tuning (WLF), which are designed for efficient visual token compression and the capture of intricate details in ultra-high-resolution images, thereby facilitating direct training with photorealistic 4K data. This method is applicable to various latent diffusion models and demonstrates its efficacy in synthesizing highly detailed 4K images. Additionally, we propose novel metrics, namely the GLCM Score and Compression Ratio, to assess the texture richness and fine details in local patches, in conjunction with holistic measures such as FID, Aesthetics, and CLIPScore, enabling a thorough and multifaceted evaluation of ultra-high-resolution image synthesis. Consequently, Diffusion-4K achieves impressive performance in ultra-high-resolution image synthesis, particularly when powered by state-of-the-art large-scale diffusion models (eg, Flux-12B). The source code is publicly available at https://github.com/zhang0jhon/diffusion-4k.

Jordi Pons, Zack Zukowski, Julian D. Parker et al.

We study how musicians use artificial intelligence (AI) across formats like singles, albums, performances, installations, voices, ballets, operas, or soundtracks. We collect 337 music artworks and categorize them based on AI usage: AI composition, co-composition, sound design, lyrics generation, and translation. We find that AI is employed as a co-creative tool, as an artistic medium, and in live performances and installations. Innovative uses of AI include exploring uncanny aesthetics, multilingual and multigenre song releases, and new formats such as online installations. This research provides a comprehensive overview of current AI music practices, offering insights into emerging artistic trends and the challenges faced by AI musicians.

Ankit Sonthalia, Arnas Uselis, Seong Joon Oh

We study whether visual embedding models capture continuous, ordinal attributes along linear directions, which we term _rank axes_. We define a model as _rankable_ for an attribute if projecting embeddings onto such an axis preserves the attribute's order. Across 7 popular encoders and 9 datasets with attributes like age, crowd count, head pose, aesthetics, and recency, we find that many embeddings are inherently rankable. Surprisingly, a small number of samples, or even just two extreme examples, often suffice to recover meaningful rank axes, without full-scale supervision. These findings open up new use cases for image ranking in vector databases and motivate further study into the structure and learning of rankable embeddings. Our code is available at https://github.com/aktsonthalia/rankable-vision-embeddings.

Puyu Han, Jiaju Kang, Yuhang Pan et al.

Large-scale pre-trained diffusion models have produced excellent results in the field of conditional image generation. However, restoration of ancient murals, as an important downstream task in this field, poses significant challenges to diffusion model-based restoration methods due to its large defective area and scarce training samples. Conditional restoration tasks are more concerned with whether the restored part meets the aesthetic standards of mural restoration in terms of overall style and seam detail, and such metrics for evaluating heuristic image complements are lacking in current research. We therefore propose DiffuMural, a combined Multi-scale convergence and Collaborative Diffusion mechanism with ControlNet and cyclic consistency loss to optimise the matching between the generated images and the conditional control. DiffuMural demonstrates outstanding capabilities in mural restoration, leveraging training data from 23 large-scale Dunhuang murals that exhibit consistent visual aesthetics. The model excels in restoring intricate details, achieving a coherent overall appearance, and addressing the unique challenges posed by incomplete murals lacking factual grounding. Our evaluation framework incorporates four key metrics to quantitatively assess incomplete murals: factual accuracy, textural detail, contextual semantics, and holistic visual coherence. Furthermore, we integrate humanistic value assessments to ensure the restored murals retain their cultural and artistic significance. Extensive experiments validate that our method outperforms state-of-the-art (SOTA) approaches in both qualitative and quantitative metrics.

Hidde Makimei, Shuai Wang, Willem van Peursen

The past years witnessed a significant amount of Artificial Intelligence (AI) tools that can generate images from texts. This triggers the discussion of whether AI can generate accurate images using text from the Bible with respect to the corresponding biblical contexts and backgrounds. Despite some existing attempts at a small scale, little work has been done to systematically evaluate these generated images. In this work, we provide a large dataset of over 7K images using biblical text as prompts. These images were evaluated with multiple neural network-based tools on various aspects. We provide an assessment of accuracy and some analysis from the perspective of religion and aesthetics. Finally, we discuss the use of the generated images and reflect on the performance of the AI generators.

Yichen Ye, Xiaofan Yu

This research aims to explore the impact of museum cultural and creative products on consumers’ cultural interest. Based on previous literature, this research proposed a research model to explore the crucial factors influencing consumers’ cultural interest. This research selected bookmarks from Dunhuang Museum’s cultural and creative products as a research case and conducted a questionnaire survey on consumers. A total of 370 valid questionnaires were collected, and structural equation modelling was used to analyze the questionnaire data. The study finds that 1) brand value, authenticity, function, and aesthetics significantly affect cultural interest, and innovation has a non-significant effect on cultural interest; 2) aesthetics and brand values have the greatest impact on cultural interest; and 3) attributes of museum cultural and creative products indirectly influence cultural interest through perceived value, satisfaction, and curiosity. This study provides a new theoretical perspective for the study of museum cultural and creative products and deepens our understanding of consumers’ cultural interest.

Sérgio M. Rebelo, J. J. Merelo, João Bicker et al.

Computational Design approaches facilitate the generation of typographic design, but evaluating these designs remains a challenging task. In this paper, we propose a set of heuristic metrics for typographic design evaluation, focusing on their legibility, which assesses the text visibility, aesthetics, which evaluates the visual quality of the design, and semantic features, which estimate how effectively the design conveys the content semantics. We experiment with a constrained evolutionary approach for generating typographic posters, incorporating the proposed evaluation metrics with varied setups, and treating the legibility metrics as constraints. We also integrate emotion recognition to identify text semantics automatically and analyse the performance of the approach and the visual characteristics outputs.

Lidia Klein

Postmodern forms and tendencies that appeared in Chilean architecture in the 1970s not only overlapped with Augusto Pinochet’s neoliberal dictatorship that lasted from 1973 to 1990 but also are closely connected to the political and economic vision fostered by the dictatorship. Postmodern forms found in banks, hotels, and other commercial buildings and spaces populating Chilean cities in the seventies and eighties aided the government’s political agenda as they helped to normalize painful neoliberal reforms and create an image of prosperity and progress. Moreover, in projects such as the Plaza de la Constitución in Santiago de Chile (1980–1982) and the Congreso Nacional de Chile in Valparaíso (1988–1990), postmodern aesthetics and philosophy were used to project an image of an open democratic country. In these realizations, postmodern tropes such as the symbolic potential of architectural form and references to architectural tradition were used to fabricate a vision of history and society desired by the Pinochet government. Simultaneously, the same architectural currents embraced by Pinochet for propagandistic purposes were utilized by Chilean architects who considered themselves opposed to the dictatorship. This can be seen in the work of CEDLA (Centro de Estudios de la Arquitectura, Center for Architectural Studies), an independent collective of Chilean architects established in 1977 in Santiago de Chile. The members of CEDLA promoted a version of a politically and socially engaged postmodernism that could counter the neoliberal agenda of Pinochet. This paper discusses both ways in which postmodernism was interpreted in Chile during the dictatorship. Investigating Chilean postmodernism helps us rethink the dominant portrayal of postmodernism as politically indifferent or conservative and as part of Jameson’s ‘cultural logic of late capitalism’.

ZHUANG Ziting, BAO Rui , LI Menghuan et al.

Objective The aim of this study was to investigate the effect of changes in nasal tip protrusion on the sense of upper lip protrusion in different populations and to provide a reference for the improvement of soft tissue beauty. Methods Informed consent and portrait authorization were obtained from the model. A female model whose face met the criteria was selected, and a 3D model of her was obtained using a 3D stereo camera. Based on the original model, ZBRUSH2019 software was used to simulate changes in nose tip protrusion. Then, 9 segments of facial dynamic rotation videos were produced, and an electronic questionnaire was created through a questionnaire website to evaluate the effect of different nose tip protrusions on perceived upper lip protrusion. Randomly selected orthodontic patients, orthodontics professionals and general adults completed the electronic questionnaire. In the questionnaire, a Visual Analog Scale was used to evaluate the perceived degree of protrusion of the upper lip. The higher the score, the more prominent the upper lip of the model in the image. The questionnaire data were statistically analyzed using a generalized linear mixed model. Results As the nasal tip position became progressively more retracted, the subjects' upper lip protrusion scores increased. Among male subjects, the results showed that the general population thought that the upper lip protrusion was higher than the patients did when the nasal tip protrusion was +6 mm and +4.5 mm (P = 0.023, P = 0.047). When the nasal tip protrusion was +6 mm, the scores of the general population were higher than those of the orthodontics professionals (P = 0.023). However, when the nasal tip variable was -6 mm, their score was lower than that of the patients (P = 0.003), and there was no significant difference in other retest distances between groups (P>0.05). Conclusion When the protrusion of the nasal tip decreased, the three groups experienced a visual illusion of upper lip protrusion. When the nasal tip protrusion is too large, the general population perceived the visual illusion of the upper lip protrusion as being more obvious.

Nassim Dehouche, Kullathida Dehouche

Text-to-Image artificial intelligence (AI) recently saw a major breakthrough with the release of Dall-E and its open-source counterpart, Stable Diffusion. These programs allow anyone to create original visual art pieces by simply providing descriptions in natural language (prompts). Using a sample of 72,980 Stable Diffusion prompts, we propose a formalization of this new medium of art creation and assess its potential for teaching the history of art, aesthetics, and technique. Our findings indicate that text-to-Image AI has the potential to revolutionize the way art is taught, offering new, cost-effective possibilities for experimentation and expression. However, it also raises important questions about the ownership of artistic works. As more and more art is created using these programs, it will be crucial to establish new legal and economic models to protect the rights of artists.

Christopher Barakat, Guillermo Escalante, Scott W. Stevenson et al.

Background: The purpose of this case study was to implement an evidence-based dietary approach to peaking for a bodybuilding competition and monitor its impact on body composition, muscle thickness (MT), intra-to-extra-cellular fluid shifts, subcutaneous thickness (ST), and hydration status. Secondarily, to document any adverse events of this peak week approach in a small, controlled setting. Methods Dietary practices were recorded, and laboratory testing was conducted throughout peak week, including competition morning. Assessments included: dual-energy X-ray absorptiometry (DEXA) for body composition, B-mode ultrasound for MT and ST, bioimpedance spectroscopy (BIS) for total body water (TBW)/intracellular water (ICW)/extracellular water (ECW), and raw BIS data (i.e., resistance, reactance, and phase angle), urine specific gravity (USG) for hydration status, and subjective fullness. Sequential dietary manipulations were made (i.e., CHO depletion/fat loading, CHO/water loading, and a refinement phase) with specific physiological goals. This was reflected in changes observed across all assessments throughout the peak week. Results: From the carbohydrate-depleted state (three days out) to competition day, we observed increases in lean body mass, MT, TBW (primarily ICW), and subjective fullness. Kendall’s Tau B revealed a strong relationship between carbohydrate intake and ∑MT (τ = 0.733, <i>p</i> = 0.056). Additionally, novel ST data demonstrated a 10% reduction for the summation of all seven sites, with some drastic changes in specific regions (e.g., −43% for triceps ST) from three days out to competition day. Conclusions: These data suggest that the prototypical goals of bodybuilders’ peak week (i.e., increasing muscle fullness, decreasing subcutaneous thickness) to enhance their aesthetics/muscularity presented can be achieved with a drug-free protocol involving dietary manipulations.

Mathilde Fautras, Blandine Veith

The commodification and patrimonialization of nature have often been studied separately or considered as contradictory. Following research that highlights the combination of these social logics in tension, this article questions their intertwining by focusing on a seemingly innocuous ornamental plant : the rose intended for bouquets. The paper focuses on the process of creation, which is less studied than that of production or preservation, in order to analyse the characteristics of the new varieties, commercial objects with symbolic values and codified uses. Based on empirical data, the article shows the evolution of cut roses bred in Europe and produced in Kenya, by tracing the partial diffusion of the aesthetic of pseudo-ancient varieties. It shows how the intertwining of market and heritage logics, materialised in the aesthetics of a plant, shed light on the dynamics of a globalised production sector.