Portrait composition plays a central role in portrait aesthetics and visual communication, yet existing datasets and benchmarks mainly focus on coarse aesthetic scoring, generic image aesthetics, or unconstrained portrait generation. This limits systematic research on structured portrait composition analysis and controllable portrait generation under explicit composition requirements. In this paper, we introduce PortraitCraft, a unified benchmark for portrait composition understanding and generation. PortraitCraft is built on a dataset of approximately 50,000 curated real portrait images with structured multi-level supervision, including global composition scores, annotations over 13 composition attributes, attribute-level explanation texts, visual question answering pairs, and composition-oriented textual descriptions for generation. Based on this dataset, we establish two complementary benchmark tasks for composition understanding and composition-aware generation within a unified framework. The first evaluates portrait composition understanding through score prediction, fine-grained attribute reasoning, and image-grounded visual question answering, while the second evaluates portrait generation from structured composition descriptions under explicit composition constraints. We further define standardized evaluation protocols and provide reference baseline results with representative multimodal models. PortraitCraft provides a comprehensive benchmark for future research on fine-grained portrait understanding, interpretable aesthetic assessment, and controllable portrait generation.
Deva Menéndez García, Daniel Carmona Cardona , Isabella Tobón Franco
Este trabajo analiza el impacto del neoliberalismo en el diseño urbano y la sostenibilidad de Medellín, centrándose en la transformación de la ciudad bajo políticas neoliberales desde la década de 1980. A partir de la revisión de los principales instrumentos de planeación del Área Metropolitana de Medellín —como la Ordenanza Departamental n.º 34 de 1980, el Plan Integral de Desarrollo Metropolitano (PIDM) 2008-2020 y el Acuerdo Metropolitano 40 de 2007—, se evalúa la planeación del Valle de Aburrá como centro conurbado y la efectividad de sus políticas públicas ambientales. Asimismo, se examina la interacción entre los sectores público y privado en proyectos urbanos estratégicos, como Metroplús y el Parque Arví. Los hallazgos evidencian una fragmentación social, territorial y ambiental, así como una estética urbana orientada al turismo ecológico, cuyos efectos en la sostenibilidad y la equidad social resultan cuestionables. Se concluye que estos elementos han sido instrumentalizados como herramientas de neoliberalización urbana, lo que pone en entredicho su verdadera contribución a la justicia ambiental y social.
Aesthetics of cities. City planning and beautifying, Urban groups. The city. Urban sociology
An urban central metro station area is a core hub within the high-quality Transit-Oriented Development (TOD) model. This study explores users’ perceptions of built environments around urban central metro stations to investigate the critical determinants of user satisfaction and proposes strategies to enhance the quality of these environments. First, a comprehensive perception system, including location situation, field environment, and urban aesthetics, was developed through literature reviews and expert consultation. Secondly, three typical central metro station areas in Chengdu were selected as study cases, and 425 questionnaires were collected from August to October 2024. The data were analyzed using a structural equation model (SEM) to reveal the impact of built environment perception on overall satisfaction. The results indicate that the field environment has the strongest direct influence on satisfaction. Urban aesthetics impacts satisfaction both directly and indirectly, making its overall effect the most significant. While the location situation does not directly affect satisfaction, it indirectly influences satisfaction through its impact on the field environment and urban aesthetics. Subsequently, based on the satisfaction performance and SEM outcomes, an importance–performance analysis (IPA) was conducted to identify specific areas needing enhancement. Finally, we integrated environmental assessments with the above findings and put forth strategic recommendations to enhance the quality of the built environment.
Clutter in photos is a distraction preventing photographers from conveying the intended emotions or stories to the audience. Photography amateurs frequently include clutter in their photos due to unconscious negligence or the lack of experience in creating a decluttered, aesthetically appealing scene for shooting. We are thus motivated to develop a camera guidance system that provides solutions and guidance for clutter identification and removal. We estimate and visualize the contribution of objects to the overall aesthetics and content of a photo, based on which users can interactively identify clutter. Suggestions on getting rid of clutter, as well as a tool that removes cluttered objects computationally, are provided to guide users to deal with different kinds of clutter and improve their photographic work. Two technical novelties underpin interactions in our system: a clutter distinguishment algorithm with aesthetics evaluations for objects and an iterative image inpainting algorithm based on generative adversarial nets that reconstructs missing regions of removed objects for high-resolution images. User studies demonstrate that our system provides flexible interfaces and accurate algorithms that allow users to better identify distractions and take higher quality images within less time.
This position paper situates AR beauty filters within the broader debate on Body Politics in HCI. We argue that these filters are not neutral tools but technologies of governance that reinforce racialized, gendered, and ableist beauty standards. Through naming conventions, algorithmic bias, and platform governance, they impose aesthetic norms while concealing their influence. To address these challenges, we advocate for transparency-driven interventions and a critical rethinking of algorithmic aesthetics and digital embodiment.
Dan-Cristian Dabija, Cristina-Bianca Pocol, Pompei Mititean
et al.
The need to use innovative packaging (active or intelligent) that extends food shelf-life and promotes sustainable production and consumption systems has become a global priority. In this context, the current research explores the consumer’s buying experience regarding food actively packed with biopolymer films. The research used a questionnaire targeting potential customers for food packed with a protein-based active film. A conceptual model was created to investigate the dependency relations between the following concepts: “superior functional packaging,” “affordable packaging,” “aesthetic packaging,” “nutritional value,” ,”spoilage prevention packaging,” “buying experience for food packed with biopolymer films,” “experiential consumption” and “informative health packaging.” The research demonstrates that affordable pricing, appealing aesthetics, functional attributes and shelf-life extension are significant elements of biopolymer films for active packaging. It validates that these incentives significantly enhance consumer awareness, shaping their experience, preference and proactive search for products packed with such materials in stores. Using biopolymer films for active packaging of foods will have social, environmental and economic benefits, both for producers and consumers.
Abstract This article explores a subgenre of naked-eye virtual reality (VR) video that features two-dimensional paintings in a three-dimensional space and is circulated on the Chinese video streaming website Bilibili. In contrast to traditional VR, which requires the spectator to wear a head-mounted display, naked-eye VR offers a stereoscopic view on the screen, eliminating the need for VR glasses. The apparent incongruity between the screen’s physical flatness and the volumetric depth of the painting becomes even more pronounced when the naked-eye VR image emphasises the painting’s inherent two-dimensionality. Employing an interdisciplinary humanities’ method that connects media archaeology, film studies, art history, and the field of science, technology, and society, this paper delves into this distinctive juxtaposition between the painting’s flatness and the volumetric depth characteristic of naked-eye VR, a subgenre that remains mostly uncharted in the field of film and media studies. Taking a media archaeological perspective, this paper introduces a parallax media history, suggesting that the aesthetics of VR can be traced not only to the stereoscope but also to scroll paintings, which are paradoxically defined by their flat compositions. In addition, naked-eye VR references pictorial traditions by generating a spatial illusion that leads spectators to feel as if they are delving beneath the surface of a painting, transitioning from spatial extensivity on the x-y axis to perceived depth along the z-axis. This oscillation between surface and depth is engendered by the horizontal parallax rooted in binocular disparity, thereby positioning naked-eye VR as a “parallax media.” In analysing the illusion created by naked-eye VR, this paper proposes a paradigmatic shift in the framework of media study from conceiving of an image as a mirror to experiencing it as a door, representing the oscillation between volumetric depth and two-dimensional surface.
History of scholarship and learning. The humanities, Social Sciences
Over 300 million people who live with color vision deficiency (CVD) have a decreased ability to distinguish between colors, limiting their ability to interact with websites and software packages. User interface designers have taken various approaches to tackle the issue with most offering a high contrast mode. The Web Content Accessibility Guidelines (WCAG) outline some best practices for maintaining accessibility that have been adopted and recommended by several governments; however, it is currently uncertain how this impacts perceived user functionality and if this could result in a reduced aesthetic look. In the absence of subjective data, we aim to investigate how a CVD observer might rate the functionality and aesthetics of existing UIs. However, the design of a comparative study of CVD vs. non-CVD populations is inherently hard, therefore we build on the successful field of physiologically-based CVD models, and propose a novel simulation-based experimental protocol, where non-CVD observers rate the relative aesthetics and functionality of screenshots of 20 popular websites as seen in full color vs. with simulated CVD. Our results show that relative aesthetics and functionality correlate positively and that an operating-system-wide high contrast mode can reduce both aesthetics and functionality. While our results are only valid in the context of simulated CVD screenshots, the approach has the benefit of being easily deployable, and can help to spot a number of common pitfalls in production. Finally, we propose a AAA-A classification of the interfaces we analyzed.
While diffusion models show extraordinary talents in text-to-image generation, they may still fail to generate highly aesthetic images. More specifically, there is still a gap between the generated images and the real-world aesthetic images in finer-grained dimensions including color, lighting, composition, etc. In this paper, we propose Cross-Attention Value Mixing Control (VMix) Adapter, a plug-and-play aesthetics adapter, to upgrade the quality of generated images while maintaining generality across visual concepts by (1) disentangling the input text prompt into the content description and aesthetic description by the initialization of aesthetic embedding, and (2) integrating aesthetic conditions into the denoising process through value-mixed cross-attention, with the network connected by zero-initialized linear layers. Our key insight is to enhance the aesthetic presentation of existing diffusion models by designing a superior condition control method, all while preserving the image-text alignment. Through our meticulous design, VMix is flexible enough to be applied to community models for better visual performance without retraining. To validate the effectiveness of our method, we conducted extensive experiments, showing that VMix outperforms other state-of-the-art methods and is compatible with other community modules (e.g., LoRA, ControlNet, and IPAdapter) for image generation. The project page is https://vmix-diffusion.github.io/VMix/.
Trees in works of art have stirred emotions in viewers for millennia. Leonardo da Vinci described geometric proportions in trees to provide both guidelines for painting and insights into tree form and function. Da Vinci's Rule of trees further implies fractal branching with a particular scaling exponent $α= 2$ governing both proportions between the diameters of adjoining boughs and the number of boughs of a given diameter. Contemporary biology increasingly supports an analogous rule with $α= 3$ known as Murray's Law. Here we relate trees in art to a theory of proportion inspired by both da Vinci and modern tree physiology. We measure $α$ in 16th century Islamic architecture, Edo period Japanese painting and 20th century European art, finding $α$ in the range 1.5 to 2.5. We find that both conformity and deviations from ideal branching create stylistic effect and accommodate constraints on design and implementation. Finally, we analyze an abstract tree by Piet Mondrian which forgoes explicit branching but accurately captures the modern scaling exponent $α= 3$, anticipating Murray's Law by 15 years. This perspective extends classical mathematical, biological and artistic ways to understand, recreate and appreciate the beauty of trees.
A large amount of User Generated Content (UGC) is uploaded to the Internet daily and displayed to people world-widely through the client side (e.g., mobile and PC). This requires the cropping algorithms to produce the aesthetic thumbnail within a specific aspect ratio on different devices. However, existing image cropping works mainly focus on landmark or landscape images, which fail to model the relations among the multi-objects with the complex background in UGC. Besides, previous methods merely consider the aesthetics of the cropped images while ignoring the content integrity, which is crucial for UGC cropping. In this paper, we propose a Spatial-Semantic Collaborative cropping network (S2CNet) for arbitrary user generated content accompanied by a new cropping benchmark. Specifically, we first mine the visual genes of the potential objects. Then, the suggested adaptive attention graph recasts this task as a procedure of information association over visual nodes. The underlying spatial and semantic relations are ultimately centralized to the crop candidate through differentiable message passing, which helps our network efficiently to preserve both the aesthetics and the content integrity. Extensive experiments on the proposed UGCrop5K and other public datasets demonstrate the superiority of our approach over state-of-the-art counterparts. Our project is available at https://github.com/suyukun666/S2CNet.
The recent advances of AI technology, particularly in AI-Generated Content (AIGC), have enabled everyone to easily generate beautiful paintings with simple text description. With the stunning quality of AI paintings, it is widely questioned whether there still exists difference between human and AI paintings and whether human artists will be replaced by AI. To answer these questions, we develop a computational framework combining neural latent space and aesthetics features with visual analytics to investigate the difference between human and AI paintings. First, with categorical comparison of human and AI painting collections, we find that AI artworks show distributional difference from human artworks in both latent space and some aesthetic features like strokes and sharpness, while in other aesthetic features like color and composition there is less difference. Second, with individual artist analysis of Picasso, we show human artists' strength in evolving new styles compared to AI. Our findings provide concrete evidence for the existing discrepancies between human and AI paintings and further suggest improvements of AI art with more consideration of aesthetics and human artists' involvement.
Predicting individual aesthetic preferences holds significant practical applications and academic implications for human society. However, existing studies mainly focus on learning and predicting the commonality of facial attractiveness, with little attention given to Personalized Facial Beauty Prediction (PFBP). PFBP aims to develop a machine that can adapt to individual aesthetic preferences with only a few images rated by each user. In this paper, we formulate this task from a meta-learning perspective that each user corresponds to a meta-task. To address such PFBP task, we draw inspiration from the human aesthetic mechanism that visual aesthetics in society follows a Gaussian distribution, which motivates us to disentangle user preferences into a commonality and an individuality part. To this end, we propose a novel MetaFBP framework, in which we devise a universal feature extractor to capture the aesthetic commonality and then optimize to adapt the aesthetic individuality by shifting the decision boundary of the predictor via a meta-learning mechanism. Unlike conventional meta-learning methods that may struggle with slow adaptation or overfitting to tiny support sets, we propose a novel approach that optimizes a high-order predictor for fast adaptation. In order to validate the performance of the proposed method, we build several PFBP benchmarks by using existing facial beauty prediction datasets rated by numerous users. Extensive experiments on these benchmarks demonstrate the effectiveness of the proposed MetaFBP method.
The Frenkel family was famous in Lithuania not only as major manufacturers but also as generous benefactors. They honourably fulfilled the duty of a wealthy Jew to provide charity and social assistance to those most in need. The Frenkel family was forced to leave Lithuania in 1939: during the Soviet and Nazi occupations, the family lost all their possessions. While some family members had Lithuanian citizenship, the property rights of the descendants of Chaim Frenkel (1857–1920) were not reinstated, and from 17 June 1993 the Chaim Frenkel Villa became a department of the Šiauliai “Aušros” Museum (ŠAM, established in 1923). After the building’s renovation (finished in 2008) the villa’s interior spaces reflect minimally survived aesthetics of high class everyday Lithuanian Jewish private life at the beginning of the 20th century. The aim of the article is to argue how the Art Nouveau style in (territory of nowadays) Lithuania was not pure, but intertwined with retro-styles and internationalism. The case of the Ch. Frenkel Villa enriches the history of Lithuanian Art Nouveau with rich combinations of colours, shapes and compositions typical of Lithuanian Jews. Noticeably in the case of the Ch. Frenkel Villa, the traditionalist way of life and the wisdom of Jewish daily life restrained fashionable European design innovations. This is proof that the living environment of Lithuanian Jews was perceived as an important space for spiritual life and the worship of God.
Recent progress in generative models, especially in text-guided diffusion models, has enabled the production of aesthetically-pleasing imagery resembling the works of professional human artists. However, one has to carefully compose the textual description, called the prompt, and augment it with a set of clarifying keywords. Since aesthetics are challenging to evaluate computationally, human feedback is needed to determine the optimal prompt formulation and keyword combination. In this paper, we present a human-in-the-loop approach to learning the most useful combination of prompt keywords using a genetic algorithm. We also show how such an approach can improve the aesthetic appeal of images depicting the same descriptions.
This study reconstructs František Xaver Němeček’s concept of the sublime by examining notes on his lectures at the University of Prague taken by Peter Eduard Bolzano during the 1811–1812 academic year. After demonstrating how Němeček’s concept deviates from Kant’s in the Critique of Judgement, the study goes on to describe the relationship between the two.
In the past decades, many graph drawing techniques have been proposed for generating aesthetically pleasing graph layouts. However, it remains a challenging task since different layout methods tend to highlight different characteristics of the graphs. Recently, studies on deep learning based graph drawing algorithm have emerged but they are often not generalizable to arbitrary graphs without re-training. In this paper, we propose a Convolutional Graph Neural Network based deep learning framework, DeepGD, which can draw arbitrary graphs once trained. It attempts to generate layouts by compromising among multiple pre-specified aesthetics considering a good graph layout usually complies with multiple aesthetics simultaneously. In order to balance the trade-off, we propose two adaptive training strategies which adjust the weight factor of each aesthetic dynamically during training. The quantitative and qualitative assessment of DeepGD demonstrates that it is capable of drawing arbitrary graphs effectively, while being flexible at accommodating different aesthetic criteria.
Color sequences, ordered sets of colors for data visualization, that balance aesthetics with accessibility considerations are presented. In order to model aesthetic preference, data were collected with an online survey, and the results were used to train a machine-learning model. To ensure accessibility, this model was combined with minimum-perceptual-distance constraints, including for simulated color-vision deficiencies, as well as with minimum-lightness-distance constraints for grayscale printing, maximum-lightness constraints for maintaining contrast with a white background, and scores from a color-saliency model for ease of use of the colors in verbal and written descriptions. Optimal color sequences containing six, eight, and ten colors were generated using the data-driven aesthetic-preference model and accessibility constraints. Due to the balance of aesthetics and accessibility considerations, the resulting color sequences can serve as reasonable defaults in data-plotting codes, e.g., for use in scatter plots and line plots.