Hasil untuk "Aesthetics"

R. Dhurat, M. Sukesh

The utility of platelet-rich plasma (PRP) has spanned various fields of dermatology from chronic ulcer management to trichology and aesthetics, due to its role in wound healing. Though PRP is being used over a long time, there is still confusion over proper terminology to define, classify and describe the different variations of platelet concentrates. There is also a wide variation in the reported protocols for standardization and preparation of PRP, in addition to lack of accurate characterization of the tested products in most articles on the topic. Additionally, the high cost of commercially available PRP kits, precludes its use over a larger population. In this article, we review the principles and preparation methods of PRP based on available literature and place our perspective in standardizing a safe, simple protocol that can be followed to obtain an optimal consistent platelet yield.

L. Rosenblatt

J. Losco

D. Berlyne

Matthew K. Hong, Joey Li, Alexandre Filipowicz et al.

Understanding and modeling consumers' stylistic taste such as "sporty" is crucial for creating designs that truly connect with target audiences. However, capturing taste during the design process remains challenging because taste is abstract and subjective, and preference data alone provides limited guidance for concrete design decisions. This paper proposes an integrated human-centered computational framework that links subjective evaluations (e.g., perceived luxury of car wheels) with domain-specific features (e.g., spoke configuration) and computer vision-based measures (e.g., texture). By jointly modeling human-derived (consumer and designer) and machine-extracted features, our framework advances aesthetic assessment by explicitly linking model outcomes to interpretable design features. In particular, it demonstrates how perceptual features, domain-specific design patterns, and consumers' own interpretations of style contribute to aesthetic evaluations. This framework will enable product teams to better understand, communicate, and critique aesthetic decisions, supporting improved anticipation of consumer taste and more informed exploration of design alternatives at design time.

Zhuowen Xie, Yan Wang, Ting-Ting Li et al.

A longstanding challenge in personal thermal management has been transitioning from static, appearance-limited passive radiative cooling (PDRC) materials to systems that are both dynamically adaptive and visually versatile. The central hurdle remains the inherent compromise between color saturation and cooling power. Inspired by organisms such as butterflies, which decouple structural color from thermal function, we present a smart textile that seamlessly merges a dynamic thermochromic layer with static photonic crystals (PCs). This design enables the solar reflectance to be autonomously switched-from approximately 0.6 in the colored state for heating to about 0.9 in the high-reflectance state for cooling. Consequently, outdoor experiments validated substantial temperature regulation: the fabric achieves a surface temperature reduction of 3-4 °C in summer and a heating difference of <1 °C in winter compared to commercial reference materials, all while maintaining high-saturation colors. This dual-mode operation offers a viable pathway for achieving adaptive, aesthetic, and energy-free thermal comfort.

Chen-Ying Chien, Po-Chih Kuo

Understanding how people perceive and evaluate interior spaces is essential for designing environments that promote well-being. However, predicting aesthetic experiences remains difficult due to the subjective nature of perception and the complexity of visual responses. This study introduces a dual-branch CNN-LSTM framework that fuses visual features with eye-tracking signals to predict aesthetic evaluations of residential interiors. We collected a dataset of 224 interior design videos paired with synchronized gaze data from 28 participants who rated 15 aesthetic dimensions. The proposed model attains 72.2% accuracy on objective dimensions (e.g., light) and 66.8% on subjective dimensions (e.g., relaxation), outperforming state-of-the-art video baselines and showing clear gains on subjective evaluation tasks. Notably, models trained with eye-tracking retain comparable performance when deployed with visual input alone. Ablation experiments further reveal that pupil responses contribute most to objective assessments, while the combination of gaze and visual cues enhances subjective evaluations. These findings highlight the value of incorporating eye-tracking as privileged information during training, enabling more practical tools for aesthetic assessment in interior design.

Mengtian Li, Fan Yang, Ruixue Xiong et al.

Jiangnan gardens, a prominent style of Chinese classical gardens, hold great potential as digital assets for film and game production and digital tourism. However, manual modeling of Jiangnan gardens heavily relies on expert experience for layout design and asset creation, making the process time-consuming. To address this gap, we propose GardenDesigner, a novel framework that encodes aesthetic principles for Jiangnan garden construction and integrates a chain of agents based on procedural modeling. The water-centric terrain and explorative pathway rules are applied by terrain distribution and road generation agents. Selection and spatial layout of garden assets follow the aesthetic and cultural constraints. Consequently, we propose asset selection and layout optimization agents to select and arrange objects for each area in the garden. Additionally, we introduce GardenVerse for Jiangnan garden construction, including expert-annotated garden knowledge to enhance the asset arrangement process. To enable interaction and editing, we develop an interactive interface and tools in Unity, in which non-expert users can construct Jiangnan gardens via text input within one minute. Experiments and human evaluations demonstrate that GardenDesigner can generate diverse and aesthetically pleasing Jiangnan gardens. Project page is available at https://monad-cube.github.io/GardenDesigner.

Jiachen Yang, Xianhui Lin, Yi Dong et al.

Face retouching requires removing subtle imperfections while preserving unique facial identity features, in order to enhance overall aesthetic appeal. However, existing methods suffer from a fundamental trade-off. Supervised learning on labeled data is constrained to pixel-level label mimicry, failing to capture complex subjective human aesthetic preferences. Conversely, while online reinforcement learning (RL) excels at preference alignment, its stochastic exploration paradigm conflicts with the high-fidelity demands of face retouching and often introduces noticeable noise artifacts due to accumulated stochastic drift. To address these limitations, we propose BeautyGRPO, a reinforcement learning framework that aligns face retouching with human aesthetic preferences. We construct FRPref-10K, a fine-grained preference dataset covering five key retouching dimensions, and train a specialized reward model capable of evaluating subtle perceptual differences. To reconcile exploration and fidelity, we introduce Dynamic Path Guidance (DPG). DPG stabilizes the stochastic sampling trajectory by dynamically computing an anchor-based ODE path and replanning a guided trajectory at each sampling timestep, effectively correcting stochastic drift while maintaining controlled exploration. Extensive experiments show that BeautyGRPO outperforms both specialized face retouching methods and general image editing models, achieving superior texture quality, more accurate blemish removal, and overall results that better align with human aesthetic preferences.

G. Hegel, T. M. Knox

Rugaved R. Gudadhe, Gaurav R. Sawarkar, Amol M. Deshpande

Hair plays a significant role in personality and aesthetics, with androgenetic alopecia affecting up to 80% of males. This case study evaluates the efficacy of palliative treatment and Viddhakarma (Puncture Therapy in Ayurveda) in managing androgenetic alopecia (Khalitya). A 37-year-old man presented with hair loss and a mild burning sensation on the scalp for six to seven years, primarily in the vertex and frontal regions. Treatment included Viddhakarma, Nilibhringadi Taila application (Shiroabhyanga), and palliative medications for four months, with weekly monitoring. New hair roots appeared within two weeks, existing hair improved in quality, and warmth sensation normalized after a month. Significant regrowth was observed without adverse effects, highlighting the effectiveness of personalized Ayurvedic management for androgenetic alopecia.

Fatemeh Behrad, Tinne Tuytelaars, Johan Wagemans

The capacity of Vision transformers (ViTs) to handle variable-sized inputs is often constrained by computational complexity and batch processing limitations. Consequently, ViTs are typically trained on small, fixed-size images obtained through downscaling or cropping. While reducing computational burden, these methods result in significant information loss, negatively affecting tasks like image aesthetic assessment. We introduce Charm, a novel tokenization approach that preserves Composition, High-resolution, Aspect Ratio, and Multi-scale information simultaneously. Charm prioritizes high-resolution details in specific regions while downscaling others, enabling shorter fixed-size input sequences for ViTs while incorporating essential information. Charm is designed to be compatible with pre-trained ViTs and their learned positional embeddings. By providing multiscale input and introducing variety to input tokens, Charm improves ViT performance and generalizability for image aesthetic assessment. We avoid cropping or changing the aspect ratio to further preserve information. Extensive experiments demonstrate significant performance improvements on various image aesthetic and quality assessment datasets (up to 8.1 %) using a lightweight ViT backbone. Code and pre-trained models are available at https://github.com/FBehrad/Charm.

Shuo Cao, Jiayang Li, Xiaohui Li et al.

Multimodal large language models (MLLMs) have achieved remarkable progress in visual understanding tasks such as visual grounding, segmentation, and captioning. However, their ability to perceive perceptual-level image features remains limited. In this work, we present UniPercept-Bench, a unified framework for perceptual-level image understanding across three key domains: Aesthetics, Quality, Structure and Texture. We establish a hierarchical definition system and construct large-scale datasets to evaluate perceptual-level image understanding. Based on this foundation, we develop a strong baseline UniPercept trained via Domain-Adaptive Pre-Training and Task-Aligned RL, enabling robust generalization across both Visual Rating (VR) and Visual Question Answering (VQA) tasks. UniPercept outperforms existing MLLMs on perceptual-level image understanding and can serve as a plug-and-play reward model for text-to-image generation. This work defines Perceptual-Level Image Understanding in the era of MLLMs and, through the introduction of a comprehensive benchmark together with a strong baseline, provides a solid foundation for advancing perceptual-level multimodal image understanding.

Dinuo Liao, James Derek Lomas, Cehao Yu

This study explores how Low-Rank Adaptation (LoRA) fine-tuning, guided by human aesthetic evaluations, can enhance the outputs of generative AI models in tangible product design, using lamp design as a case study. By integrating human feedback into the AI model, we aim to improve both the desirability and aesthetic appeal of the generated designs. Comprehensive experiments were conducted, starting with prompt optimization techniques and focusing on LoRA fine-tuning of the Stable Diffusion model. Additionally, methods to convert AI-generated designs into tangible products through 3D realization using 3D printing technologies were investigated. The results indicate that LoRA fine-tuning effectively aligns AI-generated designs with human aesthetic preferences, leading to significant improvements in desirability and aesthetic appeal scores. These findings highlight the potential of human-AI collaboration in tangible product design and provide valuable insights into integrating human feedback into AI design processes.

SiXiang Chen, Jianyu Lai, Jialin Gao et al.

Generating aesthetic posters is more challenging than simple design images: it requires not only precise text rendering but also the seamless integration of abstract artistic content, striking layouts, and overall stylistic harmony. To address this, we propose PosterCraft, a unified framework that abandons prior modular pipelines and rigid, predefined layouts, allowing the model to freely explore coherent, visually compelling compositions. PosterCraft employs a carefully designed, cascaded workflow to optimize the generation of high-aesthetic posters: (i) large-scale text-rendering optimization on our newly introduced Text-Render-2M dataset; (ii) region-aware supervised fine-tuning on HQ-Poster100K; (iii) aesthetic-text-reinforcement learning via best-of-n preference optimization; and (iv) joint vision-language feedback refinement. Each stage is supported by a fully automated data-construction pipeline tailored to its specific needs, enabling robust training without complex architectural modifications. Evaluated on multiple experiments, PosterCraft significantly outperforms open-source baselines in rendering accuracy, layout coherence, and overall visual appeal-approaching the quality of SOTA commercial systems. Our code, models, and datasets can be found in the Project page: https://ephemeral182.github.io/PosterCraft

Zhiyuan Hu, Zheng Sun, Yi Wei et al.

The performance of image generation has been significantly improved in recent years. However, the study of image screening is rare and its performance with Multimodal Large Language Models (MLLMs) is unsatisfactory due to the lack of data and the weak image aesthetic reasoning ability in MLLMs. In this work, we propose a complete solution to address these problems in terms of data and methodology. For data, we collect a comprehensive image screening dataset with over 128k samples, about 640k images. Each sample consists of an original image, four generated images. The dataset evaluates the image aesthetic reasoning ability under four aspects: appearance deformation, physical shadow, placement layout, and extension rationality. Regarding data annotation, we investigate multiple approaches, including purely manual, fully automated, and answer-driven annotations, to acquire high-quality chains of thought (CoT) data in the most cost-effective manner. Methodologically, we introduce a Hard Cases Mining (HCM) strategy with a Dynamic Proportional Accuracy (DPA) reward into the Group Relative Policy Optimization (GRPO) framework, called HCM-GRPO. This enhanced method demonstrates superior image aesthetic reasoning capabilities compared to the original GRPO. Our experimental results reveal that even state-of-the-art closed-source MLLMs, such as GPT4o and Qwen-VL-Max, exhibit performance akin to random guessing in image aesthetic reasoning. In contrast, by leveraging the HCM-GRPO, we are able to surpass the scores of both large-scale open-source and leading closed-source models with a much smaller model.

Ricardo Alonzo Fernández Salguero

Why have left-wing movements historically integrated participatory art forms (such as murals and protest songs) into their praxis, while right-wing movements have prioritized strategic communication and, more recently, the digital culture of memes? This article introduces the concept of aesthetic asymmetry to explain this divergence in political action. We argue that the asymmetry is not coincidental but the result of four interconnected structural factors: the organizational ecosystem, the moral and emotional framework, the material supports, and the historical tradition of each political spectrum. While the left tends to use art in a constitutive manner to forge community, solidarity, and hope, the contemporary right tends to use it instrumentally to mobilize polarizing affects such as humor and resentment. Drawing on comparative literature from the Theatre of the Oppressed to analyses of alt-right meme wars, we nuance this distinction and show how the aesthetic logic of each pole aligns with its strategic objectives. The article culminates in a prescriptive model for artistic action, synthesizing keys to effective mobilization into emotional, narrative, and formatting strategies. Understanding this asymmetry is crucial for analyzing political communication and for designing cultural interventions capable of generating profound social change.

Ni Made Emmi Nutrisia Dewi, Ni Komang Prasiani, Ni Komang Desita Rahayu

In the era of globalization, the integration of local cultural elements into modern architecture is becoming increasingly important to maintain cultural identity. Bali, with its rich culture and architectural traditions, offers a variety of elements that can be adapted to enhance the aesthetics and functionality of modern buildings, including bank offices. The main focus of this study is to analyze how Balinese organizational values ??and cultural heritage are reflected in the physical design of bank offices, including layout, building materials, and architectural ornaments to enhance customer interaction and service creativity. The research methods used include a qualitative approach, case studies of bank offices in Bali, field observations, and interviews with architects, bank employees, and customers. The results show that cultural integration in the architectural design of bank offices can strengthen corporate identity, enhance customer experience and interaction, and encourage service innovation. In conclusion, this study emphasizes the importance of considering cultural aspects and organizational values ??in architectural design as an effective way to create an environment that supports service innovation and enriches customer experience and also contributes to cultural preservation. These findings confirm that architecture that reflects organizational culture and local traditions can be an innovative strategy to improve the image and competitiveness of banks in the era of globalization. Keywords: representation, architecture, culture, Bali, organization, office, bank, service, public

Paul Bowie, Karen Spalding, Jennifer Medves et al.

Introduction Healthcare is a highly complex adaptive system, requiring a systems approach to understand its behaviour better. We adapt the Systems Thinking for Everyday Work (STEW) cue cards, initially introduced as a systems approach tool in the UK, in a US healthcare system as part of a study investigating the feasibility of a systems thinking approach for front-line workers.Methods The original STEW cards were adapted using consensus-building methods with front-line staff and safety leaders.Results Each card was examined for relevance, applicability, language and aesthetics (colour, style, visual cues and size). Two sets of cards were created due to the recognition that systems thinking was relatively new in healthcare and that the successful use of the principles on the cards would need initial facilitation to ensure their effective application. Six principles were agreed on and are presented in the cards: Your System outlines the need to agree that problems belong to a system and that the system must be defined. Viewpoints ensure that multiple voices are heard within the discussion. Work Condition highlights the resources, constraints and barriers that exist in the system and contribute to the system’s functions. Interactions ask participants to understand how parts of the system interact to perform the work. Performance guides users to understand how work can be performed daily. Finally, Understanding seeks to promote a just cultural environment of appreciating that people do what makes sense to them. The two final sets of cards were scored using a content validity survey, with a final score of 1.Conclusions The cards provide an easy-to-use guide to help users understand the system being studied, learn from problems encountered and understand the everyday work involved in providing excellent care. The cards offer a practical ‘systems approach’ for use within complex healthcare systems.

Richard Shiff

Within the fields of aesthetics and psychology, there is a long tradition of arguing that affect precedes cognition. A verbalized thought following upon a feeling and associated with it does not translate the feeling precisely or adequately. In fact, as C. S. Peirce would argue, the thought itself projects its own affect, which is independent of its logic. The essence of affect or feeling will always elude linguistic capture. This essay argues that experiences of belief and doubt are affective sensations, and both can be graphed on a scale of sensuous intuition or cognitive guessing (which, again, projects affect). The failure of language to grasp what we refer to as instances of emotion, feeling, sensation, affect, belief, doubt, and the like is more of an intractable problem for philosophical aesthetics than it is for the aesthetics of the art experience. Examples of the art of Cy Twombly, Barnett Newman, Donald Judd, Bridget Riley, and Katharina Grosse are invoked to argue through the gap between thought and feeling.