Hasil untuk "Aesthetics"

G. Böhme

Yan Wang, Partho Hassan, Samiha Sadeka et al.

We introduce Lunara Aesthetic II, a publicly released, ethically sourced image dataset designed to support controlled evaluation and learning of contextual consistency in modern image generation and editing systems. The dataset comprises 2,854 anchor-linked variation pairs derived from original art and photographs created by Moonworks. Each variation pair applies contextual transformations, such as illumination, weather, viewpoint, scene composition, color tone, or mood; while preserving a stable underlying identity. Lunara Aesthetic II operationalizes identity-preserving contextual variation as a supervision signal while also retaining Lunara's signature high aesthetic scores. Results show high identity stability, strong target attribute realization, and a robust aesthetic profile that exceeds large-scale web datasets. Released under the Apache 2.0 license, Lunara Aesthetic II is intended for benchmarking, fine-tuning, and analysis of contextual generalization, identity preservation, and edit robustness in image generation and image-to-image systems with interpretable, relational supervision. The dataset is publicly available at: https://huggingface.co/datasets/moonworks/lunara-aesthetic-image-variations.

Katsuhiko Yamamoto, Koichi Miyazaki, Shogo Seki

We propose an audio aesthetics score (AES) prediction system by CyberAgent (AESCA) for AudioMOS Challenge 2025 (AMC25) Track 2. The AESCA comprises a Kolmogorov--Arnold Network (KAN)-based audiobox aesthetics and a predictor from the metric scores using the VERSA toolkit. In the KAN-based predictor, we replaced each multi-layer perceptron layer in the baseline model with a group-rational KAN and trained the model with labeled and pseudo-labeled audio samples. The VERSA-based predictor was designed as a regression model using extreme gradient boosting, incorporating outputs from existing metrics. Both the KAN- and VERSA-based models predicted the AES, including the four evaluation axes. The final AES values were calculated using an ensemble model that combined four KAN-based models and a VERSA-based model. Our proposed T12 system yielded the best correlations among the submitted systems, in three axes at the utterance level, two axes at the system level, and the overall average. We also released the inference model of the proposed KAN-based predictor (KAN #1-#4).

Ke Zhang, Tianyu Ding, Jiachen Jiang et al.

Image cropping is crucial for enhancing the visual appeal and narrative impact of photographs, yet existing rule-based and data-driven approaches often lack diversity or require annotated training data. We introduce ProCrop, a retrieval-based method that leverages professional photography to guide cropping decisions. By fusing features from professional photographs with those of the query image, ProCrop learns from professional compositions, significantly boosting performance. Additionally, we present a large-scale dataset of 242K weakly-annotated images, generated by out-painting professional images and iteratively refining diverse crop proposals. This composition-aware dataset generation offers diverse high-quality crop proposals guided by aesthetic principles and becomes the largest publicly available dataset for image cropping. Extensive experiments show that ProCrop significantly outperforms existing methods in both supervised and weakly-supervised settings. Notably, when trained on the new dataset, our ProCrop surpasses previous weakly-supervised methods and even matches fully supervised approaches. Both the code and dataset will be made publicly available to advance research in image aesthetics and composition analysis.

Jingxu Wu, Yuwei Yin

This paper explores the ontological and epistemological foundations of Lev Landau's theoretical physics through the lens of his unpublished philosophical notes and scientific practice. We identify a unique form of geometric reductionism where physical laws emerge as inevitable consequences of symmetry breaking in progressively constrained phase spaces. Landau's dismissal of quantum interpretation debates and his famous "axiomatic minimalism" in the Course of Theoretical Physics are shown to stem from a deep epistemological commitment to dimensional aesthetics - the belief that fundamental truths must manifest through dimensional economy in mathematical representations.

Marcus Lin, Jennifer Lai

A healthy smile plays a significant role in functional as well as esthetic considerations, improving confidence. It is difficult for dental professionals to strike a balance between esthetic requirements and functional requirements. Traditional smile design has had heavy reliance on dentist expertise and used plaster models and hand drawings, raising questions about the outcome for patients. Digital technology, led by Dr. Christian Coachman in 2007, allows photographic and videographic assessments, enabling improved intercommunication among specialists and patients. Advances in artificial intelligence (AI) and big data have supported analysis of facial features and development of personalized smile designs in the last few years. Outputs are, however, susceptible to practitioner bias or limitations of training data, and may be suboptimal for individual users. The study presented here suggests a comprehensive system integrating AI, big data, and recognition technologies to automate the smile design process so that both experienced and inexperienced dentists can generate pleasing aesthetics with ease. The system has a Facial Feature Extraction Module and an Image Generation Module, serving diverse practitioner and patient needs. User data can be incorporated in future research for design optimization and testing of virtual and augmented reality for real-time previewing. Data gathered can also be employed in aesthetic preference analyses, which can enhance our knowledge of smile design in dental practice.

Pavlo Zaitsev, Liudmyla Lytvyniuk

The aim of the article is to define tendencies in the transformation of expressive and stylistic means in the Japanese landscape photography of the specified period, based on the analysis of archives of the Japanese landscape photography of the 1900s–1920s. Results. A stylistic transformation of the landscape genre, as well as a passing from the documentary fixation to expressive artistic solutions during the 1900s, are revealed on the example of Kurokawa Suizan’s works. A stylistic stabilisation of the landscape genre which started acquiring moderate expressiveness in the 1910s is grounded. Implementing small-format cameras in the 1910s is analysed using the example of Makoto Yoshino’s creativity, which has contributed to the compositional means’ expansion. The onset of stylistic shifts in the landscape genre during the 1920s under the influence of Constructivist tendencies is revealed on the example of Okubo Koroku’s practice. Scientific novelty. For the first time in the Ukrainian art history, an analysis of the transformation of expressive and stylistic means in the Japanese landscape photography of the 1900s–1920s is conducted. The European pictorialism assimilation and its synthesis with traditional Japanese painting is traced in the aspect of Kurokawa Suizan’s creativity in the 1900s. Materials concerning the influence of Constructivism on the landscape photography development in the 1920s are applied in the scientific circulation. Conclusions. The transformation of expressive and stylistic means in the Japanese landscape photography during the 1900s–1920s highlights a complex interplay between traditional aesthetics, European artistic influences and technical innovations. The 1900s were marked by the adaptation of the European pictorialist principles and their synthesis with the aesthetic basis of monochrome suiboku-ga painting, which led to the formation of a specific arsenal of expressive means. In the second half of the 1920s, under the influence of the Constructivist movement, active experiments with the compositional organisation of the frame and figurative expression means are observed. So, over the course of the 1900s–1920s, the Japanese landscape photography evolved from documentary fixing into an autonomous artistic direction that synthesised Western and national traditions, gradually securing its place in the Japanese cultural discourse.

LI Yunlang, LI Chaoyuan

Dental implantation has revolutionized the traditional prosthetic approach to tooth loss and is regarded as the optimal solution for replacing missing teeth and restoring oral function and aesthetics. With the swift development of artificial intelligence (AI) technology and its profound integration with oral implantology, a growing number of studies have begun to explore the application of AI in the field of oral implantology, covering multiple aspects such as auxiliary diagnosis, treatment planning and surgical robotics. This review systematically introduces the multi-dimensional progress of AI in the digital and intelligent transformation of oral implantology in recent years and provides an outlook on its potential and research value.

Parindita Sarmah, Sagar Gaurkar, Prasad Deshmukh

Ear deformities, both congenital and acquired, can significantly impact aesthetics, hearing function and psychological well-being. The present case series presents a diverse range of auricular anomalies, discussing their clinical presentation, underlying causes and management strategies. Congenital deformities include microtia, characterised by underdeveloped external ear structures that may be associated with conductive hearing loss, as well as prominent ears, which can lead to self-esteem issues. Additionally, ear tags, which are small benign appendages of skin and cartilage and cupped ear deformity, where the helix and antihelix are malformed, are highlighted, emphasising the role of early intervention in improving cosmetic and functional outcomes. Acquired ear deformities arise due to trauma, chronic inflammation, or improper healing. This series discusses cases of ear keloids, which form due to excessive scar tissue following ear piercings or surgeries, requiring multimodal treatment that includes corticosteroid injections, surgical excision and pressure therapy. Cauliflower ear, which results from repeated trauma leading to haematoma formation and fibrosis, is examined in the context of preventive measures and surgical correction. Burn-related ear deformities, which lead to severe tissue loss and contracture formation, present reconstructive challenges that necessitate skin grafts or cartilage framework reconstruction. Early diagnosis and timely management, facilitated by a multidisciplinary approach involving plastic surgeons, dermatologists and otolaryngologists, are crucial for optimising patient outcomes. The present case series underscores the importance of addressing both functional impairments and aesthetic concerns to enhance the overall quality of life for patients.

N. Tractinsky

Xuehao Cui, Guangyang Wu, Zhenghao Gan et al.

Existing methods to generate aesthetic QR codes, such as image and style transfer techniques, tend to compromise either the visual appeal or the scannability of QR codes when they incorporate human face identity. Addressing these imperfections, we present Face2QR-a novel pipeline specifically designed for generating personalized QR codes that harmoniously blend aesthetics, face identity, and scannability. Our pipeline introduces three innovative components. First, the ID-refined QR integration (IDQR) seamlessly intertwines the background styling with face ID, utilizing a unified Stable Diffusion (SD)-based framework with control networks. Second, the ID-aware QR ReShuffle (IDRS) effectively rectifies the conflicts between face IDs and QR patterns, rearranging QR modules to maintain the integrity of facial features without compromising scannability. Lastly, the ID-preserved Scannability Enhancement (IDSE) markedly boosts scanning robustness through latent code optimization, striking a delicate balance between face ID, aesthetic quality and QR functionality. In comprehensive experiments, Face2QR demonstrates remarkable performance, outperforming existing approaches, particularly in preserving facial recognition features within custom QR code designs. Codes are available at $\href{https://github.com/cavosamir/Face2QR}{\text{this URL link}}$.

Hantao Zhou, Longxiang Tang, Rui Yang et al.

Image Quality Assessment (IQA) and Image Aesthetic Assessment (IAA) aim to simulate human subjective perception of image visual quality and aesthetic appeal. Despite distinct learning objectives, they have underlying interconnectedness due to consistent human assessment perception. In this paper, we propose Unified vision-language pre-training of Quality and Aesthetics (UniQA}), to extract useful and common representations from two tasks, thereby benefiting them simultaneously. However, the lack of text in the IQA datasets and the textual noise in the IAA datasets pose severe challenges for multimodal pre-training. To address this, we (1) utilize multimodal large language models (MLLMs) to generate high-quality text descriptions; (2) use the generated text for IAA as metadata to purify noisy IAA data. To effectively adapt the pre-trained UniQA to downstream tasks, we further propose a lightweight adapter that utilizes versatile cues to fully exploit the extensive knowledge of the pre-trained model. UniQA demonstrates high competitiveness in various image assessment tasks, including classical IQA and IAA tasks, few-label IQA, and other downstream tasks, showing promise as a foundational assessment model. Codes are available at https://github.com/zht8506/UniQA.

Yuti Liu, Shice Liu, Junyuan Gao et al.

Image Aesthetic Assessment (IAA) is a vital and intricate task that entails analyzing and assessing an image's aesthetic values, and identifying its highlights and areas for improvement. Traditional methods of IAA often concentrate on a single aesthetic task and suffer from inadequate labeled datasets, thus impairing in-depth aesthetic comprehension. Despite efforts to overcome this challenge through the application of Multi-modal Large Language Models (MLLMs), such models remain underdeveloped for IAA purposes. To address this, we propose a comprehensive aesthetic MLLM capable of nuanced aesthetic insight. Central to our approach is an innovative multi-scale text-guided self-supervised learning technique. This technique features a multi-scale feature alignment module and capitalizes on a wealth of unlabeled data in a self-supervised manner to structurally and functionally enhance aesthetic ability. The empirical evidence indicates that accompanied with extensive instruct-tuning, our model sets new state-of-the-art benchmarks across multiple tasks, including aesthetic scoring, aesthetic commenting, and personalized image aesthetic assessment. Remarkably, it also demonstrates zero-shot learning capabilities in the emerging task of aesthetic suggesting. Furthermore, for personalized image aesthetic assessment, we harness the potential of in-context learning and showcase its inherent advantages.

Laura J. Martin

This position paper distinguishes restoration from rewilding and argues for the establishment of a slow restoration movement. Repair takes time. Restoration is an active and ongoing process that unites insights and methods from ecology and landscape architecture and design. Slow restoration acknowledges that repair is a never-ending process, one in which people care for other beings and attempt to undo the harms caused by centuries of colonialism, consumption, and death.

Elena Kurant

The aim of this paper it to discuss the techniques employed in modern political Russian verbatim drama, as well as in their performances. Modern verbatim drama seeks to stay relevant and up-to-date by referring to taboos, radical social controversies, and political incidents. So, it becomes an important event of not only cultural but also social life, and it exerts a strong impact on modern Russian society. The aesthetics of the modern verbatim drama is aimed at representing the reality which is absent from official discourse. Such texts as One hour eighteen minutes by Elena Gremina, Three quarters of sadness (Bolotnaya square case) by Polina Borodina, The last party by Anna Dobrovolskaya, and New Antigone by Elena Kostyuchenko openly explore the issues which do not function as part of the public discourse. Thus, they capture the traumatic experiences in order to overcome traumas. These texts take the traumatic events of current political and public life out of the marginal area, and they acquire the status of social statements which give hope for political and social changes, and give rise to unofficial discourse allowing the readers as well as the viewers to define their own opinion related to the traumatizing events.

Galyna M. Syvachenko. Shevchenko , Antonina V. Anistratenko

The article considers the second edition of Volodymyr Vynnychenko’s novel “The New Commandment” (1947), written for the first time in 1932. The author of the book translated it into French together with his wife after the end of World War II. The purpose of the work and the tasks dictated by it are to analyse the “French” novel “The New Commandment” by Volodymyr Vynnychenko in the paradigm of modernist aesthetics, to reveal the main philosophical ideas and aesthetic functions of the novel, to identify elements of intertextual memory, and to understand the influence of the book by Ukrainian dissident Viktor Kravchenko “I Chose Freedom” (1946). The set of goals determines the need to use hermeneutical (analysis of artistic text), comparative-typological (comparison of philosophical novel various functions), historical-literary (solution of a number of literary problems in the context of various national literatures) research methods. Vynnychenko’s work is analysed in the paradigm of the “Transcendent Homelessness” philosophical concept, introduced into scientific discourse by the Hungarian philosopher and literary theorist D. Lukach in his Hegelian-Weber essay “The Theory of the Novel” (1916), where he quotes the German romantic, a representative of the Jena school, Novalis: “Philosophy is homesickness – the desire to be at home everywhere”. In the study of Volodymyr Vynnychenko’s contribution to European modernism in the interwar era, the author pays attention to the key thesis of the trans-cultural theory, which touches such disciplines as anthropology, sociology and political science. Particular attention is paid to the genesis and specificity of the philosophical and figurative system of one of the key “French” texts by Volodymyr Vynnychenko. The leading aesthetic components and means of forming philosophical and ideologicalpolitical paradigms of the work are also determined. The French aristocracy had a great debate on “The New Commandment”. In April 1949, the translation was published in one of the Paris publishing houses (Nouveau Commandemant. Paris: Editions des Presses du Temps Present). The French literary critics of the time responded favourably to the publication of the Ukrainian author’s book, and the literary and artistic society “Club de Faubourg” already on 10th May 1949, arranged a massive discussion of “The New Commandment”, which testified to the approving attitude towards the author. At the same time, another well-known French artist club “Arts-Sciences-Lettres”, awarded Volodymyr Vynnychenko with an honorary diploma and a silver medal. On 21st July 1949, the prestigious Parisian weekly bulletin “Le Nuvelle Litterere” responded to this fact where noticed that after Shevchenko and Marko Vovchok, Volodymyr Vynnychenko is the first Ukrainian writer whose novels have been responded to by French audience. In this regard, it is noted that the philosophical foundations of Vynnychenko’s novel organically fit into the “spiritual crisis” European discussions of those times. We have studied philosophical character manifestation peculiarities in the genre of novel-dialogue, novel-polemic, which are widely represented in the “French” prose of the Ukrainian artist and are closely connected with the French literary tradition. It is proved that, having spent almost the last thirty years of his life in France, the Ukrainian writer seems to aim at identifying common thematic, aesthetic, philosophical and ideological paradigms that go beyond mononational boundaries, and demonstrates that Ukrainian emigrant artists were participants in pan-European literary modernism, although for the most part it concerns Volodymyr Vynnychenko himself, as well as Yu. Kosach, I. Kostetskyi, A. Arkhipenko, A. Ekster, A. Manevich, I. Pune, A. Boguslavskaya, M. Glushchenko. Particular attention is paid to the genre experiment of Vynnychenko, in particular, the philosophical and political novel with such poetic features as the presentation and discussion of concordist theory, the use of such a modernist technique as “a novel within a novel”, the constant inclusion of various discursive forms of concordism discussion. The critical optics of the study combines the historical and philosophical specificity of the era of the interwar twenties, on which the novels of Volodymyr Vynnychenko are based, as well as the national identity of the Ukrainian writer and his biographical individuality.

K. Ball, A. Bauman, E. Leslie et al.

B. Schenkman, Fredrik U. Jönsson

Noam Tractinsky, Denis Klimov

We propose and evaluate an authentication scheme that improves usability and user experience issues in the authentication process due to its reliance on people's aesthetic tastes and preferences. The scheme uses aesthetic images to verify the identity of computer users. It relies on three major premises regarding visual aesthetics: (i) that an individual has different preferences for different aesthetic stimuli; (ii) that these preferences are relatively consistent; and (iii) that aesthetic tastes are subjective and, therefore, there are considerable individual differences in aesthetic preferences. Following a review of the scientific basis for these premises, we describe the concept of the aesthetic evaluation-based authentication (AEbA) method and illustrate an implementation of it. We address AEbA's advantages and disadvantages relative to other related methods and conclude that it is adequate for low-to-medium security domains. It cannot serve as a compulsory method because we suspect that a certain portion of the user population lacks the degree of aesthetic sensitivity required to use the system effectively. On the plus side, the method offers a positive experience. It alleviates the burden of memorizing passwords to a minimum, and relative to other usability-oriented schemes provides better security in terms of shoulder-surfing, phishing, and password space. Finally, we report on a pilot evaluation of the concept and its feasibility that supports the method's main tenets, provides insights about implementation challenges and suggestions for improvements.

Yufei Tian, Nanyun Peng

Poetry generation, and creative language generation in general, usually suffers from the lack of large training data. In this paper, we present a novel framework to generate sonnets that does not require training on poems. We design a hierarchical framework which plans the poem sketch before decoding. Specifically, a content planning module is trained on non-poetic texts to obtain discourse-level coherence; then a rhyme module generates rhyme words and a polishing module introduces imagery and similes for aesthetics purposes. Finally, we design a constrained decoding algorithm to impose the meter-and-rhyme constraint of the generated sonnets. Automatic and human evaluation show that our multi-stage approach without training on poem corpora generates more coherent, poetic, and creative sonnets than several strong baselines.