https://arxiv.org/api/59iFC5+5PvvnixpOJM3ltIgoSok 2026-09-17T15:10:03Z 25 25 0 http://arxiv.org/abs/2609.02512v1 2026-09-02T12:16:22Z

Beauty assessments from Multimodal Large Language Models (MLLMs) are increasingly popular amongst users, companies, and aestheticians. This raises the question of whether these AI models can accurately reflect human judgments of attractiveness. In a pre- registered exploratory study, we compared the attractiveness ratings of 2,513 human participants to four widely used commercial AI models: Claude, Gemini, GPT, and Grok. Results showed that MLLMs systematically rate faces more favourably and within a narrower range than humans and, at the time of study, do not reproduce human ratings in absolute terms. However, MLLMs exhibit strong correlations with human attractiveness judgments, accurately tracking the rank-ordering of faces. MLLMs may judge faces by different cues than humans; only face age was a predictor of facial attractiveness in both humans and MLLMs, with inconsistent patterns across models for ethnicity and gender. AI models strongly agree with one another, except for Grok, which also showed the lowest agreement with humans. Our findings suggest that while they may be able to approximate rank-orderings of human attractiveness, current off-the-shelf commercial MLLMs systematically overrate the beauty of human faces.

2026-09-02T12:16:22Z Santiago Grandas Juan Sebastian Cely-Acosta Mohit Mendiratta Shafee Hassan Macken Murphy http://arxiv.org/abs/2608.24219v1 2026-08-25T08:24:46Z

Facial attractiveness has been linked to statistical regularities such as symmetry and averageness, suggesting that beauty may depend on the ease with which a face is perceived. We empirically test this hypothesis by training variational autoencoders on four face datasets without attractiveness supervision and evaluating their representations on the 597 faces from the Chicago Face Database. Across models, human attractiveness ratings closely aligns with the direction defined by the VAE evidence lower bound (ELBO) in rate-distortion space. Independently learned latent spaces contain an attractiveness direction that transfers strongly across random initializations and training data. We also find that attractive faces are more prototypical in both shape and latent space. Our results connect classic accounts of aesthetics with learned generative models and provide empirical support for a variational interpretation of the processing fluency theory of aesthetic pleasure.

2026-08-25T08:24:46Z 24 pages, 11 figures, 1 table Francisco M. López Jochen Triesch http://arxiv.org/abs/2601.11651v2 2026-02-02T15:50:47Z

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

2026-01-15T15:23:38Z 22 pages, 15 figures; v2 - fix typo Miriam Doh Aditya Gulati Corinna Canali Nuria Oliver http://arxiv.org/abs/2509.01431v1 2025-09-01T12:42:04Z

The computational assessment of facial attractiveness, a challenging subjective regression task, is dominated by architectures with a critical trade-off: Convolutional Neural Networks (CNNs) offer efficiency but have limited receptive fields, while Vision Transformers (ViTs) model global context at a quadratic computational cost. To address this, we propose Mamba-CNN, a novel and efficient hybrid architecture. Mamba-CNN integrates a lightweight, Mamba-inspired State Space Model (SSM) gating mechanism into a hierarchical convolutional backbone. This core innovation allows the network to dynamically modulate feature maps and selectively emphasize salient facial features and their long-range spatial relationships, mirroring human holistic perception while maintaining computational efficiency. We conducted extensive experiments on the widely-used SCUT-FBP5500 benchmark, where our model sets a new state-of-the-art. Mamba-CNN achieves a Pearson Correlation (PC) of 0.9187, a Mean Absolute Error (MAE) of 0.2022, and a Root Mean Square Error (RMSE) of 0.2610. Our findings validate the synergistic potential of combining CNNs with selective SSMs and present a powerful new architectural paradigm for nuanced visual understanding tasks.

2025-09-01T12:42:04Z Djamel Eddine Boukhari http://arxiv.org/abs/2506.11025v1 2025-05-20T10:21:51Z

This paper examines how synthetically generated faces and machine learning-based gender classification algorithms are affected by algorithmic lookism, the preferential treatment based on appearance. In experiments with 13,200 synthetically generated faces, we find that: (1) text-to-image (T2I) systems tend to associate facial attractiveness to unrelated positive traits like intelligence and trustworthiness; and (2) gender classification models exhibit higher error rates on "less-attractive" faces, especially among non-White women. These result raise fairness concerns regarding digital identity systems.

2025-05-20T10:21:51Z Accepted as an extended abstract at the Fourth European Workshop on Algorithmic Fairness (EWAF) (URL: https://2025.ewaf.org/home) Proceedings of Machine Learning Research 294 (2025) 474-480 Miriam Doh Aditya Gulati Matei Mancas Nuria Oliver http://arxiv.org/abs/2503.14402v1 2025-03-18T16:42:02Z

Facial Aesthetics Enhancement (FAE) aims to improve facial attractiveness by adjusting the structure and appearance of a facial image while preserving its identity as much as possible. Most existing methods adopted deep feature-based or score-based guidance for generation models to conduct FAE. Although these methods achieved promising results, they potentially produced excessively beautified results with lower identity consistency or insufficiently improved facial attractiveness. To enhance facial aesthetics with less loss of identity, we propose the Nearest Neighbor Structure Guidance based on Diffusion (NNSG-Diffusion), a diffusion-based FAE method that beautifies a 2D facial image with 3D structure guidance. Specifically, we propose to extract FAE guidance from a nearest neighbor reference face. To allow for less change of facial structures in the FAE process, a 3D face model is recovered by referring to both the matched 2D reference face and the 2D input face, so that the depth and contour guidance can be extracted from the 3D face model. Then the depth and contour clues can provide effective guidance to Stable Diffusion with ControlNet for FAE. Extensive experiments demonstrate that our method is superior to previous relevant methods in enhancing facial aesthetics while preserving facial identity.

2025-03-18T16:42:02Z Lisha Li Jingwen Hou Weide Liu Yuming Fang Jiebin Yan http://arxiv.org/abs/2501.02509v2 2025-03-13T02:34:18Z

Facial attractiveness prediction (FAP) has long been an important computer vision task, which could be widely applied in live streaming for facial retouching, content recommendation, etc. However, previous FAP datasets are either small, closed-source, or lack diversity. Moreover, the corresponding FAP models exhibit limited generalization and adaptation ability. To overcome these limitations, in this paper we present LiveBeauty, the first large-scale live-specific FAP dataset, in a more challenging application scenario, i.e., live streaming. 10,000 face images are collected from a live streaming platform directly, with 200,000 corresponding attractiveness annotations obtained from a well-devised subjective experiment, making LiveBeauty the largest open-access FAP dataset in the challenging live scenario. Furthermore, a multi-modal FAP method is proposed to measure the facial attractiveness in live streaming. Specifically, we first extract holistic facial prior knowledge and multi-modal aesthetic semantic features via a Personalized Attractiveness Prior Module (PAPM) and a Multi-modal Attractiveness Encoder Module (MAEM), respectively, then integrate the extracted features through a Cross-Modal Fusion Module (CMFM). Extensive experiments conducted on both LiveBeauty and other open-source FAP datasets demonstrate that our proposed method achieves state-of-the-art performance. Dataset will be available soon.

2025-01-05T11:43:35Z Section 3 in Images Collection has description errors about data cleaning. The compared methods data of Table 3 lacks other metrics Hui Li Xiaoyu Ren Hongjiu Yu Huiyu Duan Kai Li Ying Chen Libo Wang Xiongkuo Min Guangtao Zhai Xu Liu http://arxiv.org/abs/2409.15443v1 2024-09-23T18:10:19Z

Previous studies have shown that faces are rated as more attractive when they are partially occluded. The cause of this observation remains unclear. One explanation is a mental reconstruction of the occluded face parts which is biased towards a more attractive percept as shown in face-attractiveness rating tasks. We aimed to test for this hypothesis by using a delayed matching-to-sample task, which directly requires mental reconstruction. In two online experiments, we presented observers with unattractive, neutral or attractive synthetic reconstructions of the occluded face parts using a state-of-the-art diffusion-based image generator. Our experiments do not support the initial hypothesis and reveal an unattractiveness bias for occluded faces instead. This suggests that facial attractiveness rating tasks do not prompt reconstructions. Rather, the attractivity bias may arise from global image features, and faces may actually be reconstructed with unattractive properties when mental reconstruction is applied.

2024-09-23T18:10:19Z This paper and a corresponding poster were presented at the Cognitive Computational Neuroscience conference in 2024 Frederik Riedmann Bernhard Egger Tim Rohe http://arxiv.org/abs/2311.13929v1 2023-11-23T11:30:02Z

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.

2023-11-23T11:30:02Z Accepted by ACM MM 2023. Source code: https://github.com/MetaVisionLab/MetaFBP Luojun Lin Zhifeng Shen Jia-Li Yin Qipeng Liu Yuanlong Yu Weijie Chen 10.1145/3581783.3612319 http://arxiv.org/abs/2212.01742v2 2024-04-24T05:30:46Z

Facial attractiveness prediction (FAP) aims to assess facial attractiveness automatically based on human aesthetic perception. Previous methods using deep convolutional neural networks have improved the performance, but their large-scale models have led to a deficiency in flexibility. In addition, most methods fail to take full advantage of the dataset. In this paper, we present a novel end-to-end FAP approach that integrates dual label distribution and lightweight design. The manual ratings, attractiveness score, and standard deviation are aggregated explicitly to construct a dual-label distribution to make the best use of the dataset, including the attractiveness distribution and the rating distribution. Such distributions, as well as the attractiveness score, are optimized under a joint learning framework based on the label distribution learning (LDL) paradigm. The data processing is simplified to a minimum for a lightweight design, and MobileNetV2 is selected as our backbone. Extensive experiments are conducted on two benchmark datasets, where our approach achieves promising results and succeeds in balancing performance and efficiency. Ablation studies demonstrate that our delicately designed learning modules are indispensable and correlated. Additionally, the visualization indicates that our approach can perceive facial attractiveness and capture attractive facial regions to facilitate semantic predictions. The code is available at https://github.com/enquan/2D_FAP.

2022-12-04T04:19:36Z Shu Liu Enquan Huang Ziyu Zhou Yan Xu Xiaoyan Kui Tao Lei Hongying Meng http://arxiv.org/abs/2111.05149v1 2021-11-09T13:53:32Z

Facial beauty prediction (FBP) aims to develop a machine that automatically makes facial attractiveness assessment. In the past those results were highly correlated with human ratings, therefore also with their bias in annotating. As artificial intelligence can have racist and discriminatory tendencies, the cause of skews in the data must be identified. Development of training data and AI algorithms that are robust against biased information is a new challenge for scientists. As aesthetic judgement usually is biased, we want to take it one step further and propose an Unbiased Convolutional Neural Network for FBP. While it is possible to create network models that can rate attractiveness of faces on a high level, from an ethical point of view, it is equally important to make sure the model is unbiased. In this work, we introduce AestheticNet, a state-of-the-art attractiveness prediction network, which significantly outperforms competitors with a Pearson Correlation of 0.9601. Additionally, we propose a new approach for generating a bias-free CNN to improve fairness in machine learning.

2021-11-09T13:53:32Z Peer reviewed and accepted at CEPE/IACAP 2021 as Extended Abstract Michael Danner Thomas Weber Leping Peng Tobias Gerlach Xueping Su Matthias Rätsch http://arxiv.org/abs/2010.10721v1 2020-10-21T02:27:31Z

Loss function is crucial for model training and feature representation learning, conventional models usually regard facial attractiveness recognition task as a regression problem, and adopt MSE loss or Huber variant loss as supervision to train a deep convolutional neural network (CNN) to predict facial attractiveness score. Little work has been done to systematically compare the performance of diverse loss functions. In this paper, we firstly systematically analyze model performance under diverse loss functions. Then a novel loss function named ComboLoss is proposed to guide the SEResNeXt50 network. The proposed method achieves state-of-the-art performance on SCUT-FBP, HotOrNot and SCUT-FBP5500 datasets with an improvement of 1.13%, 2.1% and 0.57% compared with prior arts, respectively. Code and models are available at https://github.com/lucasxlu/ComboLoss.git.

2020-10-21T02:27:31Z Tech Report Lu Xu Jinhai Xiang http://arxiv.org/abs/2006.02766v1 2020-06-04T10:46:07Z

We propose a generative framework based on generative adversarial network (GAN) to enhance facial attractiveness while preserving facial identity and high-fidelity. Given a portrait image as input, having applied gradient descent to recover a latent vector that this generative framework can use to synthesize an image resemble to the input image, beauty semantic editing manipulation on the corresponding recovered latent vector based on InterFaceGAN enables this framework to achieve facial image beautification. This paper compared our system with Beholder-GAN and our proposed result-enhanced version of Beholder-GAN. It turns out that our framework obtained state-of-art attractiveness enhancement results. The code is available at https://github.com/zoezhou1999/BeautifyBasedOnGAN.

2020-06-04T10:46:07Z Yuhongze Zhou Qinjie Xiao http://arxiv.org/abs/2005.08168v2 2020-06-06T00:58:07Z

Facial attractiveness enhancement has been an interesting application in Computer Vision and Graphics over these years. It aims to generate a more attractive face via manipulations on image and geometry structure while preserving face identity. In this paper, we propose the first Generative Adversarial Networks (GANs) for enhancing facial attractiveness in both geometry and appearance aspects, which we call "FA-GANs". FA-GANs contain two branches and enhance facial attractiveness in two perspectives: facial geometry and facial appearance. Each branch consists of individual GANs with the appearance branch adjusting the facial image and the geometry branch adjusting the facial landmarks in appearance and geometry aspects, respectively. Unlike the traditional facial manipulations learning from paired faces, which are infeasible to collect before and after enhancement of the same individual, we achieve this by learning the features of attractiveness faces through unsupervised adversarial learning. The proposed FA-GANs are able to extract attractiveness features and impose them on the enhancement results. To better enhance faces, both the geometry and appearance networks are considered to refine the facial attractiveness by adjusting the geometry layout of faces and the appearance of faces independently. To the best of our knowledge, we are the first to enhance the facial attractiveness with GANs in both geometry and appearance aspects. The experimental results suggest that our FA-GANs can generate compelling perceptual results in both geometry structure and facial appearance and outperform current state-of-the-art methods.

2020-05-17T05:02:39Z 10 pages, 8 figures Jingwu He Chuan Wang Yang Zhang Jie Guo Yanwen Guo http://arxiv.org/abs/1910.14072v3 2020-06-06T13:58:18Z

The perception of facial beauty is a complex phenomenon depending on many, detailed and global facial features influencing each other. In the machine learning community this problem is typically tackled as a problem of supervised inference. However, it has been conjectured that this approach does not capture the complexity of the phenomenon. A recent original experiment (Ibáñez-Berganza et al., Scientific Reports 9, 8364, 2019) allowed different human subjects to navigate the face-space and ``sculpt'' their preferred modification of a reference facial portrait. Here we present an unsupervised inference study of the set of sculpted facial vectors in that experiment. We first infer minimal, interpretable, and faithful probabilistic models (through Maximum Entropy and artificial neural networks) of the preferred facial variations, that capture the origin of the observed inter-subject diversity in the sculpted faces. The application of such generative models to the supervised classification of the gender of the sculpting subjects, reveals an astonishingly high prediction accuracy. This result suggests that much relevant information regarding the subjects may influence (and be elicited from) her/his facial preference criteria, in agreement with the multiple motive theory of attractiveness proposed in previous works.

2019-10-30T18:23:56Z main article (10 pages, 4 figures) + supplementary information (22 pages, 10 figures). minor typos corrected. Federico Maggiore added as author Miguel Ibáñez-Berganza Ambra Amico Gian Luca Lancia Federico Maggiore Bernardo Monechi Vittorio Loreto http://arxiv.org/abs/1903.07526v2 2019-06-11T12:42:42Z

The origin and meaning of facial beauty represent a longstanding puzzle. Despite the profuse literature devoted to facial attractiveness, its very nature, its determinants and the nature of inter-person differences remain controversial issues. Here we tackle such questions proposing a novel experimental approach in which human subjects, instead of rating natural faces, are allowed to efficiently explore the face-space and 'sculpt' their favorite variation of a reference facial image. The results reveal that different subjects prefer distinguishable regions of the face-space, highlighting the essential subjectivity of the phenomenon.The different sculpted facial vectors exhibit strong correlations among pairs of facial distances, characterising the underlying universality and complexity of the cognitive processes, and the relative relevance and robustness of the different facial distances.

2019-03-18T16:08:16Z 15 pages, 5 figures. Supplementary information: 26 pages, 13 figures Scientific Reports 9, Article number: 8364 (2019) Miguel Ibáñez-Berganza Ambra Amico Vittorio Loreto 10.1038/s41598-019-44655-9 http://arxiv.org/abs/1803.04347v1 2018-03-12T16:14:24Z

A method to produce personalized classification models to automatically review online dating profiles on Tinder is proposed, based on the user's historical preference. The method takes advantage of a FaceNet facial classification model to extract features which may be related to facial attractiveness. The embeddings from a FaceNet model were used as the features to describe an individual's face. A user reviewed 8,545 online dating profiles. For each reviewed online dating profile, a feature set was constructed from the profile images which contained just one face. Two approaches are presented to go from the set of features for each face, to a set of profile features. A simple logistic regression trained on the embeddings from just 20 profiles could obtain a 65% validation accuracy. A point of diminishing marginal returns was identified to occur around 80 profiles, at which the model accuracy of 73% would only improve marginally after reviewing a significant number of additional profiles.

2018-03-12T16:14:24Z 6 pages, 7 figures Charles F Jekel Raphael T. Haftka http://arxiv.org/abs/1801.06345v1 2018-01-19T09:53:19Z

Facial beauty prediction (FBP) is a significant visual recognition problem to make assessment of facial attractiveness that is consistent to human perception. To tackle this problem, various data-driven models, especially state-of-the-art deep learning techniques, were introduced, and benchmark dataset become one of the essential elements to achieve FBP. Previous works have formulated the recognition of facial beauty as a specific supervised learning problem of classification, regression or ranking, which indicates that FBP is intrinsically a computation problem with multiple paradigms. However, most of FBP benchmark datasets were built under specific computation constrains, which limits the performance and flexibility of the computational model trained on the dataset. In this paper, we argue that FBP is a multi-paradigm computation problem, and propose a new diverse benchmark dataset, called SCUT-FBP5500, to achieve multi-paradigm facial beauty prediction. The SCUT-FBP5500 dataset has totally 5500 frontal faces with diverse properties (male/female, Asian/Caucasian, ages) and diverse labels (face landmarks, beauty scores within [1,~5], beauty score distribution), which allows different computational models with different FBP paradigms, such as appearance-based/shape-based facial beauty classification/regression model for male/female of Asian/Caucasian. We evaluated the SCUT-FBP5500 dataset for FBP using different combinations of feature and predictor, and various deep learning methods. The results indicates the improvement of FBP and the potential applications based on the SCUT-FBP5500.

2018-01-19T09:53:19Z 6 pages, 14 figures, conference paper Lingyu Liang Luojun Lin Lianwen Jin Duorui Xie Mengru Li http://arxiv.org/abs/1711.08801v1 2017-11-23T18:36:27Z

This paper follows the recent history of automated beauty competitions to discuss how machine learning techniques, in particular neural networks, alter the way attractiveness is handled and how this impacts the cultural landscape. We describe experiments performed to probe the behavior of two different convolutional neural network architectures in the classification of facial attractiveness in a large database of celebrity faces. As opposed to other easily definable facial features, attractiveness is difficult to detect robustly even for the best classification systems. Based on the observations from these experiments, we discuss several approaches to detect factors that come into play when a machine evaluates human features, and how bias can occur not only in data selection but in network architectures; in multiple forms on multiple levels throughout the process. The overall goal is to map out with mixed methods a novel condition: slippages produced by platform level machine learning systems that make judgements in domains considered dependent on high level human intelligence.

2017-11-23T18:36:27Z 23 pages, 14 figures, 50 references Marc Böhlen Varun Chandola Amol Salunkhe http://arxiv.org/abs/1709.03654v2 2017-11-22T13:04:41Z

Makeup is widely used to improve facial attractiveness and is well accepted by the public. However, different makeup styles will result in significant facial appearance changes. It remains a challenging problem to match makeup and non-makeup face images. This paper proposes a learning from generation approach for makeup-invariant face verification by introducing a bi-level adversarial network (BLAN). To alleviate the negative effects from makeup, we first generate non-makeup images from makeup ones, and then use the synthesized non-makeup images for further verification. Two adversarial networks in BLAN are integrated in an end-to-end deep network, with the one on pixel level for reconstructing appealing facial images and the other on feature level for preserving identity information. These two networks jointly reduce the sensing gap between makeup and non-makeup images. Moreover, we make the generator well constrained by incorporating multiple perceptual losses. Experimental results on three benchmark makeup face datasets demonstrate that our method achieves state-of-the-art verification accuracy across makeup status and can produce photo-realistic non-makeup face images.

2017-09-12T02:08:40Z The paper is accepted by AAAI-18 Yi Li Lingxiao Song Xiang Wu Ran He Tieniu Tan http://arxiv.org/abs/1705.04282v1 2017-05-05T05:47:15Z

Humans make complex inferences on faces, ranging from objective properties (gender, ethnicity, expression, age, identity, etc) to subjective judgments (facial attractiveness, trustworthiness, sociability, friendliness, etc). While the objective aspects of face perception have been extensively studied, relatively fewer computational models have been developed for the social impressions of faces. Bridging this gap, we develop a method to predict human impressions of faces in 40 subjective social dimensions, using deep representations from state-of-the-art neural networks. We find that model performance grows as the human consensus on a face trait increases, and that model predictions outperform human groups in correlation with human averages. This illustrates the learnability of subjective social perception of faces, especially when there is high human consensus. Our system can be used to decide which photographs from a personal collection will make the best impression. The results are significant for the field of social robotics, demonstrating that robots can learn the subjective judgments defining the underlying fabric of human interaction.

2017-05-05T05:47:15Z 10 pages Amanda Song Linjie Li Chad Atalla Garrison Cottrell http://arxiv.org/abs/1609.00496v2 2016-09-07T09:06:31Z

Two challenges lie in the facial attractiveness computation research: the lack of true attractiveness labels (scores), and the lack of an accurate face representation. In order to address the first challenge, this paper recasts facial attractiveness computation as a label distribution learning (LDL) problem rather than a traditional single-label supervised learning task. In this way, the negative influence of the label incomplete problem can be reduced. Inspired by the recent promising work in face recognition using deep neural networks to learn effective features, the second challenge is expected to be solved from a deep learning point of view. A very deep residual network is utilized to enable automatic learning of hierarchical aesthetics representation. Integrating these two ideas, an end-to-end deep learning framework is established. Our approach achieves the best results on a standard benchmark SCUT-FBP dataset compared with other state-of-the-art work.

2016-09-02T08:08:39Z 3 pages, 3 figures. The first two authors are parallel first author Shu Liu Bo Li Yangyu Fan Zhe Guo Ashok Samal http://arxiv.org/abs/1511.02465v1 2015-11-08T09:59:04Z

This paper proposes a deep leaning method to address the challenging facial attractiveness prediction problem. The method constructs a convolutional neural network of facial beauty prediction using a new deep cascaded fine-turning scheme with various face inputting channels, such as the original RGB face image, the detail layer image, and the lighting layer image. With a carefully designed CNN model of deep structure, large input size and small convolutional kernels, we have achieved a high prediction correlation of 0.88. This result convinces us that the problem of facial attractiveness prediction can be solved by deep learning approach, and it also shows the important roles of the facial smoothness, lightness, and color information that were involved in facial beauty perception, which is consistent with the result of recent psychology studies. Furthermore, we analyze the high-level features learnt by CNN through visualization of its hidden layers, and some interesting phenomena were observed. It is found that the contours and appearance of facial features, especially eyes and moth, are the most significant facial attributes for facial attractiveness prediction, which is also consistent with the visual perception intuition of human.

2015-11-08T09:59:04Z 5 pages, 3 figures, 5 tables Jie Xu Lianwen Jin Lingyu Liang Ziyong Feng Duorui Xie http://arxiv.org/abs/1511.02459v1 2015-11-08T09:21:32Z

In this paper, a novel face dataset with attractiveness ratings, namely, the SCUT-FBP dataset, is developed for automatic facial beauty perception. This dataset provides a benchmark to evaluate the performance of different methods for facial attractiveness prediction, including the state-of-the-art deep learning method. The SCUT-FBP dataset contains face portraits of 500 Asian female subjects with attractiveness ratings, all of which have been verified in terms of rating distribution, standard deviation, consistency, and self-consistency. Benchmark evaluations for facial attractiveness prediction were performed with different combinations of facial geometrical features and texture features using classical statistical learning methods and the deep learning method. The best Pearson correlation (0.8187) was achieved by the CNN model. Thus, the results of our experiments indicate that the SCUT-FBP dataset provides a reliable benchmark for facial beauty perception.

2015-11-08T09:21:32Z 6 pages, 8 figures, 6 tables Duorui Xie Lingyu Liang Lianwen Jin Jie Xu Mengru Li http://arxiv.org/abs/1408.2380v1 2014-08-11T11:48:46Z

Editing faces in videos is a popular yet challenging aspect of computer vision and graphics, which encompasses several applications including facial attractiveness enhancement, makeup transfer, face replacement, and expression manipulation. Simply applying image-based warping algorithms to video-based face editing produces temporal incoherence in the synthesized videos because it is impossible to consistently localize facial features in two frames representing two different faces in two different videos (or even two consecutive frames representing the same face in one video). Therefore, high performance face editing usually requires significant manual manipulation. In this paper we propose a novel temporal-spatial-smooth warping (TSSW) algorithm to effectively exploit the temporal information in two consecutive frames, as well as the spatial smoothness within each frame. TSSW precisely estimates two control lattices in the horizontal and vertical directions respectively from the corresponding control lattices in the previous frame, by minimizing a novel energy function that unifies a data-driven term, a smoothness term, and feature point constraints. Corresponding warping surfaces then precisely map source frames to the target frames. Experimental testing on facial attractiveness enhancement, makeup transfer, face replacement, and expression manipulation demonstrates that the proposed approaches can effectively preserve spatial smoothness and temporal coherence in editing facial geometry, skin detail, identity, and expression, which outperform the existing face editing methods. In particular, TSSW is robust to subtly inaccurate localization of feature points and is a vast improvement over image-based warping methods.

2014-08-11T11:48:46Z Xiaoyan Li Dacheng Tao