Image Aesthetic Assessment: An experimental survey
Open accessThe DOI matches its Crossref record; 100 of the 100 references it cites were found in a registry or an index.
Abstract
This article reviews recent computer vision techniques used in the assessment of image aesthetic quality. Image aesthetic assessment aims at computationally distinguishing high-quality from low-quality photos based on photographic rules, typically in the form of binary classification or quality scoring. A variety of approaches has been proposed in the literature to try to solve this challenging problem. In this article, we summarize these approaches based on visual feature types (hand-crafted features and deep features) and evaluation criteria (data set characteristics and evaluation metrics). The main contributions and novelties of the reviewed approaches are highlighted and discussed. In addition, following the emergence of deep-learning techniques, we systematically evaluate recent deep-learning settings that are useful for developing a robust deep model for aesthetic scoring.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“In theory, however, LMX can be generically applied to most EAs, e.g.multi-objective EAs [23,29], evolutionary strategies [1,5], or in support of open-ended evolution [121], but simply swapping it in as the genetic variation operator.”
From Language Model Crossover: Variation through Few-Shot Prompting (2024) · cites this paper as [29]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 2×
“It is worth pointing out that other more recent and deeper models such as ResNet [63] or Inception-ResNet [64] could serve as a pre-trained model.”
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 6×
“19, we observe that the convolutional response of the vanilla VGG-16 (ImageNet) for object recognition typically finds a precise focus of the salient object in view, while the 1-column CNN baseline (DAN-1-original for aesthetic quality classification) outputs an “aestheticallyoriented” salient region where both the ob…”
InfluentialImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Image quality assessment: from error visibility to structural similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.819861 · Cited by 57,892 · cited 2×
“ence PSNR / SSIM / VIF High-quality Image 7.69 / -0.13 / 0.04 Low-quality Image 8.50 / 0.12 / 0.03 Fig. 2. Quality measurement by Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM) [31] and Visual Information Fidelity (VIF) [32] (higher is better, typically measured against a referencing groundtruth…”
BackgroundMethodInfluentialImage Super-Resolution Using Deep Convolutional Networks
Dong, C., Loy, C. C., He, K., & Tang, X. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2439281 · Cited by 10,105 · cited 1×
“e Quality Metrics Image quality metrics are defined in an attempt to quantitatively measure the objective quality of an image. This is typically used in image restoration applications (superresolution [34], de-blur [35] and de-artifacts [36]) where we have a default high-quality reference image for comparison. However,…”
BackgroundSelf-citationHow transferable are features in deep neural networks?
Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014) · arXiv · doi:10.48550/arxiv.1411.1792 · Cited by 6,061 · cited 1×
“, freezing some earlier layers to prevent overfitting [65].”
BackgroundDimensionality Reduction by Learning an Invariant Mapping
Hadsell, R., Chopra, S., & LeCun, Y. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.100 · Cited by 5,336 · cited 1×
“Pretraining using triplets: The triplet loss is inspired by Dimensionality Reduction by Learning an Invariant Mapping (DrLIM) [68] and Large Margin Nearest Neighbor (LMNN) [69].”
MethodVisual categorization with bags of keypoints
Csurka, G. (2004) · European Conference on Computer Vision · Cited by 4,953
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.11231 · Cited by 4,636 · cited 2×
“It is worth pointing out that other more recent and deeper models such as ResNet [63] or Inception-ResNet [64] could serve as a pre-trained model.”
Research works printed but not linked: 15
- [33] Y. LeCun, B. Boser, J. Denker, D. Henderson, R. Howard, W. Hubbard, and L. Jackel, 'Handwritten digit recognition with a backpropagation network,' in Advacnes in Neural Information Processing Systems (NIPS) , 1989. -
- [32] H. R. Sheikh and A. C. Bovik, 'A visual information fidelity approach to video quality assessment,' in The First International Workshop on Video Processing and Quality Metrics for Consumer Electronics . Citeseer, 2005, pp. 23-25. -
- [59] Y. Kao, R. He, and K. Huang, 'Visual aesthetic quality assessment with multi-task deep learning,' arXiv preprint arXiv:1604.04970 , 2016. - · arXiv
- wang, 2016, Brain-inspired deep networks for image aesthetics assessment
- [3] J. S. Barbara London, John Upton, Photography . Pearson, 2005. -
- [5] G. T. Fechner, Vorschule der aesthetik . Breitkopf & H¨ artel, 1876, vol. 1. -
- [48] L. Marchesotti, F. Perronnin, and F. Meylan, 'Learning beautiful (and ugly) attributes.' in British Machine Vision Conference (BMVC) , vol. 7, 2013, pp. 1-11. -
- [77] C.-Y. Lee, S. Xie, P. Gallagher, Z. Zhang, and Z. Tu, 'Deeplysupervised nets.' in International Conference on Artificial Intelligence and Statistics , 2015. -
- [81] A. Krizhevsky, I. Sutskever, and G. E. Hinton, 'Imagenet classification with deep convolutional neural networks,' in Advances in Neural Information Processing Systems (NIPS) , 2012, pp. 1097-1105. -
- [2] I. J, Design and Form: The Basic Course at the Bauhaus and Later . Wiley, Chichester, 1975. -
- [1] M. Freeman, 'The complete guide to light and lighting,' 2007. -
- [104] M. Nishiyama, T. Okabe, Y. Sato, and I. Sato, 'Sensation-based photo cropping,' in Proceedings of the ACM International Conference on Multimedia , 2009, pp. 669-672. -
- [16] S. Zeki and J. Nash, Inner vision: An exploration of art and the brain . Oxford university press Oxford, 1999, vol. 415. -
- [84] L. v. d. Maaten and G. Hinton, 'Visualizing data using t-SNE,' Journal of Machine Learning Research , vol. 9, no. Nov, pp. 25792605, 2008. -
- [18] T. Ang, Digital photographer's handbook . Dorling Kindersley Publishing, Incorporated, 2002. -
Cited by
Items 201–300 of 306
Ranking-based scores for the assessment of aesthetic quality in photography
Rubio, F., Flores, M. J., & Puerta, J. M. (2022) · Signal Processing Image Communication · doi:10.1016/j.image.2022.116803 · Cited by 4
Self-Supervised Image Aesthetic Assessment Inspired by Aesthetic Domain Knowledge
Li, Q. (2022) · International Conference on Computer and Communication Systems (ICCCS) · doi:10.1109/icccs55155.2022.9846053 · Cited by 2
Learning 3D Shape Aesthetics Globally and Locally
Chen, M., & Lau, M. (2022) · Computer Graphics Forum · doi:10.1111/cgf.14702 · Cited by 2
“There have been previous works [DLT17, RSL ∗ 17, ZZL ∗ 21] that explore the automatic assessment of image aesthetics with deep learning and datasets with thousands of annotated images.”
BackgroundResultPersonalized Image Aesthetics Assessment Based on Theme and Personality
Dai, J., Jiang, M., Liu, F., & Huang, R. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-5489-2_20 · Cited by 2
Image Cropping with Content and Composition Attribute-aware Global Relation Reasoning
Zhu, H., Yan, L., Zhou, Y. Z., Yao, R., Shao, Z., Zhao, J., & Li, L. (2025) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3719012 · Cited by 2
“Therefore, the hand-crafted rules are hard to accurately and comprehensively reveal the aesthetic information in images [7].”
BackFlip: The Impact of Local and Global Data Augmentations on Artistic Image Aesthetic Assessment
Strafforello, O., Odriozola, G. M., Behrad, F., Chen, L.-W., Maerten, A.-S., Soydaner, D., & Wagemans, J. P. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91572-7_6 · Cited by 3
Generating an Album with the Best Media Using Computer Vision
Souza, T., Lima, J. P., Teichrieb, V., Nascimento, C., da Silva, F. Q. B., Santos, A. L. M., & Pinho, H. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-91803-7_25 · Cited by 2
M2FN: Multi-step modality fusion for advertisement image assessment
Park, K.-W., Ha, J.-W., Lee, J., Kwon, S., Kim, K.-M., & Zhang, B. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2021.107116 · Cited by 2
Using multi-task residual network to evaluate image aesthetic quality
Tian, X. (2021) · IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) · doi:10.1109/iaeac50856.2021.9391005 · Cited by 2
“Yubin[5] summarized these methods based on visual feature types (manual features and depth features) and evaluation criteria (data set features and evaluation indicators).”
MethodShape Analysis Approach Towards Assessment of Cleft Lip Repair Outcome
Bakaki, P., Richard, B. M., Pereira, E., Tagalakis, A. D., Ness, A., & Liu, Y. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-89128-2_16 · Cited by 2
Assessing Aesthetics of Generated Abstract Images Using Correlation Structure
Khajehabdollahi, S., Martius, G., & Levina, A. (2019) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci44817.2019.9002779 · Cited by 3
“of photographs and images were studied in the contexts of automatic image selection [22], [23], [24], or evolutionary generation of aesthetic images [25].”
BackgroundBhandari, P., Jaiswal, M., Puranik, V., Kirtane, S., & Pukale, D. D. (2020) · International Conference on Electronics and Sustainable Communication Systems (ICESC) · doi:10.1109/icesc48915.2020.9156003 · Cited by 2
Assessing Aesthetics of Generated Abstract Images Using Correlation Structure
Khajehabdollahi, S., Martius, G., & Levina, A. (2019) · MPG.PuRe (Max Planck Society) · Cited by 2
Multitask Regularization for Image Aesthetic Evaluation
Florea, C., & Florea, L. (2021) · International Conference on Electronics, Computers and Artificial Intelligence (ECAI) · doi:10.1109/ecai52376.2021.9515089 · Cited by 2
Aesthetic Features for Personalized Photo RecommendationPreprint
Zhou, Y. Q., Wu, G., Sanner, S., & Manggala, P. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.00060 · Cited by 2
“Many existing works in the literature on image aesthetic assessment are based on Photo.Net [2] or datasets from the DPChallenge, like AVA [3].”
BackgroundPark, K.-W., Lee, J., Kwon, S., Ha, J.-W., Kim, K.-M., & Zhang, B. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.02358 · Cited by 3
“Linguistic auxiliary attributes are transformed into embedding vector by BERT (Devlin et al. 2018), and the rest are given with one-hot encoding vectors.”
MethodInfluentialDocument Layout Analysis with Aesthetic-Guided Image AugmentationPreprint
Ma, T., Wu, X., Li, X., Du, X., Zhao, Z., Xue, L., & Jin, C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.13809 · Cited by 2
“In this paper, we propose a method based on layer modeling, which is built upon the Aesthetic-Guided [18] and copy-paste [19].”
MethodLearning from the Tangram to Solve Mini Visual Tasks
Zhao, Y., Qiu, L., Lu, P., Shi, F., Han, T., & Zhu, S. C. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i3.20260 · Cited by 4
“Image quality is influenced by numerous factors such as color (Nishiyama et al. 2011), lighting (Free-man 2007), texture (Ke, Tang, and Jing 2006), and image composition (Deng, Loy, and Tang 2017).”
BackgroundIllumination-Aware Image Quality Assessment for Enhanced Low-Light Image
Yao, S., Zhu, Y., Liang, L., & Wang, T. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-88010-1_19 · Cited by 1
Bianconi, F., Buratti, C., & Pascoletti, G. (2024) · Lecture notes in mechanical engineering · doi:10.1007/978-3-031-58094-9_45 · Cited by 1
Enhancing the Aesthetics of 3D Shapes via Reference-based Editing
Chen, M., & Lau, M. (2024) · ACM Transactions on Graphics · doi:10.1145/3687954 · Cited by 2
“There has also been work in the establishment of quantifiable aesthetics metrics [Datta et al. 2006; Deng et al. 2017; Nishiyama et al. 2011; Yang et al. 2022; Zhu et al. 2021].”
Multi-Task Learning of Visual Attributes for Image Aesthetics Assessment
Yu, T., & Liu, J. (2024) · IEEE International Conference on Tools with Artificial Intelligence (ICTAI) · doi:10.1109/ictai62512.2024.00058 · Cited by 1
“To predict binary aesthetic labels, researchers have traditionally used machine learning approaches like support vector machines and neural networks [8].”
Exploring the interpretability of Vision GCN with a multi-method approach
Zhao, H., Sui, Y., & Wu, L. J. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127624 · Cited by 3
Progressively Generated Text-Assisted Image Aesthetic Quality Assessment
Zhu, H., Shi, J., Shao, Z., Yao, R., Sun, K., & Li, L. (2025) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2025.3566145 · Cited by 1
“Therefore, image aesthetic quality assessment (IAQA), also known as image aesthetic assessment (IAA) [5], [6], which can simulate users’ aesthetic perceptions to evaluate the quality of images is a challenging task [7], [8].”
Analyzing the Impact of Visual and Listing Features in Real Estate Listings
Bayrak, S. N., Alptekin, G. I., Orman, G. K., & Arslan, A. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-97576-9_18 · Cited by 1
Enhancing Visual Aesthetics in Stable Diffusion: A Reinforcement Learning Approach
You, J., Lin, Y. P., & Hu, B. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11342753 · Cited by 1
“Image aesthetic assessment (IAA) aims to computationally gauge the aesthetic quality of images [9]-[16].”
ArtEEGAttention: an advanced deep learning approach for art brain decoding
Hu, S., Zhang, S., Zhang, Y., Wang, Z., Guo, B., & Yu, Z. (2026) · Frontiers of Computer Science · doi:10.1007/s11704-025-50344-w · Cited by 1
“In the field of visual aesthetic assessment, Image Aesthetic Assessment (IAA) [3,4] using deep learning models has automated the evaluation of image aesthetics, significantly accelerating human decision-making processes and enhancing the accuracy of evaluation outcomes [5–8].”
PoB: Toward Reasoning Patterns of Beauty in Image Data
Nguyen, D. T. N., Nakayama, H., Okazaki, N., & Sakaeda, T. (2018) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3240508.3240711 · Cited by 1
A Survey of Blur Detection and Sharpness Assessment Methods
Andrade, J. (2021) · Synthesis lectures on algorithms and software in engineering · doi:10.2200/s01065ed1v01y202012ase020 · Cited by 2
Image Aesthetics Assessment with Gradient Shake Regularization
Florea, C., & Florea, L. (2021) · International Conference on Electronics, Computers and Artificial Intelligence (ECAI) · doi:10.1109/ecai52376.2021.9515109 · Cited by 1
Augmenting Image Aesthetic Assessment with Diverse Deep Features
Lin, R. (2021) · Artificial Intelligence and Cloud Computing Conference (AICCC) · doi:10.1145/3508259.3508264 · Cited by 2
Selective video enhancement in the Laguerre–Gauss domain
Brizzi, M., Battisti, F., Carli, M., & Neri, A. (2022) · Signal Processing Image Communication · doi:10.1016/j.image.2022.116876 · Cited by 1
A Retrieval System for Images and Videos based on Aesthetic Assessment of Visuals
Nieto, D. V., Kalloori, S., Zünd, F., Fernandez-Labrador, C., Willhaus, M., Klingler, S., & Groß, M. H. (2023) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3539618.3591817 · Cited by 2
“Aesthetic assessment models of images can be classified into two types: classification methods [29, 33] and regression methods [13, 19, 23, 30, 31, 44].”
BackgroundMethodImage Layer Modeling for Complex Document Layout Generation
Ma, T., Wu, X., Du, X., Wang, Y., & Jin, C. (2023) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme55011.2023.00386 · Cited by 1
“Therefore, we design a data generation method based on the image layer inspired by Aesthetic-Guided and copy-paste.”
MethodMachine Learning-Based Blind Image Quality Assessment: A Review
Tausif, M., Khan, M. F., Ansari, M. S., Khan, E., & Ghanbari, M. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-99-6547-2_2 · Cited by 2
A Mobile Image Aesthetics Processing System with Intelligent Scene Perception
Zhao, X., Shi, L., Zhao, H., & Yuan, P. (2024) · Applied Sciences · doi:10.3390/app14020822 · Cited by 1
Mobile photo recommendation system of continuous shots based on aesthetic ranking
Liu, K.-H., Lo, K.-Y., Kuo, Y.-C., & Chen, C. (2019) · Journal of Computer Languages · doi:10.1016/j.cola.2019.04.005 · Cited by 1
Photo Cropping via Deep Reinforcement Learning
Zhang, Y., Li, X., & Li, X. (2019) · IEEE International Conference on Agents (ICA) · doi:10.1109/agents.2019.8929167 · Cited by 1
Tinen, B., & Okamoto, J. (2019) · doi:10.5753/eniac.2019.9278 · Cited by 1
“Deep learning models have outperformed models based on handcrafted features and models based on other forms of generic image descriptors [Deng et al. 2017].”
BackgroundMethodMultitask Attentive Network For Text Effects Quality Assessment
Yan, K., Yang, S., Wang, W., & Liu, J. (2020) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme46284.2020.9102871 · Cited by 2
“To tackle this problem, researches have been devoted to Image Quality Assessment (IQA) [12–21], which aims to automatically predict the perceptual quality of an image.”
BackgroundJuger du Beau avec subjectivité : le défi de l’esthétique computationnelle
Maître, H. (2020) · Arts et sciences · doi:10.21494/iste.op.2020.0588 · Cited by 1
“…= 0, plusieurs équipes obtiennent plus de 80 % de résultats corrects sur la base AVA [Sheng et al., 2018, Ma et al., 2017, Talebi and Milanfar, 2017, Deng et al., 2017b] (en séparant bien sûr les photos servant à l’apprentissage de celles qui serviront à la vérification) et ces performances…”
BackgroundCharacter Photo Selection for Mobile Platform
Xu, C., Yu, X., & Sun, C. (2021) · Communications in computer and information science · doi:10.1007/978-3-030-72073-5_12 · Cited by 1
Modeling Human Perception of 3D Scenes
Yıldız, Z. Ç., Bülbül, A., & Çapın, T. (2021) · Human-computer interaction series · doi:10.1007/978-3-030-71002-6_5 · Cited by 1
Zong, H., Xia, Q., Zhang, L., & Zhu, J. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/1947504 · Cited by 1
“In this way, the process of going to the hospital can be avoided, and the patient can complete the rehabilitation treatment at home, saving the medical resources of the hospital and the treatment cost of the patient [17].”
BackgroundRetractedQuantifying Visual Image Quality: A Bayesian ViewPreprint
Duanmu, Z., Liu, W., Wang, Z., & Wang, Z. (2021) · Annual Review of Vision Science · doi:10.48550/arxiv.2102.00195 · Cited by 41
“The application scope includes, but is not limited to, computer graphics [47], video compression [127], video streaming [21], camera process [23], printing [39], visual displays [75], stereo vision [43], reduced-reference quality assessment [109], degraded-reference quality assessment [2], multi-exposure fusion [53],…”
BackgroundEffect of Encoded Theories of Visual Perception in Computational Aesthetics
Hoh, W. K. (2022) · Open Access Victoria University of Wellington | Te Herenga Waka (Figshare) · doi:10.26686/wgtn.20337570 · Cited by 2
Genre linked automated assessment and feedback of photographs based on visual aesthetics
Sudheendra, P., & Jayagopi, D. B. (2017) · International Conference on Image Processing Theory, Tools and Applications (IPTA) · doi:10.1109/ipta.2017.8310080
“Visual aesthetic analysis approaches proposed in literature can be broadly divided into two categories [1].”
BackgroundImage Aesthetics Assessment Based on User Social Behavior
Liu, H., Cui, C., Ma, Y., Cheng, S., Xu, Y., & Yin, Y. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00776-8_69
Fahn, C., Pan, J.-Y., & Wu, M.-L. (2018) · IEEE Region 10 Conference (TENCON) · doi:10.1109/tencon.2018.8650544
“72% and we compared with the related methods [8], [4], [9], [10], [11], which the corresponding results are presented in [4], [12] and [13].”
ResultSurvey: Deep Learning for Video Aesthetics
Bendale, M. (2019) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2019.2021
“Aesthetics assessment is a subjective field [4] because individual preferences differ according to personal taste too, thus what may be pleasing to one person may not be pleasing to the other.”
BackgroundMethodInfluentialAnalysis and Importance of Deep Learning for Video Aesthetic Assessments
Bendale, M., Phatak, M. V., & Pise, N. N. (2019) · International Journal of Scientific Research in Computer Science Engineering and Information Technology · doi:10.32628/cseit1951100
Evaluating Artificial Systems for Pairwise Ranking Tasks Sensitive to Individual DifferencesPreprint
Liu, X., & Okatani, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.13560
Seamless Capturing of Moments Using Photographic Compositions and Image Aesthetics
Kim, D., Kwon, T., Yoo, B., Lee, G.-I., Lee, W., Lee, J., Yim, S., & Jeong, J. (2020) · International Conference on Electronics, Information, and Communication (ICEIC) · doi:10.1109/iceic49074.2020.9051282
“The last undeniable objective of cameras is to take good pictures, and many previous works have been done to analyze elements of beauty in order to take good pictures and measure photographic quality of taken pictures [1].”
BackgroundContext Sensitive Image Denoising and Enhancement using U-Nets
Gandhi, S. T. (2020) · RIT Scholar Works (Rochester Institute of Technology)
From Technical to Aesthetics Quality Assessment and Beyond: Challenges and Potential
Hosu, V., Saupe, D., Goldlüecke, B., Lin, W., Cheng, W.-H., See, J., & Wong, L.-K. (2020) · doi:10.1145/3423268.3423589
“Comparatively, IAA received less research attention than IQA until recently [5].”
BackgroundComposition Harmony Assessment Method Based on Rule of Thirds
Tang, A., Jiang, W., Zhang, J., Wang, S., & Gao, Y. (2020) · International Conference on Culture-oriented Science & Technology (ICCST) · doi:10.1109/iccst50977.2020.00034
Ternary classification for image aesthetic assessment using deep learning
Jang, H., & Lee, J. (2020) · IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia) · doi:10.1109/icce-asia49877.2020.9277483
“With the development of the deep learning technology, the research on image aesthetic assessment has been actively conducted in recent years [1].”
BackgroundDeep Learning-based Video Summarization
Seo, M., Suh, Y., & Jeong, K. (2021) · International Journal on Advanced Science Engineering and Information Technology · doi:10.18517/ijaseit.11.6.12888
“Various attempts such as an iterative cropping technique [12]-[20] required considering the image's composition.”
A Context-Aware Intelligent System to Assist User Profile Filtering using AI and Deep Learning
Que, X., & Pan, Y. (2022) · doi:10.5121/csit.2022.120105 · Cited by 2
“Image aesthetic assessment [13] aims to computationally distinguish high-quality image from low-quality image based on photographic rules.”
BackgroundAI-empowered promotional video generation
Liu, C. (2022) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/161247 · Cited by 3
American Photography as Technical Art: Ontological, Cultural and Linguistic Aspects
Komarov, A. V. (2023) · Lecture notes in networks and systems · doi:10.1007/978-3-031-26783-3_14
Dynamic User Interface Composition
Kumar, R., Natarajan, S., Shariff, M. A. U., & Mani, P. V. (2023) · SN Computer Science · doi:10.1007/s42979-023-01672-w · Cited by 2
“Figure 10 shows that similar existing solutions [8, 9] do not handle aesthetics and saliency.”
BackgroundImage aesthetic ranking using deep convolutional neural network
Fahad, H. E., & Miften, F. S. (2023) · AIP conference proceedings · doi:10.1063/5.0125729
Gao, B.-B. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-08563-4 · Cited by 1
“It is noteworthy that our approach is easily scalable to others label uncertainty tasks, such as skeletal maturity assessment on pediatric hand radiographs [71], head pose estimation [4], popularity of selfie [72] and image aesthetic assessment [2].”
BackgroundAesthetic Image Synthesis Using Multiple-Aesthetic-Aware GAN
Setiyadi, Y., Santoso, J., & Surendro, K. (2023) · International Conference on Software and Computer Applications (ICSCA) · doi:10.1145/3587828.3587852
“makes use of the Rule-of-Third, depth-of-field, brightness, color harmony, and image composition features [4], [6], [16].”
MethodMaître, H. (2023) · Wiley eBooks · doi:10.1002/9781394225972.refs
Image quality assessment based on aesthetic evaluation
Zhao, J., Zhang, X., Wang, X., & Zhang, F. (2023) · International Conference on Applied Statistics, Computational Mathematics, and Software Engineering (ASCMSE) · doi:10.1117/12.2691853
Photographer-guided attributes for underwater image aesthetics
Emberton, S., & Simons, C. L. (2024) · Quality and User Experience · doi:10.1007/s41233-024-00065-y
“The automated assessment of image aesthetics is an active research area with applications in image editing and retrieval [6, 25].”
From Pixels to Palate: Deep Learning-Based Image Aesthetics Assessment for Food and Beverages
Weiler, J., Theissler, A., & Messer, U. (2023) · International Conference on Machine Learning and Applications · doi:10.1109/icmla58977.2023.00076
“Even experts will struggle to define the full set of rules and equations, encompassing aspects like lighting, contrast, image composition, color, or the rule of three [11]–[13].”
BackgroundMethodAbe, Y., Daikoku, T., & Kuniyoshi, Y. (2024) · Lecture notes in computer science · doi:10.1007/978-981-96-0116-5_1
New Perspectives for the Deep Learning Based Photography Aesthetics Assessment
Asuncion, V., & Zhang, Y. (2024) · Lecture notes in computer science · doi:10.1007/978-981-96-0351-0_19
Generative Text Prompts for Image Aesthetic Quality Assessment
Shi, J., Zhu, H., Yao, R., Shao, Z., & Li, L. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-5084-2_8
Computing the Deep Semantics of Visual Communications
Ježić, T. J., Maričević, M., Pavlović, I., & Mikota, M. (2025) · Tehnički glasnik · doi:10.31803/tg-20240603185810
Huang, M., & Xu, X. (2025) · Journal of Computational Methods in Sciences and Engineering · doi:10.1177/14727978251364440
DrawAA-Net: An AI-Supported Evaluation Tool for Children’s Drawings
Wang, S., Liu, W., Wang, J., Yi, Y., & Xu, J. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-98414-3_22
Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation
Tanji, N., & Yamasaki, T. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084643 · Cited by 1
Abe, Y., Daikoku, T., & Kuniyoshi, Y. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084491
Image aesthetic quality assessment: A method based on deep convolutional capsule network
Hu, Y., Dong, W. C., Zhang, Y., & Lu, L. (2025) · PLoS ONE · doi:10.1371/journal.pone.0331897 · Cited by 2
“It can be applied to improve content quality, optimize recommendation systems, and enhance users’ photographic and editing skills [3].”
Efficient Visual Appearance Optimization by Learning from Prior Preferences
Li, Z., Liao, Y.-C., & Holz, C. (2025) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3746059.3747622
“While aesthetic models exist to capture broad stylistic attributes such as vibrancy, warmth, or minimalism [12, 14], they fall short in modeling individual differences of preferences, ultimately limiting true personalization.”
Optimal design of artistic brand patterns based on visual perception and multi-model decision making
Chen, S., Li, L., & Ouahada, K. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.3210
Optimizing Similar Image Selection through Multimodal Feature Fusion
Yin, H., Huang, H., Zhang, L., Liu, Z., Qiao, Q., & Jin, X. (2025) · International Workshop on Multimedia Content Generation and Evaluation: New Methods and Practice (McGE) · doi:10.1145/3746278.3759379
“To address this issue, this study proposes a ranking optimization method based on violation cost [5].”
Image Aesthetic Assessment with Understanding Aesthetic Preferences
Kermani-Nejad, P., & Mahmoudi-Aznaveh, A. (2025) · doi:10.1109/ipria68579.2025.11263638
“Then, by introducing AlexNet [19] (the first time run on GPU) and also increasing the number of datasets [20]; data-driven approaches were noticed [2].”
Image Quality Factors Influencing Selfie Preference: The Role of Skin Color
Han, H., & Kwak, Y. (2025) · Color Research & Application · doi:10.1002/col.70034
Balancing the Load: Optimizing Inference of Generative Model on Example of Stable Diffusion
Popek, Ł., Bilski, P., & Perz, R. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-04197-5_15
EASFlow: An Emotion-Guided Aesthetic Stream Network with High-Fidelity Detail PreservationPreprint
Liu, W., & Yu, L. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6129140
Blending Designer Insights With Predicted Crowd‐Based Color Compatibility in Interior Color Design
Jin, S., & Hyun, K. H. (2026) · Color Research & Application · doi:10.1002/col.70055
Medel-Vera, C., & Gates, W. F. (2026) · SpringerBriefs in architectural design and technology · doi:10.1007/978-981-95-0760-3_16
A Quantitative Analysis of AI-Evaluated Educational Video Thumbnails: Correlation with Viewership
Kawata, T., Kato, T., & Tsuda, K. (2025) · IIAI International Congress on Advanced Applied Informatics (IIAI-AAI) · doi:10.1109/iiai-aai-winter69777.2025.00025
“Research attempting to quantitatively evaluate the aesthetic quality of images and videos has been advanced within the field of Image Aesthetic Assessment (IAA) [3].”
Assessment of photos in albums based on aesthetics and context
Kuzovkin, D. (2019) · theses.fr (ABES) · doi:10.70675/5b582cfaz4c5cz4f2azac84zecef6096b812 · Cited by 2
Image Aesthetic Quality Assessment Based on Deep Neural Networks
Kang, C. (2020) · theses.fr (ABES) · doi:10.70675/778ea95fz7566z430az89f7z50ccd2de25ee
Turbulent Approaches to Image Processing and Statistical Fractography
Lakhal, S. (2023) · theses.fr (ABES) · doi:10.70675/1176d425z62f9z4c9bz8f15z549176cdabe3
Improving image quality using high dynamic range and aesthetics assessment
Chambe, M. (2023) · theses.fr (ABES) · doi:10.70675/9f28e6f3z7eb3z414cz9752z1b2c8e4a8c95
FPEM: Face Prior Enhanced Facial Attractiveness Prediction for Live Videos with Face Retouching
Li, H., Ren, X., Yu, H., Chen, Y., Li, K., Wang, L., Min, X., Duan, H., Zhai, G., & Liu, X. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01066
“The corresponding IAA methods have evolved from employing handcrafted features, the modeling of photographic rules [8], global image layout [36] or typical objects [25] in perceived images [10] to data-driven approaches based on deep learning techniques that deliver superior performance [18–21].”
Learning Artistic Image Aesthetics From Multi-Level Text Prompts Generation
Zhu, H., Xu, X., Yao, R., Li, Y., Sun, K., & Li, L. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3694497
“In the context of IAA [23], [24], AIAA represents a specialized form of aesthetic evaluation focused on artistic images.”
Deep Learning-Based Multifaceted Feature Extraction for the Analysis of Architectural CG Images
Nishioka, K., SAKURAI, G., & Akinaru, I. I. N. O. (2026) · Journal of JSEE · doi:10.4307/jsee.74.3_31
Wang, T., & Wang, Y. (2026) · Electronics · doi:10.3390/electronics15122628
Metadata
- Authors
- Deng, Y., Loy, C. C., & Tang, X.
- Affiliations
- Chinese University of Hong Kong (HK)
- Venue
- IEEE Signal Processing Magazine
- Published
- 2017-07
- Volume
- 34
- Issue
- 4
- Pages
- 80-106
- ISSN
- 1053-5888 (ISSN-L)
- 1558-0792
- OpenAlex
- W2529088810
- Cited by
- 306
- References
- 95
- Citations by year
- 2026: 14 · 2025: 29 · 2024: 26 · 2023: 40 · 2022: 39 · 2021: 39 · 2020: 43 · 2019: 43 · 2018: 29 · 2017: 4
- FWCI
- 13.51
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Signal Processing Magazine (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Video Quality Assessment
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Keywords
- image aesthetic assessment, handcrafted features, deep features, deep learning, evaluation metrics
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.