The Rich, the Poor, and the Ugly: An Aesthetic-Perspective Assessment of NFT Values
Open accessThe DOI matches its Crossref record; 28 of the 29 references it cites were found in a registry or an index.
Abstract
The adoption of non-fungible tokens (NFTs) has revolutionized digital art transactions, providing artists with unprecedented opportunities to tokenize and monetize their generative creations, leading to increased scrutiny and demand within blockchain-oriented marketplaces. The pricing of NFT artworks, however, exhibits substantial variations within and across collections, influenced by various factors. This study aims to investigate the relationship between visual features and pricing, shedding light on the variations underlying the pricing of NFTs. First, measures of both computational aesthetics and visual complexity were applied to extract multi-faceted visual aesthetic features, encompassing aesthetic factors such as color and composition as well as complexity factors like entropy. Second, with extracted visual aesthetic features and preprocessed price data, the study proceeds to conduct correlation analysis within collections and statistical modeling across collections. Through these approaches, we reveal a moderate correlation between visual features and prices within collections, while also identifying different influential visual features across collections. The differential performance of price models highlights the distinctiveness and unique pricing characteristics of NFT collections.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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
“The highest correlation with price is found to be due to the most frequent hue in the Cool Cat collection. However, the overall fitting quality in a linear regression model is rather poor, since the R 2 is just 0.15 for the Cool Cat collection and 0.24 for the Doodles one.”
From What Is the Right Price for Non-Fungible Tokens (NFTs)? A Systematic Review of the Current Literature (2025) · cites this paper as [49]
Citations
Cites
Convolutional Neural Networks for No-Reference Image Quality Assessment
Kang, L., Ye, P., Li, Y., & Doermann, D. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.224 · Cited by 1,270 · cited 1×
“Despite the existence of advanced techniques such as Deep Neural Networks for image assessment [6, 8, 16, 26, 33], the main ob-jective of our study is to elucidate and provide a comprehensive understanding of the visual aesthetics that influence the pricing of NFTs.”
MethodTalebi, H., & Milanfar, P. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2831899 · Cited by 1,023 · cited 1×
“Despite the existence of advanced techniques such as Deep Neural Networks for image assessment [6, 8, 16, 26, 33], the main ob-jective of our study is to elucidate and provide a comprehensive understanding of the visual aesthetics that influence the pricing of NFTs.”
MethodMultivariate Statistical Modelling Based on Generalized Linear Models
Fahrmeir, L., & Tutz, G. (2001) · Springer Series in Statistics · doi:10.1007/978-1-4757-3454-6 · Cited by 727
No-reference image quality assessment based on spatial and spectral entropies
Liu, L., Liu, B., Huang, H., & Bovik, A. C. (2014) · Signal Processing: Image Communication · doi:10.1016/j.image.2014.06.006 · Cited by 721 · cited 1×
“Other than relying on traditional handcrafted features grounded in art principles, statistical properties derived from image processing techniques can also be utilized as features [20] in terms of visual complexity.”
MethodMapping the NFT revolution: Market trends, trade networks, and visual features
Nadini, M., Alessandretti, L., Di Giacinto, F., Martino, M., Aiello, L. M., & Baronchelli, A. (2021) · Scientific Reports · doi:10.1038/s41598-021-00053-8 · Cited by 715 · cited 6×
“These models employ distinct analytical methods, including statistical and machine learning techniques, such as the Hedonic pricing approach [13], linear regression models [14, 17, 23], and recurrent neural networks [14].”
BackgroundMethodResultInfluentialThe Design of High-Level Features for Photo Quality Assessment
Ke, Y., Tang, X., & Jing, F. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1 (CVPR'06) · doi:10.1109/cvpr.2006.303 · Cited by 630 · cited 2×
“The features can be attributed to the visual components of aesthetics, and are grounded in specific artistic principles or photography skills [18] to substantiate their relevance.”
BackgroundMethodThe non-fungible token (NFT) market and its relationship with Bitcoin and Ethereum
Ante, L. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3861106 · Cited by 362
Aesthetic Visual Quality Assessment of Paintings
Li, C., & Chen, T. (2009) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2009.2015077 · Cited by 273
A deep neural network for image quality assessment
Bosse, S., Maniry, D., Wiegand, T., & Samek, W. (2016) · 2016 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2016.7533065 · Cited by 223 · cited 1×
“Despite the existence of advanced techniques such as Deep Neural Networks for image assessment [6, 8, 16, 26, 33], the main ob-jective of our study is to elucidate and provide a comprehensive understanding of the visual aesthetics that influence the pricing of NFTs.”
MethodBoden, M. A., & Edmonds, E. A. (2009) · Digital Creativity · doi:10.1080/14626260902867915 · Cited by 222
TweetBoost: Influence of Social Media on NFT Valuation
Kapoor, A., Guhathakurta, D., Mathur, M., Yadav, R., Gupta, M., & Kumaraguru, P. (2022) · Companion Proceedings of the Web Conference 2022 · doi:10.1145/3487553.3524642 · Cited by 115
Heterogeneous rarity patterns drive price dynamics in NFT collections
Mekacher, A., Bracci, A., Nadini, M., Martino, M., Alessandretti, L., Aiello, L. M., & Baronchelli, A. (2022) · Scientific Reports · doi:10.1038/s41598-022-17922-5 · Cited by 110
Price determinants of non-fungible tokens in the digital art market
Horky, F., Rachel, C., & Fidrmuc, J. (2022) · Finance Research Letters · doi:10.1016/j.frl.2022.103007 · Cited by 104
Yanulevskaya, V., Uijlings, J., Bruni, E., Sartori, A., Zamboni, E., Bacci, F., Melcher, D., & Sebe, N. (2012) · Proceedings of the 20th ACM international conference on Multimedia · doi:10.1145/2393347.2393399 · Cited by 102
Computational aesthetics and applications
Bo, Y., Yu, J., & Zhang, K. (2018) · Visual Computing for Industry Biomedicine and Art · doi:10.1186/s42492-018-0006-1 · Cited by 82 · cited 1×
“To retrieve the underlying determinants of visual aesthetics, utilizing feature extraction methods grounded in the direction of computational aesthetics in aesthetic measurement is supportive [4].”
MethodZhang, J., Miao, Y., & Yu, J. (2021) · IEEE Access · doi:10.1109/access.2021.3083075 · Cited by 72
The impact of NFT profile pictures within social network communities
Casale-Brunet, S., Zichichi, M., Hutchinson, L., Mattavelli, M., & Ferretti, S. (2022) · International Conference on Information Technology for Social Good (GoodIT) · doi:10.1145/3524458.3547230 · Cited by 58 · cited 1×
“Key factors that have been identified as playing a significant role include the historical price trend of the specific asset [23], the rarity of the property [22], and the popularity of the creator [7, 17] associated with the NFT pricing.”
BackgroundWhat Do We Mean by Smart Contracts? Open Challenges in Smart Contracts
Vigliotti, M. G. (2021) · Frontiers in Blockchain · doi:10.3389/fbloc.2020.553671 · Cited by 49
Ye, Y., Huang, R., & Zeng, W. (2022) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2022.3229023 · Cited by 47 · cited 1×
“In addition to enhancing methodologies, an intriguing avenue to consider involves the development of a visual exploration tool [9, 29, 31] with the primary objective of assisting individuals in navigating NFT artworks based on their specific visual features of interest.”
MethodSelf-citationTurbulent Luminance in Impassioned van Gogh Paintings
Aragón, J. L., Naumis, G. G., Bai, M., Torres, M., & Maini, P. K. (2008) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-007-0055-0 · Cited by 38
Deep Colormap Extraction From Visualizations
Yuan, L.-P., Zeng, W., Fu, S., Zeng, Z., Li, H., Fu, C., & Qu, H. (2021) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2021.3070876 · Cited by 37
Self-citationSuPoolVisor: a visual analytics system for mining pool surveillance
Xia, J., Zhang, Y., Ye, H., Wang, Y., Jiang, G., Zhao, Y., Xie, C., Kui, X., Liao, S., & Wang, W. (2020) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/fitee.1900532 · Cited by 34 · cited 1×
“Furthermore, various theoretical models and empirical studies have been proposed to provide further insight into the dynamics of NFT pricing, with potential implications for the broader cryptocurrency market [28].”
BackgroundJain, S., Bruckmann, C., & McDougall, C. (2022) · RePEc: Research Papers in Economics · doi:10.48550/arxiv.2204.12932 · Cited by 22
Comparing Neural and Attractiveness-based Visual Features for Artwork Recommendation
Dominguez, V., Messina, P., Parra, D., Mery, D., Trattner, C., & Soto, Á. (2017) · Workshop on Deep Learning for Recommender Systems (DLRS) · doi:10.1145/3125486.3125495 · Cited by 16 · cited 1×
“Despite the existence of advanced techniques such as Deep Neural Networks for image assessment [6, 8, 16, 26, 33], the main ob-jective of our study is to elucidate and provide a comprehensive understanding of the visual aesthetics that influence the pricing of NFTs.”
MethodComplexity and aesthetics in generative and evolutionary art
McCormack, J., & Gambardella, C. C. (2022) · Genetic Programming and Evolvable Machines · doi:10.1007/s10710-022-09429-9 · Cited by 15
Dong, A., Zeng, W., Chen, X., & Cheng, Z. (2019) · International Symposium on Visual Information Communication and Interaction (VINCI) · doi:10.1145/3356422.3356430 · Cited by 13
Self-citationNFTVis: Visual Analysis of NFT Performance
Yan, F., Wang, X., Mao, K., Zhang, W., & Chen, W. (2023) · IEEE Pacific Visualization Symposium · doi:10.1109/pacificvis56936.2023.00016 · Cited by 8 · cited 1×
“In addition to enhancing methodologies, an intriguing avenue to consider involves the development of a visual exploration tool [9, 29, 31] with the primary objective of assisting individuals in navigating NFT artworks based on their specific visual features of interest.”
MethodEveryone Can Be Picasso? A Computational Framework into the Myth of Human versus AI PaintingPreprint
Ye, Y., Huang, R., Kang Zhang, A., & Zeng, W. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2304.07999 · Cited by 3
Self-citation
Research works printed but not linked: 7
- 10.3390/fintech1030017 · doi:10.3390/fintech1030017 · Paper page
- George David Birkhoff . 2013. Aesthetic measure . Harvard University Press . George David Birkhoff. 2013. Aesthetic measure. Harvard University Press.
- Philip Galanter . 2003 . What is generative art? Complexity theory as a context for art theory . In Proceedings of 6th Generative Art Conference. Philip Galanter. 2003. What is generative art? Complexity theory as a context for art theory. In Proceedings of 6th Generative Art Conference.
- 10.5555/2381219.2381222 · doi:10.5555/2381219.2381222
- 10.1155/2019 · doi:10.1155/2019
- Satoshi Nakamoto . 2008 . Bitcoin: A peer-to-peer electronic cash system. https://bitcoin.org/en/bitcoin-paper. Satoshi Nakamoto. 2008. Bitcoin: A peer-to-peer electronic cash system. https://bitcoin.org/en/bitcoin-paper.
- Andrei-Dragos Popescu . 2021 . Non-Fungible Tokens (NFT) - Innovation beyond the craze . In Proceedings of Engineering & Technology Journal. Andrei-Dragos Popescu. 2021. Non-Fungible Tokens (NFT) - Innovation beyond the craze. In Proceedings of Engineering & Technology Journal.
Cited by
Unlocking the potential of NFTs in branding: An exploration of NFT-based brand experience
Li, W., de Zubielqui, G. C., & Hill, S. R. (2025) · Journal of Retailing and Consumer Services · doi:10.1016/j.jretconser.2025.104313 · Cited by 12
Integrating Machine Learning with Non-Fungible Tokens
Iosif, E., & Katelaris, L. (2024) · Computers · doi:10.3390/computers13060147 · Cited by 5
“The work in [25] comprises two main branches: the extraction of visual features, also referred to as aesthetic features, and an investigation of the development of predictive models for NFTs pricing utilizing the extracted features.”
MethodFlamini, M., & Naldi, M. (2025) · FinTech · doi:10.3390/fintech4040073 · Cited by 1
“A similar approach is taken by Chen et al. [49], where the influence of aesthetics factors on price is examined.”
Introducing the NFT Popularity to Cover the Gap of Rarity in the NFT Evaluation
Guidi, B., & Michienzi, A. (2025) · ACM Transactions on the Web · doi:10.1145/3785018 · Cited by 1
Demystifying the Role of Aesthetics in NFT Pricing: Model, Analysis, and Insights
Mahrous, A., & Pietro, R. D. (2025) · International Conference on Blockchain Computing and Applications (BCCA) · doi:10.1109/bcca66705.2025.11229591
“Chen et al. [20] analyzed two NFT collections, extracting 18 explicit visual metrics from nearly 20,000 NFT images, and applied linear regression and correlation analysis.”
Metadata
- Authors
- Chen, Y., Ye, Y., & Zeng, W.
- Affiliations
- The Hong Kong University of Science and Technology (Guangzhou) (CN)
- Venue
- Proceedings of the 16th International Symposium on Visual Information Communication and Interaction
- Publisher
- ACM
- Published
- 2023-09-22
- Pages
- 1-8
- OpenAlex
- W4387827793
- Cited by
- 6
- References
- 29
- Citations by year
- 2026: 1 · 2025: 4 · 2024: 1
- FWCI
- 3.09
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- International Symposium on Visual Information Communication and Interaction (VINCI) (publishedVersion)
- Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
- Topics
- Life Sciences › Neuroscience › Cognitive Neuroscience › Aesthetic Perception and Analysis
- Social Sciences › Arts and Humanities › Visual Arts and Performing Arts › Art History and Market Analysis
- Physical Sciences › Computer Science › Information Systems › Blockchain Technology Applications and Security
- Keywords
- non-fungible tokens, NFT pricing, digital art, computational aesthetics, visual complexity, entropy (information theory), color and composition, generative art, price prediction model, NFT collections
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.