How Art-like are AI-generated Images? An Exploratory Study
Authors: 
Junyu Chen, Jie An, Hanjia Lyu, 
Jiebo LuoAuthors Info & Claims
Junyu Chen, Jie An, Hanjia Lyu, Jiebo LuoAuthors Info & ClaimsPages 19 - 22
Abstract
Assessing the artness or artistic quality of AI-generated images continues to be a challenge within the realm of image generation. Most existing metrics cannot be used to perform instance-level and reference-free artness evaluation. This paper presents ArtScore, a metric designed to evaluate the degree to which an image resembles authentic artworks by artists (or conversely photographs), thereby offering a novel approach to artness assessment. We first blend pre-trained models for photo and artwork generation, resulting in a series of mixed models. Subsequently, we utilize these mixed models to generate images exhibiting varying degrees of artness with pseudo-annotations. Each photorealistic image has a corresponding artistic counterpart and a series of interpolated images that range from realistic to artistic. This dataset is then employed to train a neural network that learns to estimate quantized artness levels of arbitrary images. Extensive experiments reveal that the artness levels predicted by ArtScore align more closely with human artistic evaluation than existing evaluation metrics, such as Gram loss and ArtFID.
References
[1]
Rameen Abdal, Yipeng Qin, and Peter Wonka. 2019. Image2stylegan: How to embed images into the stylegan latent space?. In ICCV.
[2]
Jie An, Siyu Huang, Yibing Song, Dejing Dou, Wei Liu, and Jiebo Luo. 2021. Artflow: Unbiased image style transfer via reversible neural flows. In CVPR.
[3]
Bryandlee. 2021. Freezing generator for pseudo image translation. https://github.com/bryandlee/FreezeG
[4]
Dongdong Chen, Jing Liao, Lu Yuan, Nenghai Yu, and Gang Hua. 2017. Coherent online video style transfer. In ICCV.
[5]
Zhe Chen, Wenhai Wang, Enze Xie, Tong Lu, and Ping Luo. 2022. Towards ultra-resolution neural style transfer via thumbnail instance normalization. In AAAI.
[6]
Yingying Deng, Fan Tang, Weiming Dong, Chongyang Ma, Xingjia Pan, Lei Wang, and Changsheng Xu. 2022. Stytr2: Image style transfer with transformers. In CVPR.
[7]
Yingying Deng, Fan Tang, Weiming Dong, Wen Sun, Feiyue Huang, and Changsheng Xu. 2020. Arbitrary style transfer via multi-adaptation network. In ACM MM.
[8]
Leon A Gatys, Alexander S Ecker, and Matthias Bethge. 2015. A neural algorithm of artistic style. arXiv preprint arXiv:1508.06576 (2015).
[9]
Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. In NeurIPS.
[10]
Kibeom Hong, Seogkyu Jeon, Huan Yang, Jianlong Fu, and Hyeran Byun. 2021. Domain-aware universal style transfer. In ICCV.
[11]
Xun Huang and Serge Belongie. 2017. Arbitrary style transfer in real-time with adaptive instance normalization. In ICCV.
[12]
Jing Huo, Shiyin Jin, Wenbin Li, Jing Wu, Yu-Kun Lai, Yinghuan Shi, and Yang Gao. 2021. Manifold alignment for semantically aligned style transfer. In ICCV.
[13]
Tero Karras, Samuli Laine, and Timo Aila. 2019. A style-based generator architecture for generative adversarial networks. In CVPR.
[14]
Tero Karras, Samuli Laine, Miika Aittala, Janne Hellsten, Jaakko Lehtinen, and Timo Aila. 2020. Analyzing and improving the image quality of stylegan. In CVPR.
[15]
Xueting Li, Sifei Liu, Jan Kautz, and Ming-Hsuan Yang. 2019. Learning linear transformations for fast image and video style transfer. In CVPR.
[16]
Yijun Li, Chen Fang, Jimei Yang, Zhaowen Wang, Xin Lu, and Ming-Hsuan Yang. 2017. Universal style transfer via feature transforms. In NeurIPS.
[17]
Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C Lawrence Zitnick. 2014. Microsoft coco: common objects in context. In ECCV.
[18]
Songhua Liu, Tianwei Lin, Dongliang He, Fu Li, Meiling Wang, Xin Li, Zhengxing Sun, Qian Li, and Errui Ding. 2021. Adaattn: Revisit attention mechanism in arbitrary neural style transfer. In ICCV.
[19]
Xuan Luo, Zhen Han, Lingkang Yang, and Lingling Zhang. 2022. Consistent style transfer. arXiv preprint arXiv:2201.02233 (2022).
[20]
Kiri Nichol. 2016. Painter by numbers, WikiART. https://www.kaggle.com/c/painter-by-numbers
[21]
Utkarsh Ojha, Yijun Li, Jingwan Lu, Alexei A Efros, Yong Jae Lee, Eli Shechtman, and Richard Zhang. 2021. Few-shot image generation via cross-domain correspondence. In CVPR.
[22]
Dae Young Park and Kwang Hee Lee. 2019. Arbitrary Style Transfer With Style-Attentional Networks. In CVPR.
[23]
Lu Sheng, Ziyi Lin, Jing Shao, and Xiaogang Wang. 2018. Avatar-net: multi-scale zero-shot style transfer by feature decoration. In CVPR.
[24]
Ivan Skorokhodov, Grigorii Sotnikov, and Mohamed Elhoseiny. 2021. Aligning latent and image spaces to connect the unconnectable. In ICCV.
[25]
Jan Svoboda, Asha Anoosheh, Christian Osendorfer, and Jonathan Masci. 2020. Two-stage peer-regularized feature recombination for arbitrary image style transfer. In CVPR.
[26]
Xintao Wang, Ke Yu, Shixiang Wu, Jinjin Gu, Yihao Liu, Chao Dong, Yu Qiao, and Chen Change Loy. 2018. Esrgan: Enhanced super-resolution generative adversarial networks. In ECCV workshops.
[27]
Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. TIP, Vol. 13, 4 (2004), 600--612.
[28]
Matthias Wright and Björn Ommer. 2022. Artfid: Quantitative evaluation of neural style transfer. In PR.
[29]
Fen Xia, Tie-Yan Liu, Jue Wang, Wensheng Zhang, and Hang Li. 2008. Listwise approach to learning to rank: theory and algorithm. In ICML.
[30]
Fisher Yu, Ari Seff, Yinda Zhang, Shuran Song, Thomas Funkhouser, and Jianxiong Xiao. 2015. Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop. arXiv preprint arXiv:1506.03365 (2015).
[31]
Bolei Zhou, Agata Lapedriza, Aditya Khosla, Aude Oliva, and Antonio Torralba. 2017. Places: A 10 million image database for scene recognition. TPAMI, Vol. 40, 6 (2017), 1452--1464. io
Index Terms
- How Art-like are AI-generated Images? An Exploratory Study
Recommendations
Can Artificial Intelligence Make Art?: Folk Intuitions as to whether AI-driven Robots Can Be Viewed as Artists and Produce Art
In two experiments (total N = 693), we explored whether people are willing to consider paintings made by AI-driven robots as art, and robots as artists. Across the two experiments, we manipulated three factors: (i) agent type (AI-driven robot vs. human ...
Understanding and Creating Art with AI: Review and Outlook
Technologies related to artificial intelligence (AI) have a strong impact on the changes of research and creative practices in visual arts. The growing number of research initiatives and creative applications that emerge in the intersection of AI and art ...
Does human–AI collaboration lead to more creative art? Aesthetic evaluation of human-made and AI-generated haiku poetry
AbstractWith the development of technology, the quality of AI-generated text has improved. This is relevant in the AI art field, where AI generates literature or poetry that is appreciated. This study compared human-made and AI-generated haiku ...
Highlights- Human-made and AI-generated poetry were examined using haiku poetry.
- The beauty ...
Comments
Information & Contributors
Information
Published In
October 2023
151 pages
Copyright © 2023 Owner/Author.
This work is licensed under a Creative Commons Attribution International 4.0 License.
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 29 October 2023
Check for updates
Author Tags
Qualifiers
- Research-article
Conference
MM '23
Sponsor:
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 627Total Downloads
- Downloads (Last 12 months)541
- Downloads (Last 6 weeks)37
Reflects downloads up to 13 Jan 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in