Abstract
Based on the analysis of human-AI (artificial intelligence) collaboration in creating Chinese landscape painting, this article aims to develop the relationship between AI aesthetics and HCI in the context of Chinese aesthetics. We construct a multi-level analysis framework and propose three unique AI Aesthetics models under the frameworkâthe dynamic brushwork (bi-mo) model, the imaged mind (xin-yin) model, and the embodied narrative (shi-jing) model. We believe that the most promising AI aesthetics approach is to promote the collaboration between human and AI. The primary research task at present is to develop interactive creation platforms. In the long run, brain-AI interactive communication will help realize mutual inspiration between human and AI, thereby stimulating more creativity.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Galanter, P.: Computational aesthetic evaluation: past and future. In: McCormack, J., Inverno, M. (eds.) Computers and Creativity, pp. 255â293. Springer, Berlin. (2012)
Manovich, L.: AI Aesthetics. Strelka Press, Moskva (2018)
Fong, C.W.: Images of the Mind: Selections from the Edward L. Elliott Family and John B. Elliott Collections of Chinese Painting and Calligraphy at the Art Museum, Princeton University. Princeton University Press, New Jersey (1984)
Fong, C.W.: Beyond Representation: Chinese Painting and Calligraphy, 8thâ14th Century. Yale University Press, New Haven (1992)
Fan, Z., Li, Y., Yu, J., Zhang, K.: Visual complexity of Chinese ink paintings. In: Stephen, N.S. (Eds) ACM Symposium on Applied Perception 2017, Vol. 9, pp. 1â8. Association for Computing Machinery, New York (2017). https://doi.org/10.1145/3119881.3119883
Jia, B., Brandt, J., Mech, R., Kim, B., Manocha, D.: LPaintB: Learning to Paint from Self-supervision (2019). arXiv preprint: arXiv:1906.06841
Mordvintsev, A.: Inceptionism: Going Deeper into Neural Networks (2015). https://ai.googleblog.com/2015/06/inceptionism-going-deeper-into-neural.html. Accessed 8 Jan 2021.
Gatys, L.A., Ecker, A.S., Bethge, M.: A Neural Algorithm of Artistic Style (2015). arXiv preprint: arXiv:1508.06576
Ha, D., Eck, D.: A Neural Representation of Sketch Drawings (2017). arXiv preprint: arXiv:1704.03477
Park, T., Liu, M.Y., Wang, T.C., Zhu, J.Y.: Semantic Image Synthesis with Spatially Adaptive Normalization (2019). arXiv preprint: arXiv:1903.07291
Bidgoli, A., Guevara, M.D.L., Hsiung, C., Oh, J., Kang, E.: Artistic style in robotic painting; a machine learning approach to learning brushstroke from human artists. In: 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), pp. 412â418. IEEE Press, New York (2020)
Mousavian, A., Eppner, C., Fox, D.: 6-DOF GraspNet: variational grasp generation for object manipulation. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 2901â2910. IEEE Press, New York (2019)
Gordon, D., Kadian, A., Parikh, D., Hoffman, J., Batra, D.: SplitNet: Sim2Sim and Task2Task transfer for embodied visual navigation. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 1022â1031. IEEE Press, New York (2019)
Litany, O., Morcos, A., Sridhar, S., Guibas, L., Hoffman, J.: Representation learning through latent canonicalizations. In: 2021 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 645â654. IEEE Press, New York (2021)
Chan, C., Ginosar, S., Zhou, T., Efros, A.A.: Everybody dance now. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 5933â5942. IEEE Press, New York (2019).
Guo, C., Hou, Z.X., Shi, Y.Z., Xu, J., Yu, D.D.: A virtual 3D interactive painting method for chinese calligraphy and painting based on real-time force feedback technology. Front. Inf. Technol. Electron. Eng. 18(11), 184â195 (2017)
Zheng, S.Z., Hou, Z.X., Guo, C., Yang, G.Q.: The simulation of the half-dry stroke based on the force feedback technology. J. Comput. Aid. Des. Comput. Graph. 28(6), 1016â1024 (2016)
Zhang, G., Cheng, J.L., Song, J., Guo, J.Q., Zhou, C.R.: Chinese landscape painting automated generation model based on generative adversarial networks. Comput. Telecommun. 280(03), 5â9 (2020)
Sheng, J.C., Li, Y.Z.: Learning artistic objects for improved classification of chinese paintings. J. Image Graph. 23(8), 1193â1206 (2018)
Tong, Y.: Research on the style transfer model of Chinese paintings based on deep network. Chin. Mus. 142(3), 139â145 (2020)
Alice, X.: End-to-End Chinese Landscape Painting Creation Using Generative Adversarial Networks(2020). arXiv preprint: arXiv:2011.05552
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
Âİ 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Chang, R., Huang, Y. (2021). Towards AI Aesthetics: Human-AI Collaboration in Creating Chinese Landscape Painting. In: Rauterberg, M. (eds) Culture and Computing. Interactive Cultural Heritage and Arts. HCII 2021. Lecture Notes in Computer Science(), vol 12794. Springer, Cham. https://doi.org/10.1007/978-3-030-77411-0_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-77411-0_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-77410-3
Online ISBN: 978-3-030-77411-0
eBook Packages: Computer ScienceComputer Science (R0)