Monet2Photo: Reverse Style Transfer using CycleGAN with Impressionism-to-Reality Domain

George Kerry Wijaya, Shining Sunny Chang, Jonathan Saputra, Annabelle Chloe, Monika Evelin Johan
Pages 1483-1495
Abstract Views 397
PDF Downloads 476
Crossref Citations -
DOI https://doi.org/10.47738/jads.v7i2.1222

Abstract


The application of artificial intelligence in artistic image transformation has primarily focused on converting real-world photographs into stylized artworks. In contrast, the inverse task of reconstructing photorealistic images from paintings remains relatively underexplored and presents substantial technical challenges. This study aims to investigate the feasibility and limitations of reverse style transfer by translating impressionist paintings into realistic photographic images, using the works of Claude Monet as a representative case. The main contribution of this research lies in providing a critical examination of reverse image translation under extreme domain gaps, rather than proposing aesthetic enhancement. An unpaired image-to-image translation framework based on CycleGAN is employed to learn mappings between painting and photographic domains without relying on paired data. The methodology is conceptually grounded in adversarial learning combined with cycle consistency constraints to encourage structural preservation while attempting to reconstruct plausible visual features. The experimental setup utilizes a dataset consisting of 300 Monet paintings and 7,028 real photographs, with targeted data augmentation applied to the painting domain to address data imbalance. Prior to model training, exploratory data analysis is conducted to characterize domain discrepancies through visual and statistical comparisons, including color distribution analysis, grayscale intensity patterns, texture descriptors, and dimensionality reduction. Model performance is evaluated through controlled experiments using distribution-based distance measures and qualitative visual inspection. The results indicate that while the model is capable of preserving coarse spatial layouts and generating diverse outputs without memorization, it struggles to recover high-fidelity textures, illumination, and contrast required for photorealistic reconstruction. These findings highlight the inherent limitations of classical CycleGAN architectures for reverse style transfer and suggest the need for more expressive models and stronger constraints in future research on art-to-reality image translation.

Keywords


Adversarial Learning; CycleGAN; Image-To-Image Translation; Monet Painting; Photorealistic Image Generation

Full Text:

PDF

References


L. Wang, L. Wang, and S. Chen, “ESA-CycleGAN: Edge feature and self-attention based cycle-consistent generative adversarial network for style transfer,” IET Image Process., vol. 16, no. 1, pp. 176–190, 2022.

S. Manandhar, S. Naikodi, M. V. VL, M. Z. AN, and others, “Generating Monet Style Images Using DCGAN Based CycleGAN,” 2023.

M. Li, L. Lin, G. Luo, and H. Huang, “Monet style oil painting generation based on cyclic generation confrontation network,” in International Conference on Frontiers of Applied Optics and Computer Engineering (AOCE 2024), 2024, pp. 120–125.

A. Agarwal, I. Sangal, and A. Shrotriya, “The Artistic Transformation: Monet Style Transfer Using Cycle Gan,” in International Conference on ICT for Sustainable Development, 2025, pp. 215–224.

F. N. U. Neha, D. Bhati, D. K. Shukla, and M. Amiruzzaman, “A Tiered GAN Approach for Monet-Style Image Generation,” in 2024 34th International Conference on Computer Theory and Applications (ICCTA), 2024, pp. 232–237.

G. Yao and Z. Abindinhazir, “study and appreciation of Claude Monet’s artistic creation and life experience,” Idealogy J., vol. 8, no. 2, 2023.

T. Baumeister and with Mette Gieskes mette. gieskes@ ru. nl, “Space, Time, and Change in Claude Monet’s Late Paintings,” in Retrospection and Revision in Modern and Contemporary Art, Literature and Music, Springer, 2024, pp. 215–233.

N. H. Shabrina, S. Indarti, D. A. Kristiyanti, N. Prastomo, and others, “Explainable ensemble deep learning for potato leaf pest and diseases identification.,” Int. J. Adv. Soft Comput. Its Appl., vol. 17, no. 2, 2025.

J.-Y. Zhu, T. Park, P. Isola, and A. A. Efros, “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks,” in Computer Vision (ICCV), 2017 IEEE International Conference on, 2017.

D. Saxena and J. Cao, “Generative adversarial networks (GANs) challenges, solutions, and future directions,” ACM Comput. Surv., vol. 54, no. 3, pp. 1–42, 2021.

X. Ma, “A comparison of art style transfer in Cycle-GAN based on different generators,” in Journal of Physics: Conference Series, 2024, p. 12006.

M. Fu, Y. Liu, R. Ma, B. Zhang, L. Wu, and L. Zhu, “A model integrating attention mechanism and generative adversarial network for image style transfer,” PeerJ Comput. Sci., vol. 10, p. e2332, 2024.

L. Lakshmi et al., “Performance analysis of cycle gan in photo to portrait transfiguration using deep learning optimizers,” IEEE Access, vol. 11, pp. 136541–136551, 2023.

Y. Liao and Y. Huang, “Deep Learning-Based Application of Image Style Transfer,” Math. Probl. Eng., vol. 2022, no. 1, p. 1693892, 2022.

Y. Liu, “Improved generative adversarial network and its application in image oil painting style transfer,” Image Vis. Comput., vol. 105, p. 104087, 2021.

L. Vela, F. Fuentes-Hurtado, and A. Colomer, “Improving the quality of image generation in art with top-k training and cyclic generative methods,” Sci. Rep., vol. 13, no. 1, p. 17764, 2023.

Y. Zhao, “Application of CycleGAN-based image style transfer algorithm in visual communication design,” J. Comput. Methods Sci. Eng., p. 14727978251318804, 2025.

M. Wang, “Mask CycleGAN: Unpaired Multi-modal Domain Translation with Interpretable Latent Variable,” arXiv Prepr. arXiv2205.06969, 2022.

C.-Y. Bai, H.-T. Lin, C. Raffel, and W. C. Kan, “On training sample memorization: Lessons from benchmarking generative modeling with a large-scale competition,” in Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining, 2021, pp. 2534–2542.

C.-Y. Bai, H.-T. Lin, C. Raffel, and W. Kan, “A Large-scale Study on Training Sample Memorization in Generative Modeling,” 2020.

J. Kim and J. Song, “A review on the generative models and its performance metrics,” Commun. Stat. Appl. Methods, vol. 32, no. 2, pp. 235–248, 2025.

A. Jang, A. S. Uzsoy, and P. Culliton, “I’m Something of a Painter Myself.” 2020.

I. Maity and S. Samanta, “Utilization of Image Processing Tools for a Comparative Study on RGB and HSV Color Space: Targeting Feature Extraction of Banana Fruit Image During Different Ripeness Stages,” in 2024 IEEE Silchar Subsection Conference (SILCON 2024), 2024, pp. 1–6.

N. Phuangsaijai, J. Jakmunee, and S. Kittiwachana, “Investigation into the predictive performance of colorimetric sensor strips using RGB, CMYK, HSV, and CIELAB coupled with various data preprocessing methods: a case study on an analysis of water quality parameters,” J. Anal. Sci. Technol., vol. 12, no. 1, p. 19, 2021.

N. Iqbal, R. Mumtaz, U. Shafi, and S. M. H. Zaidi, “Gray level co-occurrence matrix (GLCM) texture based crop classification using low altitude remote sensing platforms,” PeerJ Comput. Sci., vol. 7, p. e536, 2021.

J. Ao, Z. Ye, W. Li, and S. Ji, “Impressions of Guangzhou city in Qing dynasty export paintings in the context of trade economy: a color analysis of paintings based on k-means clustering algorithm,” Herit. Sci., vol. 12, no. 1, p. 77, 2024.

B. Zhao, X. Dong, Y. Guo, X. Jia, and Y. Huang, “PCA dimensionality reduction method for image classification,” Neural Process. Lett., vol. 54, no. 1, pp. 347–368, 2022.

S.-A. Rebuffi, S. Gowal, D. A. Calian, F. Stimberg, O. Wiles, and T. A. Mann, “Data augmentation can improve robustness,” Adv. Neural Inf. Process. Syst., vol. 34, pp. 29935–29948, 2021.

K. Maharana, S. Mondal, and B. Nemade, “A review: Data pre-processing and data augmentation techniques,” Glob. Transitions Proc., vol. 3, no. 1, pp. 91–99, 2022.

V. C. Tjokro and S. Ady Sanjaya, “Enhancing Data Traceability: A Knowledge Graph Approach with Retrieval-Augmented Generation,” in 2024 7th International Seminar on Research of Information Technology and Intelligent Systems (ISRITI), 2024, pp. 473–478. doi: 10.1109/ISRITI64779.2024.10963652.

D. Torbunov et al., “Uvcgan: Unet vision transformer cycle-consistent gan for unpaired image-to-image translation,” in Proceedings of the IEEE/CVF winter conference on applications of computer vision, 2023, pp. 702–712.




DOI: https://doi.org/10.47738/jads.v7i2.1222

Refbacks

  • There are currently no refbacks.


Barcode

Journal of Applied Data Sciences

ISSN:2723-6471 (Online)
Publisher:Bright Publisher
Website:http://bright-journal.org/JADS
Email:taqwa@amikompurwokerto.ac.id (principal contact)
  support@bright-journal.org (technical issues)

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0