Theoretical and Natural Science
- The Open Access Proceedings Series for Conferences
Theoretical and Natural Science
Vol. 19, 08 December 2023
Open
Access | Article
In-game architectural image translation using improved Cycle-Gan
* Author to whom correspondence should be addressed.
Abstract
The point of video games is that players can reap success and excitement in games that they cannot easily experience in the real world. The quality of translating in-game architectural images to photos determines whether the game has many players and good prospects for development. This research in this paper is to implement the function of image-to-image translation using Cycle-GAN. In this work, the dataset is pre-processed to make it more suitable for training the network. Then images are generated by the generator, and the discriminator determines whether the generated ones seem real or not. The confrontation loss and the cycle loss are performed to constrain the learning of the entire system. However, distractions still exist in this system, such as people in the background of the game could be wrongly identified as part of the building, or as a pillar and hence resulting in odd results. To mitigate it, a self-attention mechanism was added to the network to address this phenomenon, allowing the network to focus on the architecture and not disperse attention to some of the game characters. After optimization and testing, the results show that the network can be well-optimized for game-style images to resemble the realistic architecture more closely.
Keywords
video games, Cycle-Gan, optimization, self-attention.
References
1. McAllister, G., & White, G. R. (2015). Video game development and user experience. In Game user experience evaluation, 11-35.
2. González Sánchez, J. L., Padilla, Z. N., & Gutiérrez, F. L. (2009). From usability to playability: Introduction to player-centred video game development process. In International Conference on Human Centered Design, 65-74.
3. Sweetser, P., & Wiles, J. (2002). Current AI in games: A review. Australian Journal of Intelligent Information Processing Systems, 8(1), 24-42.
4. Zackariasson, P., Walfisz, M., & Wilson, T. L. (2006). Management of creativity in video game development: A case study. Services marketing quarterly, 27(4), 73-97.
5. Dehghani, M., Montazeri, Z., Saremi, S., Dehghani, A., et al. (2020). HOGO: Hide objects game optimization. Int. J. Intell. Eng. Syst, 13(10), 216-225.
6. Isola, P., Zhu, J. Y., Zhou, T., & Efros, A. A. (2017). Image-to-image translation with conditional adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, 1125-1134.
7. Wang, X., & Gupta, A. (2016). Generative image modeling using style and structure adversarial networks. In European conference on computer vision, 318-335.
8. Zhu, J. Y., Park, T., Isola, P., & Efros, A. A. (2017). Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the IEEE international conference on computer vision, 2223-2232.
9. Engin, D., Genç, A., & Kemal Ekenel, H. (2018). Cycle-dehaze: Enhanced cyclegan for single image dehazing. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops, 825-833.
10. Suyash D. (2019). An unpaired-images dataset for training CycleGANs, URL: https://www.kaggle.com/suyashdamle/cyclegan
11. Taleb, I., Dssouli, R., & Serhani, M. A. (2015). Big data pre-processing: A quality framework. In 2015 IEEE international congress on big data, 191-198.
12. Roy, A. G., Navab, N., & Wachinger, C. (2018). Recalibrating fully convolutional networks with spatial and channel “squeeze and excitation” blocks. IEEE transactions on medical imaging, 38(2), 540-549.
13. Feiniu, Y., Lin, Z., Jinting, S., Xue, X. I. A., & Gang, L. I. (2019). A review of the theory and application of self coding neural networks. Acta Sinica Sinica, 42(001), 203-230.
14. Liu, L., Xi, Z., Ji, R., & Ma, W. (2019). Advanced deep learning techniques for image style transfer: a survey. Signal Processing: Image Communication, 78, 465-470.
15. Cho, K., Courville, A., & Bengio, Y. (2015). Describing multimedia content using attention-based encoder-decoder networks. IEEE Transactions on Multimedia, 17(11), 1875-1886.
16. Chowdhary, K. (2020). Natural language processing. Fundamentals of artificial intelligence, 603-649.
17. Anokhin, I., Demochkin, K., Khakhulin, T., Sterkin, G., Lempitsky, V., & Korzhenkov, D. (2021). Image generators with conditionally-independent pixel synthesis. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 14278-14287.
18. Chen, Y., Lai, Y. K., & Liu, Y. J. (2018). Cartoongan: Generative adversarial networks for photo cartoonization. In Proceedings of the IEEE conference on computer vision and pattern recognition, 9465-9474.
19. Wang, F., Cheng, J., Liu, W., & Liu, H. (2018). Additive margin softmax for face verification. IEEE Signal Processing Letters, 25(7), 926-930.
Data Availability
The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. Authors who publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See Open Access Instruction).
- Volume Title
- Proceedings of the 2nd International Conference on Computing Innovation and Applied Physics
- ISBN (Print)
- 978-1-83558-203-9
- ISBN (Online)
- 978-1-83558-204-6
- Published Date
- 08 December 2023
- Series
- Theoretical and Natural Science
- ISSN (Print)
- 2753-8818
- ISSN (Online)
- 2753-8826
- DOI
- 10.54254/2753-8818/19/20230477
- Copyright
- 08 December 2023
- Open Access
- This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited