Exploiting Improved Cyclic Generative Adversarial Networks to Generate Images from Different Angles of Views
DOI:
https://doi.org/10.62051/h2txdv03Keywords:
CycleGAN; image generation; view of image; angle of view.Abstract
Virtual Reality (VR), Augmented Reality (AR), and other similar technologies are becoming increasingly popular nowadays. However, despite the increasing number of related devices being launched, the feedback tends to be disappointing. A significant contributor to this dissatisfaction is the blurred viewpoints and unclear levels, which often lead to a suboptimal user experience. To address this issue, this research focuses on training a modified version of the Cycle-Consistent Generative Adversarial Networks (CycleGAN) model to generate an image from another angle of view based on a given image. This work has fine-tuned specific layers of the CycleGAN to better suit the requirements of this work. These improvements give the model enhanced adaptivity in handling visual image transformations. Consequently, the proposed model achieves superior results compared to other models, with minimal image distortion. This is likely due to the minimal angular difference between the generated images. In the future, it is expected to expand the number of viewpoints generated and enhance the model's efficiency in processing images with varying resolutions.
Downloads
References
Kavanagh, Sam, Andrew Luxton-Reilly, Burkhard Wuensche, and Beryl Plimmer. A systematic review of virtual reality in education. Themes in science and technology education, 2017, 10(2): 85-119.
Anthes, Christoph, Rubén Jesús García-Hernández, Markus Wiedemann, and Dieter Kranzlmüller. State of the art of virtual reality technology. In 2016 IEEE aerospace conference, 2016: 1-19.
Wang, Lei, Wei Chen, Wenjia Yang, Fangming Bi, and Fei Richard Yu. A state-of-the-art review on image synthesis with generative adversarial networks. Ieee Access, 2020, 8: 63514-63537.
Seitz, Steven M., and Charles R. Dyer. Physically-valid view synthesis by image interpolation. In Proceedings IEEE Workshop on Representation of Visual Scenes, 1995: 18-25.
De Oliveira, Adriano Q., Thiago LT da Silveira, Marcelo Walter, and Cláudio R. Jung. A hierarchical superpixel-based approach for DIBR view synthesis. IEEE Transactions on Image Processing, 2021, 30: 6408-6419.
GAO, Xuesong, Keqiu Li, Weiqiang Chen, Zhongyao Yang, Wenguo Wei, and Yangang Cai. Free viewpoint video synthesis based on DIBR. In 2020 IEEE Conference on Multimedia Information Processing and Retrieval, 2020: 275-278.
Wiles, Olivia, Georgia Gkioxari, Richard Szeliski, and Justin Johnson. Synsin: End-to-end view synthesis from a single image. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020: 7467-7477.
Tucker, Richard, and Noah Snavely. Single-view view synthesis with multiplane images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 551-560.
Liu, Miaomiao, Xuming He, and Mathieu Salzmann. Geometry-aware deep network for single-image novel view synthesis. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 4616-4624.
Zhu, Jun-Yan, Taesung Park, Phillip Isola, and Alexei A. Efros. Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the IEEE international conference on computer vision, 2017: 2223-2232.
KITTI dataset. URL: https://www.kaggle.com/datasets/klemenko/kitti-dataset. Last Accessed Time: 2024/03/16.
Downloads
Published
Conference Proceedings Volume
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.