Outpainting Images and Videos using GANs

© 2020 by IJCTT Journal
Volume-68 Issue-5
Year of Publication : 2020
Authors : Shailendra Singh, Nainish Aggarwal, Udit Jain, Hrithik Jaiswal
DOI :  10.14445/22312803/IJCTT-V68I5P107

How to Cite?

Shailendra Singh, Nainish Aggarwal, Udit Jain, Hrithik Jaiswal, "Outpainting Images and Videos using GANs," International Journal of Computer Trends and Technology, vol. 68, no. 5, pp. 24-29, 2020. Crossref, https://doi.org/10.14445/22312803/IJCTT-V68I5P107

This Outpainting paper studies the main fundamental issue of extrapolation of images or visual context like videos using deep generative models such as GANs (Generative Adversarial Networks), i.e., extending image and video borders with plausible structure and details. In addition, this seemingly simple job faces several critical technical challenges and has its unique properties. The challenging task of image and video outpainting (extrapolation) in comparison to it’s relative, inpainting (completion), received relatively little attention. So, we followed a deep learning adversarially approach which is based on training a network. The two main problems are the extension of scale and one side constraints. Extensive studies are carried out on various possible alternatives and methods connected with them. We are also exploring our method`s potential for various interesting applications that may support work in a variety of fields.

image processing, video processing, generative adversarial networks, extrapolation, outpainting.

[1] M. Arjovsky, S. Chintala, and L. Bottou. Wasserstein gan. arXiv preprint arXiv:1701.07875, 2017. 5
[2] L. A. Gatys, A. S. Ecker, and M. Bethge. A neural algorithm of artistic style. arXiv preprint arXiv:1508.06576, 2015. 1, 5
[3] S. Iizuka, E. Simo-Serra, and H. Ishikawa. Globally and locally consistent image completion. ACM Transactions on Graphics (TOG), 36(4):107, 2017. 1, 2, 3
[4] Itseez. Open source computer vision library https://github.com/opencv/opencv , 2015.
[5] G. Liu, F. A. Reda, K. J. Shih, T.-C. Wang, A. Tao, and B. Catanzaro. Image inpainting for irregular holes using partial convolutions. arXiv preprint arXiv:1804.07723, 2018. 1, 5
[6] D. Pathak, P. Krahenbuhl, J. Donahue, T. Darrell, and A. A. Efros. Context encoders: Feature learning by inpainting. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 2536–2544, 2016. 1
[7] M. Wang, Y. Lai, Y. Liang, R. R. Martin, and S.-M. Hu. Biggerpicture: data-driven image extrapolation using graph matching. ACM Transactions on Graphics, 33(6), 2014. 1
[8] Saito, Masaki, Eiichi Matsumoto, and Shunta Saito.” Temporal generative adversarial nets with singular value clipping.” IEEE International Conference on Computer Vision (ICCV). Vol. 2. No. 3. 2017.
[9] Salimans, Tim, et al.” Improved techniques for training gans.” Advances in Neural Information Processing Systems. 2016.
[10] Suresh Prasad Kannojia, Gaurav Jaiswal “Effects of Varying Resolution on Performance of CNN based Image Classification: An Experimental Study” IJCSE Vol.-6, Issue-9, Sept. 2018.
[11] Sharmila Shaik , Sudhakar P , Shaik Khaja Mohiddin. "A Novel Framework for Image Inpainting". International Journal of Computer Trends and Technology (IJCTT) V14(3):141-147, Aug 2014. ISSN:2231-2803. www.ijcttjournal.org.
[12] Kshitij Tripathi, Rajendra G. Vyas, Anil K. Gupta “Deep Learning through Convolutional Neural Networks for Classification of Image: A Novel Approach Using Hyper Filter”. IJCSE Vol.-7, Issue-6, June 2019. https://www.ijcseonline.org/
[13] Charu Khare, Kapil Kumar Nagwanshi “Implementation and Analysis of Image Restoration Techniques”. IJCTT - May to June Issue 2011.
[14] Finn, Chelsea, Ian Goodfellow, and Sergey Levine.” Unsupervised learning for physical interaction through video prediction.” Advances in neural information processing systems. 2016.
[15] S. M. Chavda1, M. M. Goyani “Recent evaluation on Content Based Image Retrieval” IJCSE Vol.-7, Issue-4, April 2019 E-ISSN: 2347-2693.
[16] Nazgol Hor, Shervan Fekri-Ershad “Image retrieval approach based on local texture information derived from predefined patterns and spatial domain information” IJCSE. ISSN: 2319-7323 Vol. 8 No.06 Nov-Dec 2019.