Image Out painting with GANS
DOI:
https://doi.org//10.32628/CSEIT206354Keywords:
Tensorflow, Deep Learning, CNN, GANS, Neural Networks.Abstract
The difficult task of image out painting (extrapolation) has received relatively very little attention in respect to its cousin, image-inpainting (completion). Consequently, we tend to present a deep learning approach supported [4] for adversarial perceive a network to comprehend past image boundaries. We use a three-phase training schedule to stably train a DCGAN design on a set of the Places365 dataset. In line with [4], we additionally use native discriminators to reinforce the standard of our output. Once trained, our model is ready to out paint 256×256 color images relatively realistically, thus allowing algorithmic out painting. Our results show that deep learning approaches to image out painting are each possible and promising.
References
- M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, G. S. Corrado, A. Davis, J. Dean, M. Devin, S. Ghemawat, I. Goodfellow, A. Harp, G. Irving, M. Isard, Y. Jia, R. Jozefowicz, L. Kaiser, M. Kudlur, J. Levenberg, D. Mane,´ R. Monga, S. Moore, D. Murray, C. Olah, M. Schuster,
- J. Shlens, B. Steiner, I. Sutskever, K. Talwar, P. Tucker, V. Vanhoucke, V. Vasudevan, F. Viegas,´ O. Vinyals, P. Warden, M. Wattenberg, M. Wicke, Y. Yu, and X. Zheng. TensorFlow: Large-scale machine learning on heterogeneous systems, 2015. Software available from tensorflow.org.
- M. Arjovsky, S. Chintala, and L. Bottou. Wasserstein gan. arXiv preprint arXiv:1701.07875, 2017. 5
- L. A. Gatys, A. S. Ecker, and M. Bethge. A neural algorithm of artistic style. arXiv preprint arXiv:1508.06576, 2015. 1, 5
- 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
- Itseez. Open source computer vision library. https:// github.com/itseez/opencv, 2015.
- 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
- 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
- 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.
- B. Zhou, A. Lapedriza, A. Khosla, A. Oliva, and A. Torralba. Places: A 10 million image database for scene recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017.
Downloads
Published
Issue
Section
License
Copyright (c) IJSRCSEIT
This work is licensed under a Creative Commons Attribution 4.0 International License.