Sketch to Photo Conversion using Cycle-Consistent Adversarial Networks
Kommalapati Abhiroop Tejomay1, Kishore Kumar Kamarajugadda2
1Kommalapati Abhiroop Tejomay, Department of ECE, Faculty of Science and Technology, ICFAI Foundation for Higher Education, Hyderabad, India.
2Kishore Kumar Kamarajugadda, Department of ECE, Faculty of Science and Technology, ICFAI Foundation for Higher Education, Hyderabad, India.
Manuscript received on January 12, 2020. | Revised Manuscript received on January 22, 2020. | Manuscript published on February 10, 2020. | PP: 2467-2471 | Volume-9 Issue-4, February 2020. | Retrieval Number: C8866019320/2020©BEIESP | DOI: 10.35940/ijitee.C8866.029420
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: It is proposed to use the cycle-consistent adversarial network as a way to convert images of sketches to images of photos. The network learns to perform the mapping from the domain of sketches to the domain of photos and due to its architecture also learns the inverse mapping from the domain of photos to the domain of sketches. The network converts sketches to photos by reducing a weighted sum of the validity, reconstruction and identity losses. The advantage of using a cycle-consistent adversarial network over other network architectures is that it is not mandatory to have aligned image pairs as its training set and works in an unpaired setting.
Keywords: Cycle-Consistent Adversarial Networks, Image-to-Image Translation, Generative Adversarial Networks, Generator and Discriminator.
Scope of the Article: Image Security