Open AccessSketch to Photo Conversion using Cycle-Consistent Adversarial Networks
Author(s) -
Kommalapati Abhiroop Tejomay*,
K. Kishore Kumar
Publication year - 2020
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.c8866.029420
Subject(s) - sketch , adversarial system , computer science , domain (mathematical analysis) , set (abstract data type) , artificial intelligence , image (mathematics) , network architecture , architecture , identity (music) , computer vision , algorithm , mathematics , art , computer security , mathematical analysis , visual arts , programming language , aesthetics
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