Open Access
ARTICLE
Incomplete Image Completion through GAN
Biying Deng1
, Desheng Zheng1, *, Zhifeng Liu1
, Yanling Lai1, Zhihong Zhang2
1 School of Computer Science, Southwest Petroleum University, Chengdu, 610000, China
2 AECC Sichuan Gas Turbine Establishment, Mianyang, 621700, China
* Corresponding Author:Desheng Zheng. Email:
Journal of Quantum Computing 2021, 3(3), 119-126. https://doi.org/10.32604/jqc.2021.017250
Received 03 July 2021; Accepted 29 August 2021; Issue published 21 December 2021
Abstract
There are two difficult in the existing image restoration methods. One
is that the method is difficult to repair the image with a large damaged, the other
is the result of image completion is not good and the speed is slow. With the
development and application of deep learning, the image repair algorithm based
on generative adversarial networks can repair images by simulating the
distribution of data. In the process of image completion, the first step is trained the
generator to simulate data distribution and generate samples. Then a large number
of falsified images are quickly generated using the generative adversarial network
and search for the code of the closest damaged image. Finally, the generator
generates missing content by using this code. On this basis, this paper combines
the semantic loss function and the perceptual loss function. Experimental result
show that the method successfully predicts the information of large areas missing
in the image, and realizes the photorealism, producing clearer and more consistent
results than previous methods.
Keywords
Cite This Article
B. Deng, D. Zheng, Z. Liu, Y. Lai and Z. Zhang, "Incomplete image completion through gan,"
Journal of Quantum Computing, vol. 3, no.3, pp. 119–126, 2021.