• Journal of Internet Computing and Services
    ISSN 2287 - 1136(Online) / ISSN 1598 - 0170 (Print)
    http://jics.or.kr/

GAN-based shadow removal using context information


Hee-jin Yoon, Kang-jik Kim, Jun-chul Chun, Journal of Internet Computing and Services, Vol. 20, No. 6, pp. 29-36, Dec. 2019
0.7472/jksii.2019.20.6.29, Full Text:
Keywords: Shadow removal, Generative Adversarial Network, deep-learning

Abstract

When dealing with outdoor images in a variety of computer vision applications, the presence of shadow degrades performance. In order to understand the information occluded by shadow, it is essential to remove the shadow. To solve this problem, in many studies, involves a two-step process of shadow detection and removal. However, the field of shadow detection based on CNN has greatly improved, but the field of shadow removal has been difficult because it needs to be restored after removing the shadow. In this paper, it is assumed that shadow is detected, and shadow-less image is generated by using original image and shadow mask. In previous methods, based on CGAN, the image created by the generator was learned from only the aspect of the image patch in the adversarial learning through the discriminator. In the contrast, we propose a novel method using a discriminator that judges both the whole image and the local patch at the same time. We not only use the residual generator to produce high quality images, but we also use joint loss, which combines reconstruction loss and GAN loss for training stability. To evaluate our approach, we used an ISTD datasets consisting of a single image. The images generated by our approach show sharp and restored detailed information compared to previous methods.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from November 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[APA Style]
Hee-jin Yoon, Kang-jik Kim, & Jun-chul Chun (2019). GAN-based shadow removal using context information. Journal of Internet Computing and Services, 20(6), 29-36. DOI: 0.7472/jksii.2019.20.6.29.

[IEEE Style]
H. Yoon, K. Kim and J. Chun, "GAN-based shadow removal using context information," Journal of Internet Computing and Services, vol. 20, no. 6, pp. 29-36, 2019. DOI: 0.7472/jksii.2019.20.6.29.

[ACM Style]
Hee-jin Yoon, Kang-jik Kim, and Jun-chul Chun. 2019. GAN-based shadow removal using context information. Journal of Internet Computing and Services, 20, 6, (2019), 29-36. DOI: 0.7472/jksii.2019.20.6.29.