Single Image Reflection Removal via the Spatially Adaptive Conditional Generative Adversarial Network 


Vol. 46,  No. 3, pp. 459-465, Mar.  2021
10.7840/kics.2021.46.3.459


PDF
  Abstract

Reflection removal on a single-image has been a significant problem in image processing and computer vision. To solve this problem, the proposed algorithm defines single-image reflection removal as an image-to-image translation problem. In image-to-image translation, the conditional generative adversarial network (CGAN) achieves remarkable performance in various applications. Therefore, the proposed algorithm is based on CGAN with spatially adaptive de-normalization (SPADE), which solves the wash-away problem due to normalization layers. In the experimental results, the proposed algorithm shows better performance than the conventional methods.

  Statistics
Cumulative Counts from November, 2022
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

[IEEE Style]

T. Kim, J. Yoon, Y. Choe, "Single Image Reflection Removal via the Spatially Adaptive Conditional Generative Adversarial Network," The Journal of Korean Institute of Communications and Information Sciences, vol. 46, no. 3, pp. 459-465, 2021. DOI: 10.7840/kics.2021.46.3.459.

[ACM Style]

Taehyeon Kim, Jongsu Yoon, and Yoonsik Choe. 2021. Single Image Reflection Removal via the Spatially Adaptive Conditional Generative Adversarial Network. The Journal of Korean Institute of Communications and Information Sciences, 46, 3, (2021), 459-465. DOI: 10.7840/kics.2021.46.3.459.

[KICS Style]

Taehyeon Kim, Jongsu Yoon, Yoonsik Choe, "Single Image Reflection Removal via the Spatially Adaptive Conditional Generative Adversarial Network," The Journal of Korean Institute of Communications and Information Sciences, vol. 46, no. 3, pp. 459-465, 3. 2021. (https://doi.org/10.7840/kics.2021.46.3.459)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880