Image shadow removal using cycle generative adversarial networks

Shen-Chuan Tai; Peng-Yu Chen; Xin-An Jiang

doi:10.1117/1.JEI.28.1.013034

13 February 2019 Image shadow removal using cycle generative adversarial networks

Shen-Chuan Tai, Peng-Yu Chen, Xin-An Jiang

Author Affiliations +

Journal of Electronic Imaging, Vol. 28, Issue 1, 013034 (February 2019). https://doi.org/10.1117/1.JEI.28.1.013034

Abstract

A shadow-removal algorithm based on cycle generative adversarial network is proposed. There are two networks in the proposed method. To increase the diversity of shadow images for improving the robustness in the shadow-removal process, the first network is used to add shadows in nonshadow images to increase the variation of training data. Then, the second network is trained for the shadow-removal task. Six different losses are calculated and combined in the loss function to increase the performance. Ablation experiments show that the resulting images suffer from some artifacts without any of the six losses in the loss function. The proposed method presents lower value of root-mean-squared error and the superior visual quality compared to the state-of-the-art image removal algorithms.

Citation Download Citation

Shen-Chuan Tai, Peng-Yu Chen, and Xin-An Jiang "Image shadow removal using cycle generative adversarial networks," Journal of Electronic Imaging 28(1), 013034 (13 February 2019). https://doi.org/10.1117/1.JEI.28.1.013034

Received: 15 November 2018; Accepted: 29 January 2019; Published: 13 February 2019

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available