TY - JOUR
T1 - Channel Attention GAN Trained with Enhanced Dataset for Single-Image Shadow Removal
AU - Abiko, Ryo
AU - Ikehara, Masaaki
N1 - Publisher Copyright:
© 2013 IEEE.
PY - 2022
Y1 - 2022
N2 - Even today, where many deep-learning-based methods have been published, single-image shadow removal is a challenging task to achieve high accuracy. This is because the shadow changes depending on various conditions such as the target material or the light source, and it is difficult to estimate all the physical parameters. In this paper, we propose a new single-image shadow removal method (Channel Attention GAN: CANet) using two networks for detecting shadows and removing shadows. Intensity change in shadowed regions has different characteristics depending on the wavelength of light. In addition, the image acquisition system of the camera acquires an image in a state where the RGB values influence each other. Therefore, our method focused on the physical properties of shadows and the camera's image acquisition system. The proposed network has a structure considering the relationship between color channels. When training this network, we modified the color and added some artifacts to the training images in order to make the training dataset more complex. These image processing are based on the shadow model, considering the camera image acquisition system. With these new proposals, our method can remove shadows in all ISTD, ISTD+, SRD, and SRD+ datasets with higher accuracy than the state-of-the-art methods. The code is available on GitHub: https://github.com/ryo-abiko/CANet.
AB - Even today, where many deep-learning-based methods have been published, single-image shadow removal is a challenging task to achieve high accuracy. This is because the shadow changes depending on various conditions such as the target material or the light source, and it is difficult to estimate all the physical parameters. In this paper, we propose a new single-image shadow removal method (Channel Attention GAN: CANet) using two networks for detecting shadows and removing shadows. Intensity change in shadowed regions has different characteristics depending on the wavelength of light. In addition, the image acquisition system of the camera acquires an image in a state where the RGB values influence each other. Therefore, our method focused on the physical properties of shadows and the camera's image acquisition system. The proposed network has a structure considering the relationship between color channels. When training this network, we modified the color and added some artifacts to the training images in order to make the training dataset more complex. These image processing are based on the shadow model, considering the camera image acquisition system. With these new proposals, our method can remove shadows in all ISTD, ISTD+, SRD, and SRD+ datasets with higher accuracy than the state-of-the-art methods. The code is available on GitHub: https://github.com/ryo-abiko/CANet.
KW - Image restoration
KW - deep learning
KW - generative adversarial networks
KW - shadow removal
UR - http://www.scopus.com/inward/record.url?scp=85124087885&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85124087885&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2022.3147063
DO - 10.1109/ACCESS.2022.3147063
M3 - Article
AN - SCOPUS:85124087885
SN - 2169-3536
VL - 10
SP - 12322
EP - 12333
JO - IEEE Access
JF - IEEE Access
ER -