A Generative Adversarial Network-Based Image Denoiser Controlling Heterogeneous Losses

• Published in: Sensors (Basel, Switzerland) Vol. 21; no. 4; p. 1191
• Main Authors: Cho, Sung In, Park, Jae Hyeon, Kang, Suk-Ju
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 08.02.2021; MDPI
• Subjects: Convolution; convolutional neural network; Deep learning; generative adversarial network; Generative adversarial networks; image denoising; image restoration; Neural networks; Noise; Noise reduction; Optimization; structural loss; Teaching methods; generative adversarial network; structural loss; image restoration; image denoising; convolutional neural network
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s21041191

We propose a novel generative adversarial network (GAN)-based image denoising method that utilizes heterogeneous losses. In order to improve the restoration quality of the structural information of the generator, the heterogeneous losses, including the structural loss in addition to the conventional mean squared error (MSE)-based loss, are used to train the generator. To maximize the improvements brought on by the heterogeneous losses, the strength of the structural loss is adaptively adjusted by the discriminator for each input patch. In addition, a depth wise separable convolution-based module that utilizes the dilated convolution and symmetric skip connection is used for the proposed GAN so as to reduce the computational complexity while providing improved denoising quality compared to the convolutional neural network (CNN) denoiser. The experiments showed that the proposed method improved visual information fidelity and feature similarity index values by up to 0.027 and 0.008, respectively, compared to the existing CNN denoiser.