This page has only limited features, please log in for full access.
Image denoising is a challenging task that is essential in numerous computer vision and image processing problems. This study proposes and applies a generative adversarial network-based image denoising training architecture to multiple-level Gaussian image denoising tasks. Convolutional neural network-based denoising approaches come across a blurriness issue that produces denoised images blurry on texture details. To resolve the blurriness issue, we first performed a theoretical study of the cause of the problem. Subsequently, we proposed an adversarial Gaussian denoiser network, which uses the generative adversarial network-based adversarial learning process for image denoising tasks. This framework resolves the blurriness problem by encouraging the denoiser network to find the distribution of sharp noise-free images instead of blurry images. Experimental results demonstrate that the proposed framework can effectively resolve the blurriness problem and achieve significant denoising efficiency than the state-of-the-art denoising methods.
Aamir Khan; Weidong Jin; Amir Haider; Muhibur Rahman; Desheng Wang. Adversarial Gaussian Denoiser for Multiple-Level Image Denoising. Sensors 2021, 21, 2998 .
AMA StyleAamir Khan, Weidong Jin, Amir Haider, Muhibur Rahman, Desheng Wang. Adversarial Gaussian Denoiser for Multiple-Level Image Denoising. Sensors. 2021; 21 (9):2998.
Chicago/Turabian StyleAamir Khan; Weidong Jin; Amir Haider; Muhibur Rahman; Desheng Wang. 2021. "Adversarial Gaussian Denoiser for Multiple-Level Image Denoising." Sensors 21, no. 9: 2998.
Image-to-image conversion based on deep learning techniques is a topic of interest in the fields of robotics and computer vision. A series of typical tasks, such as applying semantic labels to building photos, edges to photos, and raining to de-raining, can be seen as paired image-to-image conversion problems. In such problems, the image generation network learns from the information in the form of input images. The input images and the corresponding targeted images must share the same basic structure to perfectly generate target-oriented output images. However, the shared basic structure between paired images is not as ideal as assumed, which can significantly affect the output of the generating model. Therefore, we propose a novel Input-Perceptual and Reconstruction Adversarial Network (IP-RAN) as an all-purpose framework for imperfect paired image-to-image conversion problems. We demonstrate, through the experimental results, that our IP-RAN method significantly outperforms the current state-of-the-art techniques.
Aamir Khan; Weidong Jin; Muqeet Ahmad; Rizwan Ali Naqvi; Desheng Wang. An Input-Perceptual Reconstruction Adversarial Network for Paired Image-to-Image Conversion. Sensors 2020, 20, 4161 .
AMA StyleAamir Khan, Weidong Jin, Muqeet Ahmad, Rizwan Ali Naqvi, Desheng Wang. An Input-Perceptual Reconstruction Adversarial Network for Paired Image-to-Image Conversion. Sensors. 2020; 20 (15):4161.
Chicago/Turabian StyleAamir Khan; Weidong Jin; Muqeet Ahmad; Rizwan Ali Naqvi; Desheng Wang. 2020. "An Input-Perceptual Reconstruction Adversarial Network for Paired Image-to-Image Conversion." Sensors 20, no. 15: 4161.