scholarly journals Single Image De-Raining via Improved Generative Adversarial Nets

Sensors ◽  
2020 ◽  
Vol 20 (6) ◽  
pp. 1591 ◽  
Author(s):  
Yi Ren ◽  
Mengzhen Nie ◽  
Shichao Li ◽  
Chuankun Li
Keyword(s):  
State Of The Art ◽  
Visual Quality ◽  
Divide And Conquer ◽  
Single Image ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Subjective Measurements ◽  
Synthetic Datasets ◽  
Location Map ◽  
Rainy Days

Capturing images under rainy days degrades image visual quality and affects analysis tasks, such as object detection and classification. Therefore, image de-raining has attracted a lot of attention in recent years. In this paper, an improved generative adversarial network for single image de-raining is proposed. According to the principles of divide-and-conquer, we divide an image de-raining task into rain locating, rain removing, and detail refining sub-tasks. A multi-stream DenseNet, termed as Rain Estimation Network, is proposed to estimate the rain location map. A Generative Adversarial Network is proposed to remove the rain streaks. A Refinement Network is proposed to refine the details. These three models accomplish rain locating, rain removing, and detail refining sub-tasks, respectively. Experiments on two synthetic datasets and real world images demonstrate that the proposed method outperforms state-of-the-art de-raining studies in both objective and subjective measurements.

scholarly journals Disentangled generative adversarial network for low-dose CT

2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Wenchao Du ◽  
Hu Chen ◽  
Hongyu Yang ◽  
Yi Zhang
Keyword(s):  
Network Architecture ◽  
Low Dose ◽  
Noise Suppression ◽  
State Of The Art ◽  
Visual Quality ◽  
Ct Images ◽  
Generative Adversarial Network ◽  
Low Dose Ct ◽  
Adversarial Network ◽  
Suppression Method

AbstractGenerative adversarial network (GAN) has been applied for low-dose CT images to predict normal-dose CT images. However, the undesired artifacts and details bring uncertainty to the clinical diagnosis. In order to improve the visual quality while suppressing the noise, in this paper, we mainly studied the two key components of deep learning based low-dose CT (LDCT) restoration models—network architecture and adversarial loss, and proposed a disentangled noise suppression method based on GAN (DNSGAN) for LDCT. Specifically, a generator network, which contains the noise suppression and structure recovery modules, is proposed. Furthermore, a multi-scaled relativistic adversarial loss is introduced to preserve the finer structures of generated images. Experiments on simulated and real LDCT datasets show that the proposed method can effectively remove noise while recovering finer details and provide better visual perception than other state-of-the-art methods.

scholarly journals DR-Net: A Novel Generative Adversarial Network for Single Image Deraining

2018 ◽  
Vol 2018 ◽  
pp. 1-14 ◽  
Author(s):  
Chen Li ◽  
Yecai Guo ◽  
Qi Liu ◽  
Xiaodong Liu
Keyword(s):  
Spatial Information ◽  
State Of The Art ◽  
Single Image ◽  
Close Attention ◽  
Blurred Vision ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Rainy Weather ◽  
Rain Drops ◽  
Outdoor Vision

Blurred vision images caused by rainy weather can negatively influence the performance of outdoor vision systems. Therefore, it is necessary to remove rain streaks from single image. In this work, a multiscale generative adversarial network- (GAN-) based model is presented, called DR-Net, for single image deraining. The proposed architecture includes two subnetworks, i.e., generator subnetwork and discriminator subnetwork. We introduce a multiscale generator subnetwork which contains two convolution branches with different kernel sizes, where the smaller one captures the local rain drops information, and the larger one pays close attention to the spatial information. The discriminator subnetwork acts as a supervision signal to promote the generator subnetwork to generate more quality derained image. It is demonstrated that the proposed method yields in relatively higher performance in comparison to other state-of-the-art deraining models in terms of derained image quality and computing efficiency.

scholarly journals TWIST-GAN: Towards Wavelet Transform and Transferred GAN for Spatio-Temporal Single Image Super Resolution

2021 ◽  
Vol 12 (6) ◽  
pp. 1-20
Author(s):  
Fayaz Ali Dharejo ◽  
Farah Deeba ◽  
Yuanchun Zhou ◽  
Bhagwan Das ◽  
Munsif Ali Jatoi ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Super Resolution ◽  
Generative Adversarial Networks ◽  
Single Image ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Image Super Resolution ◽  
Spatio Temporal ◽  
Single Image Super Resolution

Single Image Super-resolution (SISR) produces high-resolution images with fine spatial resolutions from a remotely sensed image with low spatial resolution. Recently, deep learning and generative adversarial networks (GANs) have made breakthroughs for the challenging task of single image super-resolution (SISR) . However, the generated image still suffers from undesirable artifacts such as the absence of texture-feature representation and high-frequency information. We propose a frequency domain-based spatio-temporal remote sensing single image super-resolution technique to reconstruct the HR image combined with generative adversarial networks (GANs) on various frequency bands (TWIST-GAN). We have introduced a new method incorporating Wavelet Transform (WT) characteristics and transferred generative adversarial network. The LR image has been split into various frequency bands by using the WT, whereas the transfer generative adversarial network predicts high-frequency components via a proposed architecture. Finally, the inverse transfer of wavelets produces a reconstructed image with super-resolution. The model is first trained on an external DIV2 K dataset and validated with the UC Merced Landsat remote sensing dataset and Set14 with each image size of 256 × 256. Following that, transferred GANs are used to process spatio-temporal remote sensing images in order to minimize computation cost differences and improve texture information. The findings are compared qualitatively and qualitatively with the current state-of-art approaches. In addition, we saved about 43% of the GPU memory during training and accelerated the execution of our simplified version by eliminating batch normalization layers.

scholarly journals Learning a Generative Model for Fusing Infrared and Visible Images via Conditional Generative Adversarial Network with Dual Discriminators

2019 ◽  
Author(s):  
Han Xu ◽  
Pengwei Liang ◽  
Wei Yu ◽  
Junjun Jiang ◽  
Jiayi Ma
Keyword(s):  
Probability Distribution ◽  
State Of The Art ◽  
Infrared Image ◽  
Infrared Images ◽  
Generative Adversarial Network ◽  
Visible Image ◽  
Qualitative And Quantitative ◽  
Adversarial Network ◽  
Fused Image ◽  
Visible Images

In this paper, we propose a new end-to-end model, called dual-discriminator conditional generative adversarial network (DDcGAN), for fusing infrared and visible images of different resolutions. Unlike the pixel-level methods and existing deep learning-based methods, the fusion task is accomplished through the adversarial process between a generator and two discriminators, in addition to the specially designed content loss. The generator is trained to generate real-like fused images to fool discriminators. The two discriminators are trained to calculate the JS divergence between the probability distribution of downsampled fused images and infrared images, and the JS divergence between the probability distribution of gradients of fused images and gradients of visible images, respectively. Thus, the fused images can compensate for the features that are not constrained by the single content loss. Consequently, the prominence of thermal targets in the infrared image and the texture details in the visible image can be preserved or even enhanced in the fused image simultaneously. Moreover, by constraining and distinguishing between the downsampled fused image and the low-resolution infrared image, DDcGAN can be preferably applied to the fusion of different resolution images. Qualitative and quantitative experiments on publicly available datasets demonstrate the superiority of our method over the state-of-the-art.

scholarly journals Selective Feature Anonymization for Privacy-Preserving Image Data Publishing

Electronics ◽  
2020 ◽  
Vol 9 (5) ◽  
pp. 874
Author(s):  
Taehoon Kim ◽  
Jihoon Yang
Keyword(s):  
Image Data ◽  
Privacy Preserving ◽  
Data Publishing ◽  
Strong Positive Correlation ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Public Data ◽  
Synthetic Datasets ◽  
Independent Features ◽  
Original Class

There is a strong positive correlation between the development of deep learning and the amount of public data available. Not all data can be released in their raw form because of the risk to the privacy of the related individuals. The main objective of privacy-preserving data publication is to anonymize the data while maintaining their utility. In this paper, we propose a privacy-preserving semi-generative adversarial network (PPSGAN) that selectively adds noise to class-independent features of each image to enable the processed image to maintain its original class label. Our experiments on training classifiers with synthetic datasets anonymized with various methods confirm that PPSGAN shows better utility than other conventional methods, including blurring, noise-adding, filtering, and generation using GANs.

Sign in / Sign up

Export Citation Format

Share Document