Image Denoising Using A Generative Adversarial Network

Alsaiari, Abeer; Rustagi, Ridhi; Alhakamy, A’aeshah; Thomas, Manu Mathew; Forbes, Angus G.

doi:10.1109/infoct.2019.8710893

Cited by 43 publications

(26 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e whole process is shown in e output images from G and the ground truth images are then inserted into D. e parameters of G are optimized according to the output of D. We designed the architectures for G and D and trained the database through an end-to-end trainable neural network. In addition, the algorithm combined the adversarial loss, pixel loss, and feature loss to design the generator loss function in order to further improve the network performance [35]. In the following, we give a detailed introduction to different parts of the network.…”

Section: The Proposed Methodsmentioning

confidence: 99%

Image Demosaicing Based on Generative Adversarial Network

Luo

Wang

2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Digital cameras with a single sensor use a color filter array (CFA) that captures only one color component in each pixel. Therefore, noise and artifacts will be generated when reconstructing the color image, which reduces the resolution of the image. In this paper, we proposed an image demosaicing method based on generative adversarial network (GAN) to obtain high-quality color images. The proposed network does not need any initial interpolation process in the data preparation phase, which can greatly reduce the computational complexity. The generator of the GAN is designed using the U-net to directly generate the demosaicing images. The dense residual network is used for the discriminator to improve the discriminant ability of the network. We compared the proposed method with several interpolation-based algorithms and the DnCNN. Results from the comparative experiments proved that the proposed method can more effectively eliminate the image artifacts and can better recover the color image.

show abstract

Section: The Proposed Methodsmentioning

confidence: 99%

Image Demosaicing Based on Generative Adversarial Network

Luo

Wang

2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…In addition, they adapt a feature modulation method to encode auxiliary features that allow features to better take effect at the pixel level, leading to fine-grained denoising results. Another GANbased denoising method also considers denoising rendered images from a dataset containing 40 Pixar movie image frames with added Gaussian noise [24]. Because the network does not take auxiliary features as input, it can also denoise noisy photographs under natural light and CT scans.…”

Section: Radiance Predictionmentioning

confidence: 99%

A survey on deep learning-based Monte Carlo denoising

Huo

Yoon

2021

Comp. Visual Media

View full text Add to dashboard Cite

Monte Carlo (MC) integration is used ubiquitously in realistic image synthesis because of its flexibility and generality. However, the integration has to balance estimator bias and variance, which causes visually distracting noise with low sample counts. Existing solutions fall into two categories, in-process sampling schemes and post-processing reconstruction schemes. This report summarizes recent trends in the post-processing reconstruction scheme. Recent years have seen increasing attention and significant progress in denoising MC rendering with deep learning, by training neural networks to reconstruct denoised rendering results from sparse MC samples. Many of these techniques show promising results in real-world applications, and this report aims to provide an assessment of these approaches for practitioners and researchers.

show abstract

“…The GAN does not rely on the explicit computation of probability densities and is thus suitable for a wider range of applications. Presently this approach has been applied to problems from many domains: ranging from generating musical notes [18], to natural language [19], to medical data [20], [21], to natural scenes [13] and image denoising [22]. The adversarial approach has also been successfully applied to anomaly detection tasks for industrial [23] and medical [24] applications.…”

Section: Previous Workmentioning

confidence: 99%

High Energy Physics Calorimeter Detector Simulation Using Generative Adversarial Networks With Domain Related Constraints

et al. 2021

View full text Add to dashboard Cite

Generative Adversarial Networks (GANs) have gained notoriety by generating highly realistic images. The present work explores GAN for simulating High Energy Physics detectors, interpreting detector output as three-dimensional images. The demands and requirements of a scientific simulation are quite stringent, as compared to the domain of visual images. Image characteristics such as pixel intensity and sparsity, for example, have very different distributions. Moreover, detector simulation requires conditioning on physics inputs, and domain knowledge becomes essential. We, therefore, adjust the pre-processing and incorporate physics-based constraints in the loss function. We also introduce a multi-step training process based on transfer learning by breaking up the task complexity. Validation of the results primarily consists of a detailed comparison to full Monte Carlo in terms of several physics quantities where a high level of agreement is found (ranging from a few percent up to 10% across a large particle energy range). In addition, we assess the performance by physics unrelated metrics, thereby proving further the variability and pertinence through diverse standpoints. We have demonstrated that an image generation technique from vision can successfully simulate highly complex physics processes while achieving a speedup of more than three orders of magnitude in comparison to the standard Monte Carlo.INDEX TERMS 3D vision, generative adversarial networks, high energy physics, fast simulation, image processing and generation, transfer learning.

show abstract

Image Denoising Using A Generative Adversarial Network

Abstract: Figure 1. Gaussian noise image (left), our denoised image (middle) and ground truth photorealistic image (right).

Cited by 43 publications

References 9 publications

Image Demosaicing Based on Generative Adversarial Network

Image Demosaicing Based on Generative Adversarial Network

A survey on deep learning-based Monte Carlo denoising

High Energy Physics Calorimeter Detector Simulation Using Generative Adversarial Networks With Domain Related Constraints

Contact Info

Product

Resources

About