Deep Generative Adversarial Networks for Image-to-Image Translation: A Review

Alotaibi, Aziz

doi:10.3390/sym12101705

Cited by 92 publications

(57 citation statements)

References 82 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both networks are then trained simultaneously, with the generator trying to create data which can fool the discriminator and the discriminator attempting to identify fake data (Goodfellow et al ., 2014). As GANs calculate the joint probability distribution, compared to a convolutional neural network (CNN) which maps an input to a class label, GAN may be more suited for image‐to‐image translation tasks such as seismic event separation (Alotaibi, 2020). Additionally, GANs can perform well with a lack of data and are thus more suitable when data availability may be an issue (Han et al ., 2019).…”

Section: Methodsmentioning

confidence: 99%

Pre‐migration diffraction separation using generative adversarial networks

Lowney

Lokmer

O’Brien

et al. 2021

Geophysical Prospecting

View full text Add to dashboard Cite

Diffraction imaging is the process of separating diffraction events from the seismic wavefield and imaging them independently, highlighting subsurface discontinuities. While there are many analytic‐based methods for diffraction imaging which use kinematic, dynamic or both, properties of the diffracted wavefield, they can be slow and require parameterization. Here, we propose an image‐to‐image generative adversarial network to automatically separate diffraction events on pre‐migrated seismic data in a fraction of the time of conventional methods. To train the generative adversarial network, plane‐wave destruction was applied to a range of synthetic and real images from field data to create training data. These training data were screened and any areas where the plane‐wave destruction did not perform well, such as synclines and areas of complex dip, were removed to prevent bias in the neural network. A total of 14,132 screened images were used to train the final generative adversarial network. The trained network has been applied across several geologically distinct field datasets, including a 3D example. Here, generative adversarial network separation is shown to be comparable to a benchmark separation created with plane‐wave destruction, and up to 12 times faster. This demonstrates the clear potential in generative adversarial networks for fast and accurate diffraction separation.

show abstract

Section: Methodsmentioning

confidence: 99%

Pre‐migration diffraction separation using generative adversarial networks

Lowney

Lokmer

O’Brien

et al. 2021

Geophysical Prospecting

View full text Add to dashboard Cite

show abstract

“…i.e., the discriminator cannot distinguish between the correctly generated data and real data. Benefiting from its strong generating ability, the GAN has also been employed in style transfer [14].…”

Section: Related Workmentioning

confidence: 99%

Image-to-Image Style Transfer Based on the Ghost Module

Jiang¹,

Jia²,

Zhang³

et al. 2021

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

The technology for image-to-image style transfer (a prevalent image processing task) has developed rapidly. The purpose of style transfer is to extract a texture from the source image domain and transfer it to the target image domain using a deep neural network. However, the existing methods typically have a large computational cost. To achieve efficient style transfer, we introduce a novel Ghost module into the GANILLA architecture to produce more feature maps from cheap operations. Then we utilize an attention mechanism to transform images with various styles. We optimize the original generative adversarial network (GAN) by using more efficient calculation methods for image-to-illustration translation. The experimental results show that our proposed method is similar to human vision and still maintains the quality of the image. Moreover, our proposed method overcomes the high computational cost and high computational resource consumption for style transfer. By comparing the results of subjective and objective evaluation indicators, our proposed method has shown superior performance over existing methods.

show abstract

“…The traditional generative models operate with diverse forms of probability density functions approximating the distribution. Infinite Gaussian mixture models [36], hidden Markov models [37], and hidden naive Bayes models [38] are not capable to learn complicated distributions [39]. In contrast, the deep generative models use such methods as stochastic backpropagation, deep neural networks, and approximate of Bayesian inference for producing new samples from variational distributions in large-scale datasets.…”

Section: Deep Generative Modelsmentioning

confidence: 99%

Virtual sawing using generative adversarial networks

Daniel

Zolotarev

Eerola

et al. 2021

2021 36th International Conference on Image and Vision Computing New Zealand (IVCNZ)

View full text Add to dashboard Cite

The global trend towards digitalization along with the 4th Industrial Revolution allows building new innovative solutions to optimize manufacturing. In particular, the highly competitive sawmill industry is not an exception. The industry always depends on efficient raw material utilization, and thus, exploration of the internal log structure is an important feature in the timber conversion process. One common approach for a comprehensive internal wood structure examination is virtual sawing that is predicting the outcome of sawing process based on log measurements. The main objective of this thesis was to study the suitability of state-of-the-art generative adversarial networks for virtual sawing. The specific aims were to choose an appropriate generative adversarial network architecture to build a trainable model as an extension to an existing virtual sawing system. The proposed method for image-to-image translation is capable to synthesize the photorealistic images of the boards based on log measurements. The defects (knots) on virtual boards were detectable and their locations correspond to those in real boards. PREFACEI would like to thank Heikki Kälviäinen, Lasse Lensu, Tuomas Eerola, and Fedor Zolotarev for sharing their immense knowledge and precious time with me. I am also grateful to my family, relatives, and friends for tremendous support during the studies.

show abstract

Deep Generative Adversarial Networks for Image-to-Image Translation: A Review

Cited by 92 publications

References 82 publications

Pre‐migration diffraction separation using generative adversarial networks

Pre‐migration diffraction separation using generative adversarial networks

Image-to-Image Style Transfer Based on the Ghost Module

Virtual sawing using generative adversarial networks

Contact Info

Product

Resources

About