The Unreasonable Effectiveness of Texture Transfer for Single Image Super-Resolution

Gondal, Muhammad Waleed; Schölkopf, Bernhard; Hirsch, Michael

doi:10.1007/978-3-030-11021-5_6

Cited by 27 publications

(20 citation statements)

References 59 publications

(132 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the for proposed SNN model, we are making the given set of datasets into train and test by the general division ratio either 80:20. To test the logic we are going to use 20% of data, and that will be given as input to the network, based on the train data the image is going to be Inpainted the missing pixels [20][21][22].…”

Section: Results and Analysismentioning

confidence: 99%

Image Completion using Spiking Neural Networks

Kumar*,

Sinha,

Solanki

2019

IJITEE

View full text Add to dashboard Cite

In this paper, we are showing how spiking neural networks are applied in image repainting, and its results are outstanding compared with other machine learning techniques. Spiking Neural Networks uses the shape of patterns and shifting distortion on images and positions to retrieve the original picture. Thus, Spiking Neural Networks is one of the advanced generations and third generation of machine learning techniques, and is an extension to the concept of Neural Networks and Convolutional Neural Networks. Spiking Neural Networks (SNN) is biologically plausible, computationally more powerful, and is considerably faster. The proposed algorithm is tested on different sized digital images over which free form masks are applied. The performance of the algorithm is examined to find the PSNR, QF and SSIM. The model has an effective and fast to complete the image by filling the gaps (holes).

show abstract

Section: Results and Analysismentioning

confidence: 99%

Image Completion using Spiking Neural Networks

Kumar*,

Sinha,

Solanki

2019

IJITEE

View full text Add to dashboard Cite

show abstract

“…The higher the PSNR and SSIM, the less noise the image has. In addition, this article also refers to learned perceptual image patch similarity (LPIPS) [45,46], which we describe as Perceptual Similarity. In this paper, CNN features are used to represent the visual perception of images.…”

Section: Evaluation Methodsmentioning

confidence: 99%

Generative Adversarial Network-Based Super-Resolution Considering Quantitative and Perceptual Quality

Wang

Cheng

et al. 2020

Symmetry

View full text Add to dashboard Cite

In recent years, the common algorithms for image super-resolution based on deep learning have been increasingly successful, but there is still a large gap between the results generated by each algorithm and the ground-truth. Even some algorithms that are dedicated to image perception produce more textures that do not exist in the original image, and these artefacts also affect the visual perceptual quality of the image. We believe that in the existing perceptual-based image super-resolution algorithm, it is necessary to consider Super-Resolution (SR) image quality, which can restore the important structural parts of the original picture. This paper mainly improves the Enhanced Super-Resolution Generative Adversarial Networks (ESRGAN) algorithm in the following aspects: adding a shallow network structure, adding the dual attention mechanism in the generator and the discriminator, including the second-order channel mechanism and spatial attention mechanism and optimizing perceptual loss by adding second-order covariance normalization at the end of feature extractor. The results of this paper ensure image perceptual quality while reducing image distortion and artefacts, improving the perceived similarity of images and making the images more in line with human visual perception.

show abstract

“…The neural networks of the generative model and the discriminative model used in this study are similar to those of Edge Connect. In detail, a generative model follows the super-resolution architecture [21,22], and the discriminative model follows a 70 × 70 patch GAN architecture [23,24].…”

Section: Training Ganmentioning

confidence: 99%

Tooth Segmentation of 3D Scan Data Using Generative Adversarial Networks

et al. 2020

View full text Add to dashboard Cite

The use of intraoral scanners in the field of dentistry is increasing. In orthodontics, the process of tooth segmentation and rearrangement provides the orthodontist with insights into the possibilities and limitations of treatment. Although, full-arch scan data, acquired using intraoral scanners, have high dimensional accuracy, they have some limitations. Intraoral scanners use a stereo-vision system, which has difficulties scanning narrow interdental spaces. These areas, with a lack of accurate scan data, are called areas of occlusion. Owing to such occlusions, intraoral scanners often fail to acquire data, making the tooth segmentation process challenging. To solve the above problem, this study proposes a method of reconstructing occluded areas using a generative adversarial network (GAN). First, areas of occlusion are eliminated, and the scanned data are sectioned along the horizontal plane. Next, images are trained using the GAN. Finally, the reconstructed two-dimensional (2D) images are stacked to a three-dimensional (3D) image and merged with the data where the occlusion areas have been removed. Using this method, we obtained an average improvement of 0.004 mm in the tooth segmentation, as verified by the experimental results.

show abstract

The Unreasonable Effectiveness of Texture Transfer for Single Image Super-Resolution

Cited by 27 publications

References 59 publications

Image Completion using Spiking Neural Networks

Image Completion using Spiking Neural Networks

Generative Adversarial Network-Based Super-Resolution Considering Quantitative and Perceptual Quality

Tooth Segmentation of 3D Scan Data Using Generative Adversarial Networks

Contact Info

Product

Resources

About