scholarly journals iSeeBetter: Spatio-temporal video super-resolution using recurrent generative back-projection networks

2020 ◽  
Vol 6 (3) ◽  
pp. 307-317
Author(s):  
Aman Chadha ◽  
John Britto ◽  
M. Mani Roja
Keyword(s):  
Mean Squared Error ◽  
Signal To Noise Ratio ◽  
Super Resolution ◽  
Structural Similarity ◽  
Generative Adversarial Networks ◽  
Video Frame ◽  
Perceptual Quality ◽  
Back Projection ◽  
Generative Adversarial Network ◽  
Spatio Temporal

Abstract Recently, learning-based models have enhanced the performance of single-image super-resolution (SISR). However, applying SISR successively to each video frame leads to a lack of temporal coherency. Convolutional neural networks (CNNs) outperform traditional approaches in terms of image quality metrics such as peak signal to noise ratio (PSNR) and structural similarity (SSIM). On the other hand, generative adversarial networks (GANs) offer a competitive advantage by being able to mitigate the issue of a lack of finer texture details, usually seen with CNNs when super-resolving at large upscaling factors. We present iSeeBetter, a novel GAN-based spatio-temporal approach to video super-resolution (VSR) that renders temporally consistent super-resolution videos. iSeeBetter extracts spatial and temporal information from the current and neighboring frames using the concept of recurrent back-projection networks as its generator. Furthermore, to improve the “naturality” of the super-resolved output while eliminating artifacts seen with traditional algorithms, we utilize the discriminator from super-resolution generative adversarial network. Although mean squared error (MSE) as a primary loss-minimization objective improves PSNR/SSIM, these metrics may not capture fine details in the image resulting in misrepresentation of perceptual quality. To address this, we use a four-fold (MSE, perceptual, adversarial, and total-variation loss function. Our results demonstrate that iSeeBetter offers superior VSR fidelity and surpasses state-of-the-art performance.

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

Symmetry ◽  
2020 ◽  
Vol 12 (3) ◽  
pp. 449 ◽  
Author(s):  
Can Li ◽  
Liejun Wang ◽  
Shuli Cheng ◽  
Naixiang Ao
Keyword(s):  
Super Resolution ◽  
Ground Truth ◽  
Second Order ◽  
Attention Mechanism ◽  
Generative Adversarial Networks ◽  
Perceptual Quality ◽  
Human Visual Perception ◽  
Image Perception ◽  
Generative Adversarial Network ◽  
Image Super Resolution

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.

Super-resolution in Structural Geological Models.

2021 ◽  
Author(s):  
Mustaeen Ur Rehman Qazi ◽  
Florian Wellmann
Keyword(s):  
High Resolution ◽  
Structural Model ◽  
Mean Squared Error ◽  
Super Resolution ◽  
Generative Adversarial Networks ◽  
Low Resolution ◽  
Generative Adversarial Network ◽  
Data Set ◽  
Adversarial Networks ◽  
Geological Models

<p>Structural geological models are often calculated on a specific spatial resolution – for example in the form of grid representations, or when surfaces are extracted from implicit fields. However, the structural inventory in these models is limited by the underlying mathematical formulations. It is therefore logical that, above a certain resolution, no additional information is added to the representation.</p><p>We evaluate here if Deep Neural Networks can be trained to obtain a high-resolution representation based on a low-resolution structural model, at different levels of resolution. More specifically, we test the use of state-of-the-art Generative Adversarial Networks (GAN’s) for image superresolution in the context of 2-D geological model sections. These techniques aim to learn the hidden structure or information in high resolution image data set and then reproduce highly detailed and super resolved image from its low resolution counterpart. We propose the use of Generative Adversarial Networks GANS for super resolution of geological images and 2D geological models represented as images. In this work a generative adversarial network called SRGAN has been used which uses a perceptual loss function consisting of an adversarial loss, mean squared error loss and content loss for photo realistic image super resolution. First results are promising, but challenges remain due to the different interpretation of color in images for which these GAN’s are typically used, whereas we are mostly interested in structures.</p>

scholarly journals Super-Resolution Reconstruction of Underwater Image Based on Image Sequence Generative Adversarial Network

2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Li Li ◽  
Zijia Fan ◽  
Mingyang Zhao ◽  
Xinlei Wang ◽  
Zhongyang Wang ◽  
...  
Keyword(s):  
Network Architecture ◽  
Signal To Noise Ratio ◽  
Super Resolution ◽  
Structural Similarity ◽  
Image Sequence ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Underwater Image ◽  
Dual Generator ◽  
The Stability

Since the underwater image is not clear and difficult to recognize, it is necessary to obtain a clear image with the super-resolution (SR) method to further study underwater images. The obtained images with conventional underwater image super-resolution methods lack detailed information, which results in errors in subsequent recognition and other processes. Therefore, we propose an image sequence generative adversarial network (ISGAN) method for super-resolution based on underwater image sequences collected by multifocus from the same angle, which can obtain more details and improve the resolution of the image. At the same time, a dual generator method is used in order to optimize the network architecture and improve the stability of the generator. The preprocessed images are, respectively, passed through the dual generator, one of which is used as the main generator to generate the SR image of sequence images, and the other is used as the auxiliary generator to prevent the training from crashing or generating redundant details. Experimental results show that the proposed method can be improved on both peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) compared to the traditional GAN method in underwater image SR.

scholarly journals Deblending galaxy superpositions with branched generative adversarial networks

2019 ◽  
Vol 485 (2) ◽  
pp. 2617-2627 ◽  
Author(s):  
David M Reiman ◽  
Brett E Göhre
Keyword(s):  
Signal To Noise Ratio ◽  
Ground Truth ◽  
Structural Similarity ◽  
Generative Models ◽  
Generative Adversarial Networks ◽  
Wide Field ◽  
Generative Adversarial Network ◽  
Galaxy Surveys ◽  
Adversarial Network ◽  
Natural Choice

Abstract Near-future large galaxy surveys will encounter blended galaxy images at a fraction of up to 50 per cent in the densest regions of the Universe. Current deblending techniques may segment the foreground galaxy while leaving missing pixel intensities in the background galaxy flux. The problem is compounded by the diffuse nature of galaxies in their outer regions, making segmentation significantly more difficult than in traditional object segmentation applications. We propose a novel branched generative adversarial network to deblend overlapping galaxies, where the two branches produce images of the two deblended galaxies. We show that generative models are a powerful engine for deblending given their innate ability to infill missing pixel values occluded by the superposition. We maintain high peak signal-to-noise ratio and structural similarity scores with respect to ground truth images upon deblending. Our model also predicts near-instantaneously, making it a natural choice for the immense quantities of data soon to be created by large surveys such as Large Synoptic Survey Telescope, Euclid, and Wide-Field Infrared Survey Telescope.

The enhanced deep Plug-and-play super-resolution algorithm with residual channel attention networks

2021 ◽  
pp. 1-10
Author(s):  
Hongguang Pan ◽  
Fan Wen ◽  
Xiangdong Huang ◽  
Xinyu Lei ◽  
Xiaoling Yang
Keyword(s):  
Signal To Noise Ratio ◽  
Low Frequency ◽  
Super Resolution ◽  
Structural Similarity ◽  
Plug And Play ◽  
Attention Networks ◽  
Frequency Information ◽  
Blind Deblurring ◽  
Adaptive Adjustment ◽  
Deep Feature Extraction

In the field of super-resolution image reconstruction, as a learning-based method, deep plug-and-play super-resolution (DPSR) algorithm can be used to find the blur kernel by using the existing blind deblurring methods. However, DPSR is not flexible enough in processing images with high- and low-frequency information. Considering a channel attention mechanism can distinguish low-frequency information and features in low-resolution images, in this paper, we firstly introduce this mechanism and design a new residual channel attention networks (RCAN); then the RCAN is adopted to replace deep feature extraction part in DPSR to achieve the adaptive adjustment of channel characteristics. Through four test experiments based on Set5, Set14, Urban100 and BSD100 datasets, we find that, under different blur kernels and different scale factors, the average peak signal to noise ratio (PSNR) and structural similarity (SSIM) values of our proposed method increase by 0.31dB and 0.55%, respectively; under different noise levels, the average PSNR and SSIM values increase by 0.26dB and 0.51%, respectively.

Towards Accuracy Enhancement of Age Group Classification Using Generative Adversarial Networks

2021 ◽  
pp. 1-17
Author(s):  
Khaled ELKarazle ◽  
Valliappan Raman ◽  
Patrick Then
Keyword(s):  
Age Estimation ◽  
Super Resolution ◽  
Generative Adversarial Networks ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Original Dataset ◽  
Age Group Classification ◽  
Facial Images

Age estimation models can be employed in many applications, including soft biometrics, content access control, targeted advertising, and many more. However, as some facial images are taken in unrestrained conditions, the quality relegates, which results in the loss of several essential ageing features. This study investigates how introducing a new layer of data processing based on a super-resolution generative adversarial network (SRGAN) model can influence the accuracy of age estimation by enhancing the quality of both the training and testing samples. Additionally, we introduce a novel convolutional neural network (CNN) classifier to distinguish between several age classes. We train one of our classifiers on a reconstructed version of the original dataset and compare its performance with an identical classifier trained on the original version of the same dataset. Our findings reveal that the classifier which trains on the reconstructed dataset produces better classification accuracy, opening the door for more research into building data-centric machine learning systems.

scholarly journals A GENERATIVE ADVERSARIAL NETWORK APPROACH FOR SUPER-RESOLUTION OF SENTINEL-2 SATELLITE IMAGES

2020 ◽  
Vol XLIII-B1-2020 ◽  
pp. 9-14
Author(s):  
F. Pineda ◽  
V. Ayma ◽  
C. Beltran
Keyword(s):  
High Resolution ◽  
Satellite Images ◽  
Resolution Enhancement ◽  
Super Resolution ◽  
Structural Similarity ◽  
Generative Adversarial Network ◽  
Acceptable Result ◽  
Adversarial Network ◽  
High Resolution Satellite Images ◽  
Sentinel 2

Abstract. High-resolution satellite images have always been in high demand due to the greater detail and precision they offer, as well as the wide scope of the fields in which they could be applied; however, satellites in operation offering very high-resolution (VHR) images has experienced an important increase, but they remain as a smaller proportion against existing lower resolution (HR) satellites. Recent models of convolutional neural networks (CNN) are very suitable for applications with image processing, like resolution enhancement of images; but in order to obtain an acceptable result, it is important, not only to define the kind of CNN architecture but the reference set of images to train the model. Our work proposes an alternative to improve the spatial resolution of HR images obtained by Sentinel-2 satellite by using the VHR images from PeruSat1, a peruvian satellite, which serve as the reference for the super-resolution approach implementation based on a Generative Adversarial Network (GAN) model, as an alternative for obtaining VHR images. The VHR PeruSat-1 image dataset is used for the training process of the network. The results obtained were analyzed considering the Peak Signal to Noise Ratios (PSNR) and the Structural Similarity (SSIM). Finally, some visual outcomes, over a given testing dataset, are presented so the performance of the model could be analyzed as well.

scholarly journals TopologyGAN: Topology Optimization Using Generative Adversarial Networks Based on Physical Fields Over the Initial Domain

2020 ◽  
Author(s):  
Zhenguo Nie ◽  
Tong Lin ◽  
Haoliang Jiang ◽  
Levent Burak Kara
Keyword(s):  
Topology Optimization ◽  
Boundary Conditions ◽  
Mean Squared Error ◽  
Sparse Matrices ◽  
Hybrid Network ◽  
Generative Adversarial Networks ◽  
Test Problems ◽  
Generative Adversarial Network ◽  
The Mean ◽  
Physical Fields

Abstract In topology optimization using deep learning, load and boundary conditions represented as vectors or sparse matrices often miss the opportunity to encode a rich view of the design problem, leading to less than ideal generalization results. We propose a new data-driven topology optimization model called TopologyGAN that takes advantage of various physical fields computed on the original, unoptimized material domain, as inputs to the generator of a conditional generative adversarial network (cGAN). Compared to a baseline cGAN, TopologyGAN achieves a nearly 3× reduction in the mean squared error and a 2.5× reduction in the mean absolute error on test problems involving previously unseen boundary conditions. Built on several existing network models, we also introduce a hybrid network called U-SE(Squeeze-and-Excitation)-ResNet for the generator that further increases the overall accuracy. We publicly share our full implementation and trained network.

scholarly journals Single Image Super-Resolution: Depthwise Separable Convolution Super-Resolution Generative Adversarial Network

2020 ◽  
Vol 10 (1) ◽  
pp. 375 ◽  
Author(s):  
Zetao Jiang ◽  
Yongsong Huang ◽  
Lirui Hu
Keyword(s):  
Similarity Index ◽  
Super Resolution ◽  
Structural Similarity ◽  
Image Features ◽  
Single Image ◽  
Generative Adversarial Network ◽  
Visual Evaluation ◽  
Adversarial Network ◽  
Image Super Resolution ◽  
Single Image Super Resolution

The super-resolution generative adversarial network (SRGAN) is a seminal work that is capable of generating realistic textures during single image super-resolution. However, the hallucinated details are often accompanied by unpleasant artifacts. To further enhance the visual quality, we propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The method is based on depthwise separable convolution super-resolution generative adversarial network (DSCSRGAN). A new depthwise separable convolution dense block (DSC Dense Block) was designed for the generator network, which improved the ability to represent and extract image features, while greatly reducing the total amount of parameters. For the discriminator network, the batch normalization (BN) layer was discarded, and the problem of artifacts was reduced. A frequency energy similarity loss function was designed to constrain the generator network to generate better super-resolution images. Experiments on several different datasets showed that the peak signal-to-noise ratio (PSNR) was improved by more than 3 dB, structural similarity index (SSIM) was increased by 16%, and the total parameter was reduced to 42.8% compared with the original model. Combining various objective indicators and subjective visual evaluation, the algorithm was shown to generate richer image details, clearer texture, and lower complexity.

Sign in / Sign up

Export Citation Format

Share Document