Video Super Resolution with Generative Adversarial Network

Gopan, K Gopika; Kumar, G. Suvarna

doi:10.1109/icoei.2018.8553719

Cited by 4 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The spatial alignment modules and the temporal adaptation are manifested to increase the reconstruction quality, and thus considerably of the SR performance is improved. Wang et al [33] suggested depth SR on RGB-D video streams with significant displacement 3D motion. This method is improved in two phases: merging of compensated depth images and motion compensation of depth images.…”

Section: Related Workmentioning

confidence: 99%

Three-Dimensional Video Super-Resolution Reconstruction Scheme Based on Histogram Matching and Recursive Bayesian Algorithms

et al. 2022

View full text Add to dashboard Cite

Multimedia Super-Resolution (SR) reconstruction is an essential and mandatory process for different visualization functions. Recently, several procedures have been suggested for single and multiimages SR processes. This work presents an effective SR scheme for visual quality and resolution enhancement of 3D Video (3DV) sequences. The idea behind the proposed 3DV SR reconstruction scheme is the utilization of a recursive Bayesian process for improving the reconstruction resolution of the degraded 3DV sequences with down-sampling, blurring, and noise effects. In addition, a significant stage of histogram matching based on a visual image with a better-distributed histogram is employed. The main aim of employing the histogram matching stage for the improved 3DV stream is to introduce a dynamic range modification of each 3DV frame. It further generates 3DV sequences with an enhanced distribution of intensities. This improves the whole performance efficiency of the suggested scheme. The performance of the proposed SR scheme is contrasted with the conventional Bicubic approach. The comparative analyses with recent and related SR techniques are also performed. Simulation results revealed that the proposed scheme achieves superior outcomes of Structural Similarity (SSIM) index, local contrast, average gradient, Mean Square Error (MSE), edge intensity, average gradient, entropy, and Peak Signal-to-Noise Ratio (PSNR) metrics for the resulted 3DV frames.

show abstract

Section: Related Workmentioning

confidence: 99%

Three-Dimensional Video Super-Resolution Reconstruction Scheme Based on Histogram Matching and Recursive Bayesian Algorithms

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In computer vision, super resolution (SR) refers to a computational technique that reconstructs a higher resolution image from low-resolution image. Image and video super resolution studies are found in [45][46][47]. In super-resolution, images generally lose their finer texture details when they are super resolved at large upscaling factors.…”

Section: Related Study: Denoising Learningmentioning

confidence: 99%

Comparing U-Net Based Models for Denoising Color Images

Komatsu

Gonsalves

2020

View full text Add to dashboard Cite

Digital images often become corrupted by undesirable noise during the process of acquisition, compression, storage, and transmission. Although the kinds of digital noise are varied, current denoising studies focus on denoising only a single and specific kind of noise using a devoted deep-learning model. Lack of generalization is a major limitation of these models. They cannot be extended to filter image noises other than those for which they are designed. This study deals with the design and training of a generalized deep learning denoising model that can remove five different kinds of noise from any digital image: Gaussian noise, salt-and-pepper noise, clipped whites, clipped blacks, and camera shake. The denoising model is constructed on the standard segmentation U-Net architecture and has three variants—U-Net with Group Normalization, Residual U-Net, and Dense U-Net. The combination of adversarial and L1 norm loss function re-produces sharply denoised images and show performance improvement over the standard U-Net, Denoising Convolutional Neural Network (DnCNN), and Wide Interface Network (WIN5RB) denoising models.

show abstract

“…The losses can be classed into adversarial loss, the pixel-based loss and feature map based loss. For example, Ledig et al use an adversarial loss and a content loss[214],while Chen et al use an MSE loss, the generative loss and the VGG loss[212].Other loss functions contain the sum of the perceptual loss, MSE-based content loss, and an adversarial loss, which is used[215] by Gopan and Kumar, the sum of the pixel-wise loss and adversarial loss used in[216] by Jiang et al and the sum of joint sparsifying transform loss and supervision loss in [213] by You et al.…”

mentioning

confidence: 99%

Deep Learning Methods for Solving Linear Inverse Problems: Research Directions and Paradigms

Bai,

Chen,

Chen

et al. 2020

Preprint

View full text Add to dashboard Cite

The linear inverse problem is fundamental to the development of various scientific areas. Innumerable attempts have been carried out to solve different variants of the linear inverse problem in different applications. Nowadays, the rapid development of deep learning provides a fresh perspective for solving the linear inverse problem, which has various well-designed network architectures results in state-of-the-art performance in many applications. In this paper, we present a comprehensive survey of the recent progress in the development of deep learning for solving various linear inverse problems. We review how deep learning methods are used in solving different linear inverse problems, and explore the structured neural network architectures that incorporate knowledge used in traditional methods. Furthermore, we identify open challenges and potential future directions along this research line.

show abstract

Video Super Resolution with Generative Adversarial Network

Cited by 4 publications

References 8 publications

Three-Dimensional Video Super-Resolution Reconstruction Scheme Based on Histogram Matching and Recursive Bayesian Algorithms

Three-Dimensional Video Super-Resolution Reconstruction Scheme Based on Histogram Matching and Recursive Bayesian Algorithms

Comparing U-Net Based Models for Denoising Color Images

Deep Learning Methods for Solving Linear Inverse Problems: Research Directions and Paradigms

Contact Info

Product

Resources

About