Image Super-Resolution using a Improved Generative Adversarial Network

Wang, Han; Wu, Wei; Yang, Su; Duan, Yongsheng; Wang, Pengze

doi:10.1109/iceiec.2019.8784610

Cited by 11 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The goal of the generator network is to map random vectors to real images, and the goal of the discriminator is to distinguish the generated images from the real images. In computer vision, GANs have been widely used in various fields such as image synthesis [31]- [33], image translation [34]- [36], and super-resolution [37], [38]. In recent years, the frameworks of GAN have been successfully applied to optical flow [18], [20]- [22] because GAN-based architecture can replace the brightness constancy widely used in general CNN-based optical flow estimation methods, allowing for an end-to-end estimation of the flow field, and eliminating the requirement of the time-costing energy function minimization process.…”

Section: Generative Adversarial Networkmentioning

confidence: 99%

SDOF-GAN: Symmetric Dense Optical Flow Estimation With Generative Adversarial Networks

Che

Zheng

Yang

et al. 2021

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

There is a growing consensus in computer vision that symmetric optical flow estimation constitutes a better model than a generic asymmetric one for its independence of the selection of source/target image. Yet, convolutional neural networks (CNNs), that are considered the de facto standard vision model, deal with the asymmetric case only in most cutting-edge CNNs-based optical flow techniques. We bridge this gap by introducing a novel model named SDOF-GAN: symmetric dense optical flow with generative adversarial networks (GANs). SDOF-GAN realizes a consistency between the forward mapping (source-to-target) and the backward one (target-to-source) by ensuring that they are inverse of each other with an inverse network. In addition, SDOF-GAN leverages a GAN model for which the generator estimates symmetric optical flow fields while the discriminator differentiates the "real" ground-truth flow field from a "fake" estimation by assessing the flow warping error. Finally, SDOF-GAN is trained in a semi-supervised fashion to enable both the precious labeled data and large amounts of unlabeled data to be fully-exploited. We demonstrate significant Manuscript

show abstract

Section: Generative Adversarial Networkmentioning

confidence: 99%

SDOF-GAN: Symmetric Dense Optical Flow Estimation With Generative Adversarial Networks

Che

Zheng

Yang

et al. 2021

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…In the field of computer vision, GANs are widely used as generating models. The ability to learn the distribution of real samples through GANs can not only generate higher resolution images [ 15 , 60 ] but also play an increasingly important role in the fields of video super-resolution [ 61 ], speech super-resolution [ 14 ], image enhancement [ 62 ], etc. GAN works in an end-to-end manner; it learns the feature distribution and mapping relationship of real samples better than traditional machine learning algorithms.…”

Section: Application Of Gans In Computer Visionmentioning

confidence: 99%

“…In public security supervision, surveillance cameras used to monitor suspicious behavior are widely distributed in public places. Real-time personnel monitoring is realized through target detection [12,13] and faces recognition technologies [14][15][16][17][18], which provides effective help for hunting suspicious persons. Microsoft Kinect has successfully developed related game applications using stereo vision technologies in-game and control.…”

Section: Introductionmentioning

confidence: 99%

Generative Adversarial Network Technologies and Applications in Computer Vision

Jin

Tan

Jiang

2020

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Computer vision is one of the hottest research fields in deep learning. The emergence of generative adversarial networks (GANs) provides a new method and model for computer vision. The idea of GANs using the game training method is superior to traditional machine learning algorithms in terms of feature learning and image generation. GANs are widely used not only in image generation and style transfer but also in the text, voice, video processing, and other fields. However, there are still some problems with GANs, such as model collapse and uncontrollable training. This paper deeply reviews the theoretical basis of GANs and surveys some recently developed GAN models, in comparison with traditional GAN models. The applications of GANs in computer vision include data enhancement, domain transfer, high-quality sample generation, and image restoration. The latest research progress of GANs in artificial intelligence (AI) based security attack and defense is introduced. The future development of GANs in computer vision is also discussed at the end of the paper with possible applications of AI in computer vision.

show abstract

“…Assuming that an observed image y represents the output of model T, and x is the input of T, then given output y, calculating the input x is the inverse problem [9]. In recent years, convolutional neural networks (CNNs) have become a popular way to solve the inverse problem [10][11][12][13][14][15] in problems such as dehazing, style transfer, and image superresolution reconstruction.…”

Section: Introductionmentioning

confidence: 99%

Multiprojector Interreflection Compensation Using a Deep Convolution Network

et al. 2022

Scientific Programming

View full text Add to dashboard Cite

The aim of multiprojector interreflection compensation is to modify input images to remove complex physical stray-light effects (interreflection) from a multiprojector immersive system. This is an important but often ignored problem, which can lead to degradation of a projection image. Traditional methods usually address this problem by computing a matrix inversion. These traditional methods often ignore issue of the clarity of the generated images. In this paper, we describe a method for learning the inversion using a deep convolutional neural network (CNN), named Superresolution Compensation Net (SRCN). SRCN consists of four convolution layers to learn interactions of global light, six convolution layers, and two transposed convolution layers to extract multilevel features and generate compensation images. We also used a subpixel convolution layer to increase the resolution. To make compensation images more consistent with human visual perception, we used a perceptual loss, which compares the differences between feature maps on the VGG16 network. We implemented an immersive projector-camera display prototype (Pro-Cam) and calculated the quality index of the compensation images and the projection results. Our method achieved better results than previous methods in both objective evaluations and subjective visual perception.

show abstract

Image Super-Resolution using a Improved Generative Adversarial Network

Cited by 11 publications

References 9 publications

SDOF-GAN: Symmetric Dense Optical Flow Estimation With Generative Adversarial Networks

SDOF-GAN: Symmetric Dense Optical Flow Estimation With Generative Adversarial Networks

Generative Adversarial Network Technologies and Applications in Computer Vision

Multiprojector Interreflection Compensation Using a Deep Convolution Network

Contact Info

Product

Resources

About