Multi Scale-Adaptive Super-Resolution Person Re-Identification Using GAN

Adil, Muhammad; Mamoon, Saqib; Ali, Zakir; Manzoor, Muhammad Arslan; Lian, Zhichao

doi:10.1109/access.2020.3023594

Cited by 20 publications

(7 citation statements)

References 63 publications

(94 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, Adil et al exploited SRGAN and a denoising module to obtain a clear image. Then, they used a network to learn unique representative information for identifying a person [113]. In terms of image super-resolution and object detection, Wang et al used multi-class cyclic super-resolution GAN to restore high-quality images, and used a YOLOv5 detector to finish object detection task [114].…”

Section: Popular Gans For Image Applicationsmentioning

confidence: 99%

Generative Adversarial Networks for Image Super-Resolution: A Survey

Tian¹,

Zhang²,

Lin³

et al. 2022

Preprint

View full text Add to dashboard Cite

Single image super-resolution (SISR) has played an important role in the field of image processing. Recent generative adversarial networks (GANs) can achieve excellent results on low-resolution images with small samples. However, there are little literatures summarizing different GANs in SISR. In this paper, we conduct a comparative study of GANs from different perspectives. We first take a look at developments of GANs. Second, we present popular architectures for GANs in big and small samples for image applications. Then, we analyze motivations, implementations and differences of GANs based optimization methods and discriminative learning for image super-resolution in terms of supervised, semi-supervised and unsupervised manners. Next, we compare performance of these popular GANs on public datasets via quantitative and qualitative analysis in SISR. Finally, we highlight challenges of GANs and potential research points for SISR.

show abstract

Section: Popular Gans For Image Applicationsmentioning

confidence: 99%

Generative Adversarial Networks for Image Super-Resolution: A Survey

Tian¹,

Zhang²,

Lin³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The SR results for the various scale factors are shown in Figs. 3,4,5,6. Table 1 lists the the quantitative results of various methods under various scaling factors.…”

Section: A Implementation and Training Detailsmentioning

confidence: 99%

“…I MAGE super-resolution (SR) is used in various computer vision applications, ranging from security and surveillance imaging [1], medical imaging [2], [3] to object recognition [4]. However, image SR is a problematic problem due to exists multiple solutions for low resolution (LR) input.…”

Section: Introductionmentioning

confidence: 99%

Image Super-Resolution Using Multi-Scale Space Feature and Deformable Convolutional Network

Jiang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Recent researches on image super-resolution (SR) have achieved great progressing with the great development of convolutional neural networks (CNNs). However, existing CNNs usually adopt fixed filter structures and the convolutions just rely on the local information contained in the fixed receptive field. Above phenomena prevent high-level convolution layers from encoding semantics over spatial locations and largely limits the learning capacity of CNNs. What's more, many methods simply used a single-size feature map and failed to consider the spatial information, thereby these results also are unsatisfactory. To address these problems, in this paper, a network with multi-scale space features and deformable convolutional (MulSSD) is presented to further improve the reconstruction accuracy. Specifically, a multi-scale space features compressed block containing the deformable convolutional layer is proposed, which can augment the spatial sampling locations and incorporate the multi-scale space compression features and adaptively adjust the sampling grid and receptive fields. In addition, the design of symmetrical combinations make the information can be smoothly propagated through multiple channels during the training, which effectively improves the training efficiency. Extensive experiments on benchmark datasets validate that the proposed method achieves outperforming quantitative and qualitative performance. And the experimental results also proved that our proposed MulSSD can reconstruct high-quality high-resolution (HR) images at a relatively fast speed and outperform other methods by a large margin.

show abstract

“…Although these state-of-the-art algorithms have high PSNR/SSIM, traditional DCNN-based algorithm tends to generate the average of these SR solutions [29], so the generated image will be visually blurred to a certain extent. Some researchs focus on generating clear and seemingly real images, such as SR-GAN, ESRGAN, etc [30]- [32]. They design a discriminator to provide adversarial loss to reduce the gap between the generated data distribution and the real data distribution.…”

Section: A Dcnn-based Single Image Super-resolutionmentioning

confidence: 99%

Lightweight Dual-Stream Residual Network for Single Image Super-Resolution

Jiang¹,

Liu

Zhan

et al. 2021

IEEE Access

View full text Add to dashboard Cite

The deep convolutional neural network has achieved great success in the Single Image Super-resolution task. It is obviously that among the well-known super-resolution methods, the deep learning-based algorithms show the most advanced performance. However, the most advanced algorithms currently use complex networks with a large number of parameters, which makes it difficult to apply deep learning algorithms on mobile devices. To solve this problem, we propose a lightweight dualresidual network(LDRN) for single image super-resolution, which has better reconstruction quality than most current advanced lightweight algorithms. Due to its fewer parameters and computational expense, real-time and mobile applications of our networks can be easily realized. On the basis of the residual module, we propose a new residual unit, which uses two depthwise separable(DW) convolution to obtain better balance between feature extraction capacity and lightweight performance. We further design a dualstream residual block, which contains a multiplication branch and an addition branch. The dual-stream residual block can improve the reconstruction performance more effectively than expanding the network width. In addition, we also designed a new up-sampling module to simplify the previous up-sampling methods. Extensive experimental results show that our network has better reconstruction performance and lightweight performance than most existing state-of-the-art algorithms.

show abstract

Multi Scale-Adaptive Super-Resolution Person Re-Identification Using GAN

Cited by 20 publications

References 63 publications

Generative Adversarial Networks for Image Super-Resolution: A Survey

Generative Adversarial Networks for Image Super-Resolution: A Survey

Image Super-Resolution Using Multi-Scale Space Feature and Deformable Convolutional Network

Lightweight Dual-Stream Residual Network for Single Image Super-Resolution

Contact Info

Product

Resources

About