An Unsupervised Remote Sensing Single-Image Super-Resolution Method Based on Generative Adversarial Network

Zhang, Ning; Wang, Yongcheng; Zhang, Xin; Xu, Dongdong; Wang, Xiaodong

doi:10.1109/access.2020.2972300

Cited by 20 publications

(14 citation statements)

References 80 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3) Unsupervised GANs with improved loss functions for image super-resolution: Combining loss functions and GANs in an unsupervised way is useful for training image superresolution models in the real world [139]. For instance, Zhang et al used a novel loss function based image quality assessment in a GAN to obtain accurate texture information and more visual effects [139]. Besides, an encoder-decoder architecture is embedded in this GAN to mine more structure information for pursuing high-quality images of a generator from this GAN [139].…”

Section: Unsupervised Gans For Image Super-resolutionmentioning

confidence: 99%

“…For instance, Zhang et al used a novel loss function based image quality assessment in a GAN to obtain accurate texture information and more visual effects [139]. Besides, an encoder-decoder architecture is embedded in this GAN to mine more structure information for pursuing high-quality images of a generator from this GAN [139]. Han et al depended on SAGAN and L1 loss in a GAN in an unsupervised manner to act multisequence structural MRI for detecting braining anomalies [140].…”

Section: Unsupervised Gans For Image Super-resolutionmentioning

confidence: 99%

See 1 more Smart Citation

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: Unsupervised Gans For Image Super-resolutionmentioning

confidence: 99%

Section: Unsupervised Gans For Image Super-resolutionmentioning

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 prefix span algorithm eliminates the scanning of unnecessary pixels [27]. The spatial resolution of remote sensing images can be improved by super resolution technique [28].…”

Section: Literature Reviewmentioning

confidence: 99%

Quantized ternary pattern and singular value decomposition for the efficient mining of sequences in SRSI images

R¹,

Anandharaj²

2020

SN Appl. Sci.

View full text Add to dashboard Cite

The growth and development of particular region over time can be witnessed by remote sensing images. Although such raw images have less possibility to derive the insights, Serial Remote Sensing Images (SRSI) has the large potential to discover the patterns. The evolution of spatial patterns in various areas including urban development, expansion of vegetation cover and agriculture is the evidence for the utilization of SRSI accumulation. The application of conventional sequential pattern-mining algorithms on the SRSI images results in high computational complexity. This issue can be resolved by grouping the pixels and mining sequence patterns. A one-pass framework is introduced to compress and hide the data in the marked stream without any loss. In this paper, we proposed a Quantized ternary pattern based pixel grouping and Singular Value Decomposition-Run Length Coding based pattern mining. The algorithms are experimented using a dataset, namely, the Cropland data layer dataset. The proposed algorithm is efficient in terms of mining time and sequence pattern generation.

show abstract

“…Ulyanov et al [27] proposed a new strategy for dealing with the regularization tasks in inverse problems and has been proved to be very effective and has been successful in many imaging inverse problems such as denoising, super-resolution and so on. Since the imaging environment of remote sensing images is generally unknown and complex, unsupervised learning has been developed in remote sensing image SR. Zhang et al [28] proposed an unsupervised method that employs GAN to obtain super-resolved and achieved satisfactory performance. Inspired by CycleGAN, Wang et al [29] proposed two generative CNNs for down-sampling named Cycle-CNN modeling the degradation process and the corresponding reconstruction, named CycleCNN.…”

Section: Introductionmentioning

confidence: 99%

Unpaired Remote Sensing Image Super-Resolution with Multi-Stage Aggregation Networks

Zhang¹,

Lu²,

Huang

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

Mainstream image super-resolution (SR) methods are generally based on paired training samples. As the high-resolution (HR) remote sensing images are difficult to collect with a limited imaging device, most of the existing remote sensing super-resolution methods try to down-sample the collected original images to generate an auxiliary low-resolution (LR) image and form a paired pseudo HR-LR dataset for training. However, the distribution of the generated LR images is generally inconsistent with the real images due to the limitation of remote sensing imaging devices. In this paper, we propose a perceptually unpaired super-resolution method by constructing a multi-stage aggregation network (MSAN). The optimization of the network depends on consistency losses. In particular, the first phase is to preserve the contents of the super-resolved results, by constraining the content consistency between the down-scaled SR results and the low-quality low-resolution inputs. The second stage minimizes perceptual feature loss between the current result and LR input to constrain perceptual-content consistency. The final phase employs the generative adversarial network (GAN) to adding photo-realistic textures by constraining perceptual-distribution consistency. Numerous experiments on synthetic remote sensing datasets and real remote sensing images show that our method obtains more plausible results than other SR methods quantitatively and qualitatively. The PSNR of our network is 0.06dB higher than the SOTA method—HAN on the UC Merced test set with complex degradation.

show abstract

An Unsupervised Remote Sensing Single-Image Super-Resolution Method Based on Generative Adversarial Network

Cited by 20 publications

References 80 publications

Generative Adversarial Networks for Image Super-Resolution: A Survey

Generative Adversarial Networks for Image Super-Resolution: A Survey

Quantized ternary pattern and singular value decomposition for the efficient mining of sequences in SRSI images

Unpaired Remote Sensing Image Super-Resolution with Multi-Stage Aggregation Networks

Contact Info

Product

Resources

About