Fast simultaneous image super-resolution and motion deblurring with decoupled cooperative learning

Liu, Heng; Qin, Jiajun; Fu, Zilin; Li, Xue; Han, Jungong

doi:10.1007/s11554-020-00976-x

Cited by 11 publications

(4 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Du et al [17] suggested a novel approach based on CNN to reconstruct high resolution images from low-blurry ones. Liu et al [18] proposed a deep decoupled cooperative learning based CNN deblurring model to achieve disentangling and synthesizing single image super-resolution and motion deblurring. Lumentut et al [19] proposed a framework for the light field (LF) image enhancement using a deep neural net to supersolve the LF spatial deblurring and super-resolution under 6degree-of-freedom camera motion.…”

Section: Joint Super-resolution and Deblurringmentioning

confidence: 99%

Deep CNN with Skip Connection and Network in Network for Super-Resolving Blurry Text Images

Neji¹

2022

Preprint

View full text Add to dashboard Cite

show abstract

Section: Joint Super-resolution and Deblurringmentioning

confidence: 99%

Deep CNN with Skip Connection and Network in Network for Super-Resolving Blurry Text Images

Neji¹

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Du et al [21] suggested an approach based on CNN to reconstruct high resolution images from low-blurry ones. Liu et al [22] proposed a deep decoupled cooperative learning based CNN deblurring model to achieve disentangling and synthesizing single image super-resolution and motion deblurring. Lumentut et al [23] proposed a framework for the light field (LF) image enhancement using a deep neural net to super-solve the LF spatial deblurring and super-resolution under 6-degree-of-freedom camera motion.…”

Section: Joint Super-resolution and Deblurringmentioning

confidence: 99%

Deep CNN with Skip Connection and Network in Network for Super-Resolving Blurry Text Images

Neji¹

2022

Preprint

View full text Add to dashboard Cite

<p>Deep convolutional neural networks (Deep CNN) have achieved hopeful performancefor single image super-resolution. In particular, the Deep CNN skip Connection andNetwork in Network (DCSCN) architecture has been successfully applied to naturalimages super-resolution. In this work we propose an approach called SDT-DCSCN thatjointly performs super-resolution and deblurring of low-resolution blurry text imagesbased on DCSCN. Our approach uses subsampled blurry images in the input and origi-nal sharp images as ground truth. The used architecture is consists of a higher numberof filters in the input CNN layer to a better analysis of the text details. The quantitativeand qualitative evaluation on different datasets prove the high performance of our modelto reconstruct high-resolution and sharp text images. In addition, in terms of computa-tional time, our proposed method gives competitive performance compared to state ofthe art methods.</p>

show abstract

“…Actually, as discussed in [29], the HR-to-LR generation is just the complex image degradation process, which may involve multiple degeneration factors, such as noising, blurring and resolution decreasing. Fortunately, illuminated by the work [30], we introduce Gauss noise accompanied with LR image as input and construct a fully convolutional network (FCN) model to fulfill degrading high-resolution ultrasound image to LR one.…”

Section: Cyclegan Based Perception Consistency Srmentioning

confidence: 99%

Perception Consistency Ultrasound Image Super-resolution via Self-supervised CycleGAN

Liu¹,

Liu²,

Tao³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Due to the limitations of sensors, the transmission medium and the intrinsic properties of ultrasound, the quality of ultrasound imaging is always not ideal, especially its low spatial resolution. To remedy this situation, deep learning networks have been recently developed for ultrasound image super-resolution (SR) because of the powerful approximation capability. However, most current supervised SR methods are not suitable for ultrasound medical images because the medical image samples are always rare, and usually, there are no low-resolution (LR) and high-resolution (HR) training pairs in reality. In this work, based on self-supervision and cycle generative adversarial network (CycleGAN), we propose a new perception consistency ultrasound image super-resolution (SR) method, which only requires the LR ultrasound data and can ensure the re-degenerated image of the generated SR one to be consistent with the original LR image, and vice versa. We first generate the HR fathers and the LR sons of the test ultrasound LR image through image enhancement, and then make full use of the cycle loss of LR-SR-LR and HR-LR-SR and the adversarial characteristics of the discriminator to promote the generator to produce better perceptually consistent SR results. The evaluation of PSNR/IFC/SSIM, inference efficiency and visual effects under the benchmark CCA-US and CCA-US datasets illustrate our proposed approach is effective and superior to other state-of-the-art methods.

show abstract

Fast simultaneous image super-resolution and motion deblurring with decoupled cooperative learning

Cited by 11 publications

References 34 publications

Deep CNN with Skip Connection and Network in Network for Super-Resolving Blurry Text Images

Deep CNN with Skip Connection and Network in Network for Super-Resolving Blurry Text Images

Deep CNN with Skip Connection and Network in Network for Super-Resolving Blurry Text Images

Perception Consistency Ultrasound Image Super-resolution via Self-supervised CycleGAN

Contact Info

Product

Resources

About