Image Super-Resolution Using Very Deep Residual Channel Attention Networks

Zhang, Yulun; Li, Kunpeng; Li, Kai; Wang, Lichen; Zhong, Bineng; Fu, Yun

doi:10.1007/978-3-030-01234-2_18

Cited by 3,060 publications

(2,942 citation statements)

References 45 publications

(181 reference statements)

Supporting

Mentioning

2,929

Contrasting

Unclassified

Order By: Relevance

“…A large variety of successful network architectures have been developed in other areas of image processing, e.g. FFDNet [36] or RCAN [37]. Furthermore, the denoiser may be trained on smaller patches of the reconstruction, rather than on the entire map as done here, and the patches may be combined using a sliding window.…”

Section: Conclusion and Discussionmentioning

confidence: 99%

Exploiting prior knowledge about biological macromolecules in cryo-EM structure determination

Kimanius

Zickert

Nakane

et al. 2020

Preprint

View full text Add to dashboard Cite

Three-dimensional reconstruction of the electron scattering potential of biological macromolecules from electron cryo-microscopy (cryo-EM) projection images is an ill-posed problem. The most popular cryo-EM software solutions to date rely on a regularisation approach that is based on the prior assumption that the scattering potential varies smoothly over three-dimensional space. Although this approach has been hugely successful in recent years, the amount of prior knowledge it exploits compares unfavourably to the knowledge about biological structures that has been accumulated over decades of research in Structural Biology. Here, we present a regularisation framework for cryo-EM structure determination that exploits prior knowledge about biological structures through a convolutional neural network that is trained on known macromolecular structures. We insert this neural network into the iterative cryo-EM structure determination process through an approach that is inspired by Regularisation by Denoising. We show that the new regularisation approach yields better reconstructions than the current state-of-the-art for simulated data and discuss options to extend this work for application to experimental cryo-EM data.

show abstract

Section: Conclusion and Discussionmentioning

confidence: 99%

Exploiting prior knowledge about biological macromolecules in cryo-EM structure determination

Kimanius

Zickert

Nakane

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Their network is more efficient, because it builds the HR image only at the very end. Other works, such as [29], proposed deeper architectures, focusing strictly on accuracy. Indeed, Zhang et al [29] presented one of the deepest CNNs used for SR, composed of 400 layers.…”

Section: Related Workmentioning

confidence: 99%

Convolutional Neural Networks With Intermediate Loss for 3D Super-Resolution of CT and MRI Scans

Ionescu

Verga

2020

IEEE Access

View full text Add to dashboard Cite

Computed Tomography (CT) scanners that are commonly-used in hospitals and medical centers nowadays produce low-resolution images, e.g. one voxel in the image corresponds to at most onecubic millimeter of tissue. In order to accurately segment tumors and make treatment plans, radiologists and oncologists need CT scans of higher resolution. The same problem appears in Magnetic Resonance Imaging (MRI). In this paper, we propose an approach for the single-image super-resolution of 3D CT or MRI scans. Our method is based on deep convolutional neural networks (CNNs) composed of 10 convolutional layers and an intermediate upscaling layer that is placed after the first 6 convolutional layers. Our first CNN, which increases the resolution on two axes (width and height), is followed by a second CNN, which increases the resolution on the third axis (depth). Different from other methods, we compute the loss with respect to the ground-truth high-resolution image right after the upscaling layer, in addition to computing the loss after the last convolutional layer. The intermediate loss forces our network to produce a better output, closer to the ground-truth. A widely-used approach to obtain sharp results is to add Gaussian blur using a fixed standard deviation. In order to avoid overfitting to a fixed standard deviation, we apply Gaussian smoothing with various standard deviations, unlike other approaches. We evaluate the proposed method in the context of 2D and 3D super-resolution of CT and MRI scans from two databases, comparing it to related works from the literature and baselines based on various interpolation schemes, using 2× and 4× scaling factors. The empirical study shows that our approach attains superior results to all other methods. Moreover, our subjective image quality assessment by human observers reveals that both doctors and regular annotators chose our method in favor of Lanczos interpolation in 97.55% cases for an upscaling factor of 2× and in 96.69% cases for an upscaling factor of 4×. In order to allow others to reproduce our state-of-the-art results, we provide our code as open source at https://github.com/lilygeorgescu/3d-super-res-cnn. INDEX TERMSConvolutional neural networks, single-image super-resolution, CT images, MRI images, medical image super-resolution.

show abstract

“…The adjacent band number K is set to 64, the downsample ratio r is set to 10 as in [12] and the trade-off parameter λ is equal to 10 during all the training procedure. We use the truncated normal distribution to initialize the weights and train the network from scratch.…”

Section: Implementation Detailsmentioning

confidence: 99%

ADRN: Attention-Based Deep Residual Network for Hyperspectral Image Denoising

Zhao

Zhai

Jiang

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Hyperspectral image (HSI) denoising is of crucial importance for many subsequent applications, such as HSI classification and interpretation. In this paper, we propose an attention-based deep residual network to directly learn a mapping from noisy HSI to the clean one. To jointly utilize the spatial-spectral information, the current band and its K adjacent bands are simultaneously exploited as the input. Then, we adopt convolution layer with different filter sizes to fuse the multi-scale feature, and use shortcut connection to incorporate the multi-level information for better noise removal. In addition, the channel attention mechanism is employed to make the network concentrate on the most relevant auxiliary information and features that are beneficial to the denoising process best. To ease the training procedure, we reconstruct the output through a residual mode rather than a straightforward prediction. Experimental results demonstrate that our proposed ADRN scheme outperforms the state-ofthe-art methods both in quantitative and visual evaluations.

show abstract

Image Super-Resolution Using Very Deep Residual Channel Attention Networks

Cited by 3,060 publications

References 45 publications

Exploiting prior knowledge about biological macromolecules in cryo-EM structure determination

Exploiting prior knowledge about biological macromolecules in cryo-EM structure determination

Convolutional Neural Networks With Intermediate Loss for 3D Super-Resolution of CT and MRI Scans

ADRN: Attention-Based Deep Residual Network for Hyperspectral Image Denoising

Contact Info

Product

Resources

About