Multi-Scale Deep Neural Networks for Real Image Super-Resolution

Gao, Shangqi; Zhuang, Xiahai

doi:10.1109/cvprw.2019.00252

Cited by 34 publications

(14 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The DBPN [2] not only uses dense connection but also applies upsampling and downsampling alternatively on a single network to preserve HR features inside the network. The MsRN [27] extends the work of EDSR and the RDN to infer multi-scale HR images at the same time. EBRN [5] utilizes multiple block residual modules to restore different frequencies in models of different complexity, which reduces the problem of over-enhancing and over-smoothing.…”

Section: Related Workmentioning

confidence: 97%

Blind Image Super-Resolution with Spatial Context Hallucination

Dong¹,

Yang²

2020

Preprint

View full text Add to dashboard Cite

Deep convolution neural networks (CNNs) play a critical role in single image super-resolution (SISR) since the amazing improvement of high performance computing. However, most of the super-resolution (SR) methods only focus on recovering bicubic degradation. Reconstructing high-resolution (HR) images from randomly blurred and noisy lowresolution (LR) images is still a challenging problem. In this paper, we propose a novel Spatial Context Hallucination Network (SCHN) for blind super-resolution without knowing the degradation kernel. We find that when the blur kernel is unknown, separate deblurring and superresolution could limit the performance because of the accumulation of error. Thus, we integrate denoising, deblurring and super-resolution within one framework to avoid such a problem. We train our model on two high quality datasets, DIV2K and Flickr2K. Our method performs better than state-of-the-art methods when input images are corrupted with random blur and noise.

show abstract

Section: Related Workmentioning

confidence: 97%

Blind Image Super-Resolution with Spatial Context Hallucination

Dong¹,

Yang²

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Many techniques have been explored to improve the generalization ability of network for image restoration. Kim et al [21] and Gao et al [9] both proposed a joint-training strategy Figure 1: Overview of the network architecture. SCM is to realize DSR with different downscaling factors in an unified model, which allows to finely-grained control the depth restoration results by using a scale parameter, while DSM aims to learn a set of slicing branches in a divide-and-conquer manner, parameterized by a distance-aware weighting scheme to adaptively aggregate all the branches in the ensemble.…”

Section: Generalization Abilitymentioning

confidence: 99%

Depth Super-Resolution via Deep Controllable Slicing Network

Sun

Wang

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Due to the imaging limitation of depth sensors, high-resolution (HR) depth maps are often difficult to be acquired directly, thus effective depth super-resolution (DSR) algorithms are needed to generate HR output from its low-resolution (LR) counterpart. Previous methods treat all depth regions equally without considering different extents of degradation at region-level, and regard DSR under different scales as independent tasks without considering the modeling of different scales, which impede further performance improvement and practical use of DSR. To alleviate these problems, we propose a deep controllable slicing network from a novel perspective. Specifically, our model is to learn a set of slicing branches in a divide-and-conquer manner, parameterized by a distance-aware weighting scheme to adaptively aggregate different depths in an ensemble. Each branch that specifies a depth slice (e.g., the region in some depth range) tends to yield accurate depth recovery. Meanwhile, a scale-controllable module that extracts depth features under different scales is proposed and inserted into the front of slicing network, and enables finely-grained control of the depth restoration results of slicing network with a scale hyper-parameter. Extensive experiments on synthetic and real-world benchmark datasets demonstrate that our method achieves superior performance. CCS CONCEPTS • Computing methodologies → 3D imaging; Reconstruction.

show abstract

“…In order to solve the above problems, researchers have proposed the concept and model of multiscale convolutional neural networks in recent years [18,26,27]. e multiscale methods use convolution kernels of different scales to extract features on different scale layers of the image, and then fuse them, thus alleviating the loss of image feature information and improving the quality of super-resolution.…”

Section: Related Workmentioning

confidence: 99%

“…It performs feature fusion of different scale layers after each feature extraction module and then extracts the residuals between the fusion information of adjacent modules. Gao and Zhuang [26] developed a multiscale super-resolution method based on the deep neural network and showed the advantages of the multiscale residual dense network in feature extraction compared with the single-scale network. In addition, the enhanced deep super-resolution network [18] also utilizes multiscale residual blocks to eliminate gradient disappearance and gradient explosion.…”

Section: Related Workmentioning

confidence: 99%

Image Super-Resolution Using Lightweight Multiscale Residual Dense Network

Li¹,

Zhao²,

Fang

et al. 2020

International Journal of Optics

View full text Add to dashboard Cite

The current super-resolution methods cannot fully exploit the global and local information of the original low-resolution image, resulting in loss of some information. In order to solve the problem, we propose a multiscale residual dense network (MRDN) for image super-resolution. This network is constructed based on the residual dense network. It can integrate the multiscale information of the image and avoid losing too much information in the deep level of the network, while extracting more information under different receptive fields. In addition, in order to reduce the redundancy of the network parameters of MRDN, we further develop a lightweight parameter method and deploy it at different scales. This method can not only reduce the redundancy of network parameters but also enhance the nonlinear mapping ability of the network at different scales. Thus, it can better learn and fit the feature information of the original image and recover the satisfactory super-resolution image. Extensive experiments are conducted, which demonstrate the effectiveness of the proposed method.

show abstract

Multi-Scale Deep Neural Networks for Real Image Super-Resolution

Cited by 34 publications

References 25 publications

Blind Image Super-Resolution with Spatial Context Hallucination

Blind Image Super-Resolution with Spatial Context Hallucination

Depth Super-Resolution via Deep Controllable Slicing Network

Image Super-Resolution Using Lightweight Multiscale Residual Dense Network

Contact Info

Product

Resources

About