Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network

Ahn, Namhyuk; Kang, Bada; Sohn, Kyung-Ah

doi:10.1007/978-3-030-01249-6_16

Cited by 891 publications

(854 citation statements)

References 31 publications

Supporting

Mentioning

768

Contrasting

Order By: Relevance

“…For lightweight networks, Hui et al [11] developed the information distillation network for better exploiting hierarchical features by separation processing of the current feature maps. And Ahn [2] designed an architecture that implemented a cascading mechanism on a residual network to boost the performance.…”

Section: Single Image Super-resolutionmentioning

confidence: 99%

“…We evaluate the performance of the super-resolved images using two metrics, including peak signalto-noise ratio (PSNR) and structure similarity index (SSIM) [30]. As with existing works [2,11,12,18,24,36,38], we calculate the values on the luminance channel (i.e., Y channel of the YCbCr channels converted from the RGB channels). Additionally, for any/unknown scale factor experiments, we use RealSR dataset from NTIRE2019 Real Super-Resolution Challenge 1 .…”

Section: Experiments 41 Datasets and Metricsmentioning

confidence: 99%

“…To address this issue, the better way is to design the lightweight and efficient network structures that avoid using recursive paradigm. Ahn et al developed CARN-M [2] for mobile scenario through a cascading network architecture, but it is at the cost of a substantial reduction on PSNR. Hui et al [11] proposed an information distillation network (IDN) that explicitly divided the preceding extracted features into two parts, one was retained and another was further processed.…”

Section: Introductionmentioning

confidence: 99%

“…And RCAN has only 16M parameters, its depth is up to 415 and results in very slow inference speed. Compared with CARN[2] and EDSR-baseline[18],…”

mentioning

confidence: 99%

See 3 more Smart Citations

Lightweight Image Super-Resolution with Information Multi-distillation Network

Hui

Gao

Yang

et al. 2019

Proceedings of the 27th ACM International Conference on Multimedia

660

426

View full text Add to dashboard Cite

In recent years, single image super-resolution (SISR) methods using deep convolution neural network (CNN) have achieved impressive results. Thanks to the powerful representation capabilities of the deep networks, numerous previous ways can learn the complex non-linear mapping between low-resolution (LR) image patches and their high-resolution (HR) versions. However, excessive convolutions will limit the application of super-resolution technology in low computing power devices. Besides, super-resolution of any arbitrary scale factor is a critical issue in practical applications, which has not been well solved in the previous approaches. To address these issues, we propose a lightweight information multi-distillation network (IMDN) by constructing the cascaded information multidistillation blocks (IMDB), which contains distillation and selective fusion parts. Specifically, the distillation module extracts hierarchical features step-by-step, and fusion module aggregates them according to the importance of candidate features, which is evaluated by the proposed contrast-aware channel attention mechanism. To process real images with any sizes, we develop an adaptive cropping strategy (ACS) to super-resolve block-wise image patches using the same well-trained model. Extensive experiments suggest that the proposed method performs favorably against the state-of-the-art SR algorithms in term of visual quality, memory footprint, and inference time. Code is available at https://github.com/Zheng222/IMDN.

show abstract

Section: Single Image Super-resolutionmentioning

confidence: 99%

Section: Experiments 41 Datasets and Metricsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…And RCAN has only 16M parameters, its depth is up to 415 and results in very slow inference speed. Compared with CARN[2] and EDSR-baseline[18],…”

mentioning

confidence: 99%

See 2 more Smart Citations

Lightweight Image Super-Resolution with Information Multi-distillation Network

Hui

Gao

Yang

et al. 2019

Proceedings of the 27th ACM International Conference on Multimedia

660

426

View full text Add to dashboard Cite

show abstract

“…A number of neural network-based SR models were proposed. According to different model designs, these models can be categorized into linear models such as SRCNN [9] and VDSR [10], residual models like CARN [11] and REDNet [12], recursive models like DRCN [13] and DRRN [14], densely connected models RDN [15] and D-DBPN [16], attentionbased models with SelNet [17] and RCAN [18] as examples, progressive models SCN [19] and LapSRN [20], and generative adversarial network (GAN) models EnhanceNet [21] and SRGAN [22].…”

Section: Introductionmentioning

confidence: 99%

Multi-Contrast Super-Resolution MRI Through a Progressive Network

Lyu

Shan

Steber

et al. 2020

IEEE Trans. Med. Imaging

116

View full text Add to dashboard Cite

Magnetic resonance imaging (MRI) is widely used for screening, diagnosis, image-guided therapy, and scientific research. A significant advantage of MRI over other imaging modalities such as computed tomography (CT) and nuclear imaging is that it clearly shows soft tissues in multi-contrasts. Compared with other medical image super-resolution (SR) methods that are in a single contrast, multi-contrast super-resolution studies can synergize multiple contrast images to achieve better super-resolution results. In this paper, we propose a one-level non-progressive neural network for low up-sampling multicontrast super-resolution and a two-level progressive network for high up-sampling multi-contrast super-resolution. Multicontrast information is combined in high-level feature space. Our experimental results demonstrate that the proposed networks can produce MRI super-resolution images with good image quality and outperform other multi-contrast super-resolution methods in terms of structural similarity and peak signal-to-noise ratio. Also, the progressive network produces a better SR image quality than the non-progressive network, even if the original low-resolution images were highly down-sampled.

show abstract