Kernel-attended residual network for single image super-resolution

Kernel-attended residual network for single image super-resolution
复制标题

用于单图像超分辨率的内核参与残差网络

DOI:
10.1016/j.knosys.2020.106663
复制
发表时间:
2020-12
影响因子:
8.8
通讯作者:
Xueming Qian
Xueming Qian
中科院分区:
计算机科学1区
文献类型:
--
作者:
Yujie Dun;Zongyang Da;Shuai Yang;Yao Xue;Xueming Qian

文献摘要

参考文献

被引文献

相似文献

单幅图像的超分辨率是一项非常重要的底层计算机视觉任务。随着深度卷积神经网络(cnn)的发展,近年来使用cnn的方法在单幅图像超分辨率(SISR)领域已经超越了现有的传统方法。然而,这些方法可能会受到较弱的表征能力和过度平滑纹理的影响。为了解决这些问题,我们提出了一种核出席残余网络(KARN)。我们的KARN在特征融合和特征表示方面具有最优的性能。具体来说,我们提出了一种多通道融合块(MCFB)来恢复大量的文本特征信息,以及一种核参与块(KAB)来提高我们的多核网络的表示能力。此外,我们还提出了空间特征重新校准块(SFRB),将校准整合到空间方面的特征中。由于我们提取的高级信息,KARN通过基于基准数据集评估结果的性能,实现了比最先进的方法更显着的性能。
Single image super-resolution is very important as a low-level computer vision task. With the development of deep convolution neural networks (CNNs), recent approaches with CNNs have outperformed existing traditional methods in the single image super-resolution (SISR) field. However, these methods may suffer from weaker representational power and overly-smoothing textures. To handle these problems, we propose a Kernel-Attended Residual Network (KARN). Our KARN possesses the optimal performance for feature fusion and feature representation. Specifically, we present a multi-channel fusion block (MCFB) to restore plentiful textual feature information, and a kernel-attended block (KAB) to improve the representation power of our network with multiple kernels. Besides, we present a space-feature re-calibration block (SFRB) to integrate the calibration into features in the spatial aspect. Owing to the advanced information that we extract, KARN achieves a more notable performance than state-of-the-art methods by evaluating the performance of results based on benchmark datasets.
DOI: 10.1109/tip.2006.877407
发表时间: 2006-08-01
影响因子: 10.6
作者:
Zhang, Lei;Wu, Xiaolin
通讯作者: Wu, Xiaolin
DOI: 10.1002/mrm.27178
发表时间: 2018-11
影响因子: 3.3
作者:
Chaudhari AS;Fang Z;Kogan F;Wood J;Stevens KJ;Gibbons EK;Lee JH;Gold GE;Hargreaves BA
通讯作者: Hargreaves BA
DOI: 10.1109/tci.2016.2644865
发表时间: 2017-03-01
影响因子: 5.4
作者:
Zhao, Hang;Gallo, Orazio;Kautz, Jan
通讯作者: Kautz, Jan
DOI: 10.1109/cvpr.2012.6247930
发表时间: 2012-06
期刊: 2012 IEEE Conference on Computer Vision and Pattern Recognition
影响因子: --
作者:
Shenlong Wang;Lei Zhang;Yan Liang;Q. Pan
通讯作者: Shenlong Wang;Lei Zhang;Yan Liang;Q. Pan
JCS-Net:用于监控图像中小规模行人检测的联合分类和超分辨率网络
DOI: 10.1109/tifs.2019.2916592
发表时间: 2019-12-01
影响因子: 6.8
作者:
Pang, Yanwei;Cao, Jiale;Han, Jungong
通讯作者: Han, Jungong