当前位置: X-MOL 学术IET Image Process. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Combination of multi-scale and residual learning in deep CNN for image denoising
IET Image Processing ( IF 2.3 ) Pub Date : 2020-10-15 , DOI: 10.1049/iet-ipr.2019.1386
Haiying Xia 1 , Fuyu Zhu 1 , Haisheng Li 1 , Shuxiang Song 1 , Xiangwei Mou 1
Affiliation  

To better restore a clean image from a noise observation under high noise levels, the authors propose an image denoising network based on the combination of multi-scale and residual learning. Instead of using filters with different large sizes in traditional multi-scale schemes, they arrange multi-layer convolutions with the filters of the same size to speed up the model. Some dilated convolutions of different rates are combined with the common convolutions to enrich the extracted features in multi-layer convolutions. Furthermore, they cascade the multi-layer convolutions with residual blocks to improve the performance of image denoising. Their extensive evaluations on several challenging datasets demonstrate that the proposed model outperforms the state-of-art methods under all different noise levels in terms of peak signal-to-noise ratio, and the visual effects achieved by the proposed model are also better than the competing methods.

中文翻译:

深度CNN中多尺度和残差学习相结合的图像去噪

为了更好地从高噪声水平下的噪声观察中恢复出清晰的图像,作者提出了一种基于多尺度学习和残差学习相结合的图像去噪网络。他们没有在传统的多尺度方案中使用具有不同大尺寸的滤波器,而是使用具有相同尺寸的滤波器来安排多层卷积,以加快模型的速度。将一些不同速率的膨胀卷积与普通卷积结合在一起,以丰富多层卷积中提取的特征。此外,他们将多层卷积与残差块级联,以提高图像去噪性能。他们对几个具有挑战性的数据集进行了广泛的评估,结果表明,在所有不同噪声水平下,就峰值信噪比而言,所提出的模型均优于最新方法。
更新日期:2020-10-16
down
wechat
bug