arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2203.01645eess.IVcs.AIcs.CVcs.LGcs.MM
收藏

实图像去噪的选择性残差M-网

Selective Residual M-Net for Real Image Denoising

National Chung Hsing University(国立中兴大学);National Taichung University of Science and Technology(国立台中科技大学)

Chi-Mao Fan, Tsung-Jung Liu, Kuan-Hsien Liu

摘要:

图像恢复是一个低层次的视觉任务,它是将退化的图像恢复为无噪声的图像。随着深度神经网络的成功,卷积神经网络超越了传统的恢复方法,成为计算机视觉领域的主流。为了提高去噪算法的性能,本文提出了一种基于U-Net改进的分层结构的盲实图像去噪网络(SRMNet)。具体来说,我们使用一个选择性核与残留块的层次结构称为M-Net丰富的多尺度语义信息。此外,我们的SRMNet在定量指标和视觉质量方面对两个合成数据集和两个真实噪声数据集具有竞争力的性能结果。源代码和预训练模型可在https://github.com/TentativeGitHub/SRMNet上获得。

英文摘要:

Image restoration is a low-level vision task which is to restore degraded images to noise-free images. With the success of deep neural networks, the convolutional neural networks surpass the traditional restoration methods and become the mainstream in the computer vision area. To advance the performanceof denoising algorithms, we propose a blind real image denoising network (SRMNet) by employing a hierarchical architecture improved from U-Net. Specifically, we use a selective kernel with residual block on the hierarchical structure called M-Net to enrich the multi-scale semantic information. Furthermore, our SRMNet has competitive performance results on two synthetic and two real-world noisy datasets in terms of quantitative metrics and visual quality. The source code and pretrained model are available at https://github.com/TentativeGitHub/SRMNet.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑