当前位置: X-MOL 学术IEEE J. Sel. Top. Signal 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.)
Multi-Scale Image Super-Resolution Via a Single Extendable Deep Network
IEEE Journal of Selected Topics in Signal Processing ( IF 8.7 ) Pub Date : 2020-12-16 , DOI: 10.1109/jstsp.2020.3045282
Huanrong Zhang 1 , Jie Xiao 1 , Zhi Jin 1
Affiliation  

Deep neural networks have achieved remarkable success in single image super-resolution (SISR). However, in most cases, image SR with different scale factors is considered as different tasks and solved by training specific models. It makes the image SR applications inefficient and tedious. Hence, to tackle these problems, we propose a lightweight and fast network (MSWSR) to implement multi-scale SR simultaneously by learning multi-level wavelet coefficients of the target image. The proposed network is composed of one CNN part and one RNN part. The CNN part is used for predicting the highest-level low-frequency wavelet coefficients, while the RNN part is used for predicting the rest frequency bands of wavelet coefficients. Moreover, the RNN part is extendable to more scales. For further lightweight, a non-square (side window) convolution kernel is proposed to reduce the network parameters. Experiments on commonly-used datasets demonstrate that the proposed method achieves favorable reconstruction performance with a fast speed and lightweight network. The code is available at https://github.com/FVL2020/MSWSR .

中文翻译:

通过单个可扩展深度网络进行多尺度图像超分辨率

深度神经网络在单图像超分辨率(SISR)中取得了显著成功。但是,在大多数情况下,具有不同比例因子的图像SR被视为不同的任务,并通过训练特定模型来解决。这使得图像SR应用程序效率低下且乏味。因此,为了解决这些问题,我们提出了一种轻量级的快速网络(MSWSR),通过学习目标图像的多级小波系数来同时实现多尺度SR。所提出的网络由一个CNN部分和一个RNN部分组成。CNN部分用于预测最高级别的低频小波系数,而RNN部分用于预测小波系数的其余频带。此外,RNN部分可扩展到更多比例。为了进一步减轻重量,为了减少网络参数,提出了一个非正方形(侧窗)卷积核。对常用数据集的实验表明,该方法具有快速,轻量级的网络,具有良好的重建性能。该代码位于https://github.com/FVL2020/MSWSR
更新日期:2021-02-23
down
wechat
bug