基于轻量化渐进式残差网络的图像快速去模糊

基于深度学习的去模糊方法已经取得了较大进展，但是随着网络层数加深，去模糊网络需要更多的计算资源和内存消耗，难以用于实际场景。针对目前的去模糊网络参数量大、运算时间长等问题，该文设计了一种轻量快速的渐进式残差去模糊网络。该网络使用浅层残差网络作为基准模型，可充分利用图像的局部特征信息，加强反向传播时的信息流通。同时，通过多阶段递归调用残差网络并进行参数共享，可大大简化网络模型，减少网络参数。为了进一步提高去模糊网络的特征重建能力，该文引入特征重标定模块进行特征融合，对输入图像与各个残差网络的输出特征图进行通道加权，并对特征图的空间信息进行自适应选择，实现更好的特征重建。实验结果表明，所提算法网络模型参数量小、运行速度快，大幅度领先于现有算法，且对各种空域可变模糊去除均可实现理想复原效果。

Fast Image Deblurring Based On the Lightweight Progressive Residual Network

Although deep learning-based methods show their superiority in the field of single image deblurring, it is difficult to be applied to practice for requiring more computing resources and memory consumption as network deepens. In this work, a lightweight and fast progressive residual network for image deburring is proposed. The network takes shallow residual network as basic model to make full use of the local feature information and strengthen the information flow during back propagation. By reusing the residual network recursively in subsequent several stages and sharing parameters, the network model can be greatly simplified and the parameters can be reduced. To improve the reconstruction performance of the network, the feature recalibration module is applied to feature fusion. The channel attention mechanism is applied to integrate input image and output feature map of each residual network, and then the spatial information of feature map is selected adaptively to achieve better feature reconstruction. Experimental results show that the proposed model has fast running speed with a small number of parameters, which is much better than the existing algorithms, and can produce quite promising results for the removal of spatial-invariant blurring.