多尺度循环注意力网络运动模糊图像复原方法

在图像采集过程中，由于拍摄对象运动或相机自身运动造成的图像模糊对于后续的高级视觉任务会产生很不利的影响。针对当前深度学习图像去模糊方法不能兼顾去模糊效果和效率的问题，提出了一种多尺度循环注意力网络，使用深度可分离卷积降低参数量，改进注意力模块合理分配计算资源，对卷积层进行密集型连接提高参数利用效率，引入边缘损失提升生成图像边缘细节信息。经过实验验证，所提方法具有良好的泛化性能和鲁棒性，在Lai数据集和K?hler数据集上的SSIM和PSNR较近年典型方法的最佳效果分别提升了约1.15%、0.86%和0.91%、1.04%，在GoPro数据集上的平均单帧运行速度较同类方法提升约2.5倍。

Multi-scale recurrent attention network for image motion deblurring

In image acquisition process, the image blur caused by the moving subject or the camera itself will have a negative impact on the subsequent high-level vision tasks. Aiming at the problem that the current deep learning image deblurring method cannot balance the deblurring effect and efficiency, a multi-scale recurrent attention network was proposed, which used separable convolution to reduce the amount of parameters, and improved the attention module to allocate computing resources reasonably. Layers were used for dense connection to improve parameter utilization efficiency, and edge loss was introduced to improve the edge detail information in the generated image. Experiments prove that the proposed method has good generalization performance and robustness. Compared with the typical methods in recent years, the SSIM and PSNR have increased by about 1.15%, 0.86% and 0.91%, 1.04% on the Lai dataset and K?hler dataset, respectively. The average single frame running speed on the GoPro dataset is nearly 2.5 times faster than similar methods.