Coarse-to-fine strategies have been extensively used for the architecture design of single image deblurring networks. Conventional methods typically stack sub-networks with multi-scale input images and gradually improve sharpness of images from the bottom sub-network to the top sub-network, yielding inevitably high computational costs. Toward a fast and accurate deblurring network design, we revisit the coarse-to-fine strategy and present a multi-input multi-output U-net (MIMO-UNet). The MIMO-UNet has three distinct features. First, the single encoder of the MIMO-UNet takes multi-scale input images to ease the difficulty of training. Second, the single decoder of the MIMO-UNet outputs multiple deblurred images with different scales to mimic multi-cascaded U-nets using a single U-shaped network. Last, asymmetric feature fusion is introduced to merge multi-scale features in an efficient manner. Extensive experiments on the GoPro and RealBlur datasets demonstrate that the proposed network outperforms the state-of-the-art methods in terms of both accuracy and computational complexity. Source code is available for research purposes at https://github.com/chosj95/MIMO-UNet.
翻译:常规方法通常堆叠多级输入图像的子网络,逐步提高从底部子网络到顶部子网络的图像的清晰度,产生不可避免的高计算成本。为了快速和准确的拆解网络设计,我们重新审视粗到软的网络战略,并推出多投入多输出多输出Unet(IMO-UNet) 。MIMO-UNet有三个不同的特征。首先,MIMO-UNet的单个编码器采用多规模输入图像,以减轻培训难度。第二,MIMO-UNet的单个编码器从底部子网络到顶端子网络逐步地提高图像的清晰度,产生不可避免的高计算成本成本。为了利用一个单一的U形网络模拟多压缩Unet,我们重新审视了粗到软的网络,并提出了多输出多输出Unet(IMO-UNet)。GoPro和RealBur数据集的大规模实验表明,拟议的网络超越了UNMIMO/MO的复杂度/comart 数据计算方法。在httpsmacoal 95/MUB的精确度上, 两种方法都可用。