With the recently massive development in convolution neural networks, numerous lightweight CNN-based image super-resolution methods have been proposed for practical deployments on edge devices. However, most existing methods focus on one specific aspect: network or loss design, which leads to the difficulty of minimizing the model size. To address the issue, we conclude block devising, architecture searching, and loss design to obtain a more efficient SR structure. In this paper, we proposed an edge-enhanced feature distillation network, named EFDN, to preserve the high-frequency information under constrained resources. In detail, we build an edge-enhanced convolution block based on the existing reparameterization methods. Meanwhile, we propose edge-enhanced gradient loss to calibrate the reparameterized path training. Experimental results show that our edge-enhanced strategies preserve the edge and significantly improve the final restoration quality. Code is available at https://github.com/icandle/EFDN.
翻译:随着神经网络的演化最近出现大规模发展,为在边缘装置上的实际部署提出了许多轻量级CNN图像超分辨率方法。然而,大多数现有方法侧重于一个具体方面:网络或损失设计,导致模型尺寸的最小化困难。为了解决这个问题,我们完成了块设计、建筑搜索和损失设计,以获得一个效率更高的SR结构。在本文件中,我们提议了一个称为EFDN的边缘强化特征蒸馏网络,以在有限的资源下保存高频信息。详细说来,我们根据现有的再补偿方法建立一个边缘增强的混凝土块。与此同时,我们提议用边缘增强的梯度损失来校准再校准的路径训练。实验结果表明,我们的边缘强化战略能够保护边缘并大大改善最后的恢复质量。代码可在https://github.com/icandle/EFDN查阅。