Recently, the performance of single image super-resolution (SR) has been significantly improved with powerful networks. However, these networks are developed for image SR with a single specific integer scale (e.g., x2;x3,x4), and cannot be used for non-integer and asymmetric SR. In this paper, we propose to learn a scale-arbitrary image SR network from scale-specific networks. Specifically, we propose a plug-in module for existing SR networks to perform scale-arbitrary SR, which consists of multiple scale-aware feature adaption blocks and a scale-aware upsampling layer. Moreover, we introduce a scale-aware knowledge transfer paradigm to transfer knowledge from scale-specific networks to the scale-arbitrary network. Our plug-in module can be easily adapted to existing networks to achieve scale-arbitrary SR. These networks plugged with our module can achieve promising results for non-integer and asymmetric SR while maintaining state-of-the-art performance for SR with integer scale factors. Besides, the additional computational and memory cost of our module is very small.
翻译:最近,通过强大的网络,单一图像超分辨率(SR)的性能有了显著改善,然而,这些网络是为单一特定整数的图像SR(例如,x2;x3x4)开发的,不能用于非整数和不对称SR。在本文中,我们提议从特定规模的网络中学习一个尺度任意图像SR(SR)网络。具体地说,我们提议为现有的斯洛伐克网络提供一个插座模块,以实施比例的任意SR(SSR),该模块由多个比例特征适应区块和比例的升级层组成。此外,我们还引入一个规模意识知识转移模式,将特定规模的网络的知识转移到规模的任意网络。我们的插座模块可以很容易地适应现有网络,以实现比例的任意SR。这些与我们的模块连接的网络可以取得有希望的结果,即不匹配和不对称的SR(SR),同时以整数规模因素保持斯洛伐克的状态和艺术性能。此外,我们模块的额外计算和记忆成本非常小。