基于空间自适应特征调制的高效图像超分辨率
Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolution
摘要:
尽管已经提出了许多用于图像超分辨率的解决方案,但是它们通常与具有许多计算和存储器约束的低功率设备不兼容。在本文中,我们通过提出一种简单而有效的深度网络来解决这个问题,以有效地解决图像超分辨率。详细地说,我们开发了一个空间自适应功能调制(SAFM)机制上的视觉Transformer(ViT)一样的块。在它里面,我们首先应用SAFM块在输入特征上动态地选择代表性的特征表示。由于SAFM块从远程角度处理输入特征,因此我们进一步引入了卷积信道混合器(CCM),以同时提取本地上下文信息并执行信道混合。大量的实验结果表明,所提出的方法是$3\times$小于最先进的有效SR方法,例如,就网络参数而言,IMDN需要更少的计算成本,同时实现相当的性能。该代码可在https://github.com/sunny2109/SAFMN上获得。
英文摘要:
Although numerous solutions have been proposed for image super-resolution, they are usually incompatible with low-power devices with many computational and memory constraints. In this paper, we address this problem by proposing a simple yet effective deep network to solve image super-resolution efficiently. In detail, we develop a spatially-adaptive feature modulation (SAFM) mechanism upon a vision transformer (ViT)-like block. Within it, we first apply the SAFM block over input features to dynamically select representative feature representations. As the SAFM block processes the input features from a long-range perspective, we further introduce a convolutional channel mixer (CCM) to simultaneously extract local contextual information and perform channel mixing. Extensive experimental results show that the proposed method is $3\times$ smaller than state-of-the-art efficient SR methods, e.g., IMDN, in terms of the network parameters and requires less computational cost while achieving comparable performance. The code is available at https://github.com/sunny2109/SAFMN.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。