Look-up table(LUT)-based methods have shown the great efficacy in single image super-resolution (SR) task. However, previous methods ignore the essential reason of restricted receptive field (RF) size in LUT, which is caused by the interaction of space and channel features in vanilla convolution. They can only increase the RF at the cost of linearly increasing LUT size. To enlarge RF with contained LUT sizes, we propose a novel Reconstructed Convolution(RC) module, which decouples channel-wise and spatial calculation. It can be formulated as $n^2$ 1D LUTs to maintain $n\times n$ receptive field, which is obviously smaller than $n\times n$D LUT formulated before. The LUT generated by our RC module reaches less than 1/10000 storage compared with SR-LUT baseline. The proposed Reconstructed Convolution module based LUT method, termed as RCLUT, can enlarge the RF size by 9 times than the state-of-the-art LUT-based SR method and achieve superior performance on five popular benchmark dataset. Moreover, the efficient and robust RC module can be used as a plugin to improve other LUT-based SR methods. The code is available at https://github.com/liuguandu/RC-LUT.

翻译：查询表（LUT）方法在单图像超分辨率（SR）任务中展现出卓越性能。然而，现有方法忽略了LUT中感受野（RF）尺寸受限的本质原因——标准卷积中空间与通道特征的耦合效应。它们只能以线性增加LUT尺寸为代价来扩大感受野。为在可控LUT尺寸下扩大感受野，本文提出新型重构卷积（RC）模块，该模块解耦了通道计算与空间计算。该模块可表示为$n^2$个一维LUT以维持$n\times n$的感受野，显著小于此前构建的$n\times n$维LUT。通过RC模块生成的LUT存储量较SR-LUT基线降低至1/10000以下。基于重构卷积模块的LUT方法（RCLUT）可将感受野尺寸提升至当前最优LUT超分辨率方法的9倍，并在五个主流基准数据集上取得优越性能。此外，高效鲁棒的RC模块可作为插件提升其他基于LUT的超分辨率方法。相关代码已开源至https://github.com/liuguandu/RC-LUT。