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 this https URL

本文介绍一种称为 RCLUT 的 LUT 方法，通过提出重构卷积模块来增加 LUT 的有效感受野大小，并在多个基准数据集上表现出更好的性能。

基于重构卷积模块的查找表高效图像超分辨率

Reconstructed Convolution Module Based Look-Up Tables for Efficient  Image Super-Resolution

We propose a quantized decoding algorithm for low- density parity-check codes
where the variable node update rule of the standard min-sum algorithm is
replaced with a look-up table (LUT) that is designed using an
information-theoretic criterion. We show that even with message resolutions as
low as 3 bits, the proposed algorithm can achieve better error rates than a
floating-point min-sum decoder. Moreover, we study in detail the effect of
different decoder design parameters, like the design SNR and the LUT tree
structure on the performance of our decoder, and we propose some complexity
reduction techniques, such as LUT re-use and message alphabet downsizing.

本文提出了一种用于低密度奇偶校验码的量化解码算法，其中，标准的最小和算法的变量节点更新规则被用信息论准则设计的查找表所替换。研究结果表明，即使使用只有 3 位消息分辨率的算法，也能比使用浮点数的最小和译码器取得更好的误码率；此外，研究了不同的译码器设计参数对译码性能的影响，如设计信噪比和查找表树结构等，并提出了一些复杂度约简技术，如查找表重用和消息字母表缩小。