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

TL;DR

This paper introduces RCLUT, a novel LUT-based super-resolution method using a reconstructed convolution module to significantly enlarge receptive fields while reducing storage, outperforming previous methods on benchmark datasets.

Contribution

It proposes a reconstructed convolution module that decouples spatial and channel calculations, enabling larger receptive fields with smaller LUTs, and demonstrates its effectiveness in super-resolution tasks.

Findings

Enlarges receptive field by 9 times compared to state-of-the-art.

Reduces LUT storage to less than 1/10000 of baseline.

Achieves superior performance on five benchmark datasets.

Abstract

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.