Reconstructed Convolution Module Based Look-Up Tables for Efficient Image Super-Resolution
This work addresses efficiency and performance bottlenecks in LUT-based super-resolution methods, offering a plugin module for broader application, though it is incremental in improving existing LUT approaches.
The paper tackles the limited receptive field in look-up table (LUT) methods for image super-resolution by proposing a Reconstructed Convolution module that decouples channel-wise and spatial calculations, achieving a 9x larger receptive field with less than 1/10000 storage compared to the baseline and superior performance on five benchmarks.
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.