SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution
This work addresses the problem of improving image super-resolution quality for applications like media enhancement, though it is incremental as it builds directly on SwinIR.
The authors tackled image super-resolution by proposing SwinFIR, which extends SwinIR with Fast Fourier Convolution to capture global information more efficiently, achieving state-of-the-art performance such as a PSNR of 32.83 dB on the Manga109 dataset, 0.8 dB higher than SwinIR.
Transformer-based methods have achieved impressive image restoration performance due to their capacities to model long-range dependency compared to CNN-based methods. However, advances like SwinIR adopts the window-based and local attention strategy to balance the performance and computational overhead, which restricts employing large receptive fields to capture global information and establish long dependencies in the early layers. To further improve the efficiency of capturing global information, in this work, we propose SwinFIR to extend SwinIR by replacing Fast Fourier Convolution (FFC) components, which have the image-wide receptive field. We also revisit other advanced techniques, i.e, data augmentation, pre-training, and feature ensemble to improve the effect of image reconstruction. And our feature ensemble method enables the performance of the model to be considerably enhanced without increasing the training and testing time. We applied our algorithm on multiple popular large-scale benchmarks and achieved state-of-the-art performance comparing to the existing methods. For example, our SwinFIR achieves the PSNR of 32.83 dB on Manga109 dataset, which is 0.8 dB higher than the state-of-the-art SwinIR method.