English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Transformer-based methods have achieved impressive image restorationperformance due to their capacities to model long-range dependency compared toCNN-based methods. However, advances like SwinIR adopts the window-based andlocal attention strategy to balance the performance and computational overhead,which restricts employing large receptive fields to capture global informationand establish long dependencies in the early layers. To further improve theefficiency of capturing global information, in this work, we propose SwinFIR toextend SwinIR by replacing Fast Fourier Convolution (FFC) components, whichhave the image-wide receptive field. We also revisit other advanced techniques,i.e, data augmentation, pre-training, and feature ensemble to improve theeffect of image reconstruction. And our feature ensemble method enables theperformance of the model to be considerably enhanced without increasing thetraining and testing time. We applied our algorithm on multiple popularlarge-scale benchmarks and achieved state-of-the-art performance comparing tothe existing methods. For example, our SwinFIR achieves the PSNR of 32.83 dB onManga109 dataset, which is 0.8 dB higher than the state-of-the-art SwinIRmethod.

SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution