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

Remote sensing image super-resolution (RSISR) plays a vital role in enhancingspatial detials and improving the quality of satellite imagery. Recently,Transformer-based models have shown competitive performance in RSISR. Tomitigate the quadratic computational complexity resulting from globalself-attention, various methods constrain attention to a local window,enhancing its efficiency. Consequently, the receptive fields in a singleattention layer are inadequate, leading to insufficient context modeling.Furthermore, while most transform-based approaches reuse shallow featuresthrough skip connections, relying solely on these connections treats shallowand deep features equally, impeding the model's ability to characterize them.To address these issues, we propose a novel transformer architecture calledCross-Spatial Pixel Integration and Cross-Stage Feature Fusion BasedTransformer Network (SPIFFNet) for RSISR. Our proposed model effectivelyenhances global cognition and understanding of the entire image, facilitatingefficient integration of features cross-stages. The model incorporatescross-spatial pixel integration attention (CSPIA) to introduce contextualinformation into a local window, while cross-stage feature fusion attention(CSFFA) adaptively fuses features from the previous stage to improve featureexpression in line with the requirements of the current stage. We conductedcomprehensive experiments on multiple benchmark datasets, demonstrating thesuperior performance of our proposed SPIFFNet in terms of both quantitativemetrics and visual quality when compared to state-of-the-art methods.

Cross-Spatial Pixel Integration and Cross-Stage Feature Fusion Based Transformer Network for Remote Sensing Image Super-Resolution