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

Recently, convolutional networks have achieved remarkable development inremote sensing image Super-Resoltuion (SR) by minimizing the regressionobjectives, e.g., MSE loss. However, despite achieving impressive performance,these methods often suffer from poor visual quality with over-smooth issues.Generative adversarial networks have the potential to infer intricate details,but they are easy to collapse, resulting in undesirable artifacts. To mitigatethese issues, in this paper, we first introduce Diffusion Probabilistic Model(DPM) for efficient remote sensing image SR, dubbed EDiffSR. EDiffSR is easy totrain and maintains the merits of DPM in generating perceptual-pleasant images.Specifically, different from previous works using heavy UNet for noiseprediction, we develop an Efficient Activation Network (EANet) to achievefavorable noise prediction performance by simplified channel attention andsimple gate operation, which dramatically reduces the computational budget.Moreover, to introduce more valuable prior knowledge into the proposed EDiffSR,a practical Conditional Prior Enhancement Module (CPEM) is developed to helpextract an enriched condition. Unlike most DPM-based SR models that directlygenerate conditions by amplifying LR images, the proposed CPEM helps to retainmore informative cues for accurate SR. Extensive experiments on four remotesensing datasets demonstrate that EDiffSR can restore visual-pleasant images onsimulated and real-world remote sensing images, both quantitatively andqualitatively. The code of EDiffSR will be available athttps://github.com/XY-boy/EDiffSR

EDiffSR: An Efficient Diffusion Probabilistic Model for Remote Sensing Image Super-Resolution