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

Satellite imagery generation and super-resolution are pivotal tasks in remotesensing, demanding high-quality, detailed images for accurate analysis anddecision-making. In this paper, we propose an innovative and lightweightapproach that employs two-stage diffusion models to gradually generatehigh-resolution Satellite images purely based on text prompts. Our innovativepipeline comprises two interconnected diffusion models: a Low-ResolutionGeneration Diffusion Model (LR-GDM) that generates low-resolution images fromtext and a Super-Resolution Diffusion Model (SRDM) conditionally produced. TheLR-GDM effectively synthesizes low-resolution by (computing the correlations ofthe text embedding and the image embedding in a shared latent space), capturingthe essential content and layout of the desired scenes. Subsequently, the SRDMtakes the generated low-resolution image and its corresponding text prompts andefficiently produces the high-resolution counterparts, infusing fine-grainedspatial details and enhancing visual fidelity. Experiments are conducted on thecommonly used dataset, Remote Sensing Image Captioning Dataset (RSICD). Ourresults demonstrate that our approach outperforms existing state-of-the-art(SoTA) models in generating satellite images with realistic geographicalfeatures, weather conditions, and land structures while achieving remarkablesuper-resolution results for increased spatial precision.

RSDiff: Remote Sensing Image Generation from Text Using Diffusion Model