RSDiff: remote sensing image generation from text using diffusion model
Neural Computing and Applications · 2024-12 · 36 (36) · 23103-23111
DOI: 10.1007/s00521-024-10363-3 ↗Kurz gefasst
Fachartikel in der Zeitschrift Neural Computing and Applications, online erschienen am 05.10.2024. Verfasst von Ahmad Sebaq und 1 weiteren Autor:innen. Die Arbeit wurde bisher 73-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Nile University.
Abstract (Originalsprache)
The generation and enhancement of satellite imagery are critical in remote sensing, requiring high-quality, detailed images for accurate analysis. This research introduces a two-stage diffusion model methodology for synthesizing high-resolution satellite images from textual prompts. The pipeline comprises a low-resolution diffusion model (LRDM) that generates initial images based on text inputs and a super-resolution diffusion model (SRDM) that refines these images into high-resolution outputs. The LRDM merges text and image embeddings within a shared latent space, capturing essential scene content and structure. The SRDM then enhances these images, focusing on spatial features and visual clarity. Experiments conducted using the Remote Sensing Image Captioning Dataset demonstrate that our method outperforms existing models, producing satellite images with accurate geographical details and improved spatial resolution.
Förderung
- Nile University
Zitieren
APA
Sebaq, A., & ElHelw, M. (2024). RSDiff: remote sensing image generation from text using diffusion model. Neural Computing and Applications, 36(36), 23103-23111. https://doi.org/10.1007/s00521-024-10363-3
Vancouver
Sebaq A, ElHelw M. RSDiff: remote sensing image generation from text using diffusion model. Neural Computing and Applications. 2024;36(36):23103-23111. doi:10.1007/s00521-024-10363-3
BibTeX
@article{Sebaq2024,
author = {Sebaq, Ahmad and ElHelw, Mohamed},
title = {RSDiff: remote sensing image generation from text using diffusion model},
journal = {Neural Computing and Applications},
year = {2024},
volume = {36},
number = {36},
pages = {23103--23111},
doi = {10.1007/s00521-024-10363-3}
}
EUVIMED