RSDiff: Remote Sensing Image Generation from Text Using Diffusion Model
This addresses the need for high-quality satellite imagery in remote sensing analysis, though it appears incremental as it builds on existing diffusion model techniques.
The paper tackles generating high-resolution satellite images from text by proposing a two-stage diffusion model, achieving improved spatial resolution and accurate geographical details compared to existing models.
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 (RSICD) demonstrate that our method outperforms existing models, producing satellite images with accurate geographical details and improved spatial resolution.