RSDiff: Remote Sensing Image Generation from Text Using Diffusion Model
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929528477057024 |
|---|---|
| author | Sebaq, Ahmad ElHelw, Mohamed |
| author_facet | Sebaq, Ahmad ElHelw, Mohamed |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_02455 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | RSDiff: Remote Sensing Image Generation from Text Using Diffusion Model Sebaq, Ahmad ElHelw, Mohamed Computer Vision and Pattern Recognition 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. |
| title | RSDiff: Remote Sensing Image Generation from Text Using Diffusion Model |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2309.02455 |