---
license: creativeml-openrail-m
language:
- en
tags:
- stable-diffusion
- image-inpainting
- remote-sensing
- satellite
- vhr
- diffusion
- geospatial
library_name: diffusers
pipeline_tag: image-to-image
---
# ๐ฐ๏ธ KAO-DIFFSAT-VHR-v1 (Beta Version)
**Diffusion-based Satellite Image Inpainting (VHR) โ Baseline Release**
๐ Project website: https://kaopanboonyuen.github.io/KAO/
---
## ๐ฐ๏ธ Visual Overview
High-fidelity satellite image reconstruction across diverse scenes (urban, agricultural, coastal).
---
## ๐ Overview
**KAO-DIFFSAT-VHR-v1** is a satellite-domain adaptation of diffusion-based inpainting, designed for **Very High Resolution (VHR) remote sensing imagery**.
This release serves as a **baseline model** in our IEEE TGRS work:
> *KAO: Kernel-Adaptive Optimization in Diffusion for Satellite Image*
> ๐ **Accepted to IEEE Transactions on Geoscience and Remote Sensing (TGRS)**
> ๐ Presentation at **AOGS 2026, Japan**
โ ๏ธ **Important:**
This model is **NOT the KAO method itself**.
It is a **Stable Diffusionโbased inpainting backbone adapted for satellite imagery**, used as one of the reference baselines in our study.
๐ The full KAO framework (**training-free / prompt-free optimization**) will be released separately.
---
## ๐ง Positioning
| Component | Description |
|----------|------------|
| This Repo | Diffusion baseline for satellite inpainting |
| KAO (Paper) | Optimization-based enhancement (no retraining required) |
| Future Release | KAO-integrated inference (no prompt dependency) |
---
## ๐๏ธ Base Model
This model is built upon:
- Stable Diffusion v2 Inpainting
- Provided via the Hugging Face ecosystem
We adapt the pipeline for **remote sensing characteristics**, including:
- Large spatial structures (roads, rivers, urban layouts)
- Texture consistency across wide regions
- Geometric coherence in aerial perspective
---
## ๐ Key Features
- ๐ฐ๏ธ Satellite-aware inpainting behavior
- ๐ Improved structural consistency for urban layouts
- ๐ฟ Better handling of vegetation and natural textures
- ๐งฉ Compatible with standard diffusion pipelines (Diffusers)
---
## ๐ฌ Results Overview
**Qualitative comparison across multiple models. KAO demonstrates superior structural reconstruction and texture consistency.**
**Detailed comparison highlighting fine-grained structures and realistic spatial coherence.**
---
## ๐ฐ๏ธ Full Benchmark Results
Comparison across multiple scenes including urban, agricultural, and occluded environments.
KAO consistently preserves spatial structure, enhances texture fidelity, and improves reconstruction realism.
---
## โ ๏ธ What This Model Is (and Is Not)
### โ
This model:
- A **baseline diffusion model** for satellite inpainting
- Used for **comparative evaluation** in our research
- Suitable for prompt-based reconstruction tasks
### โ This model is NOT:
- The full **KAO algorithm**
- A training-free optimization method
- A prompt-free system
๐ Those capabilities are introduced in our paper and will be released in future versions.
---
## ๐ Usage (Diffusers)
```python
from diffusers import StableDiffusionInpaintPipeline
import torch
pipe = StableDiffusionInpaintPipeline.from_pretrained(
"kaopanboonyuen/KAO-DIFFSAT-VHR-v1",
torch_dtype=torch.float16
).to("cuda")
prompt = "High-resolution satellite image of urban area with missing regions reconstructed"
image = pipe(
prompt=prompt,
image=init_image,
mask_image=mask
).images[0]
````
---
## ๐ฐ๏ธ Prompt Guide (Satellite Domain)
Use prompts that enforce:
* spatial coherence
* structural realism
* geospatial consistency
### ๐น Template
```
High-resolution satellite image of [SCENE],
reconstruct missing regions with realistic [STRUCTURE],
maintain spatial consistency, natural textures, and accurate geometry
```
---
## ๐งช Use Cases
* Cloud removal in satellite imagery
* Infrastructure reconstruction
* Map completion
* Environmental monitoring
* Disaster recovery (flood, wildfire)
---
## โ ๏ธ Limitations
* Prompt-sensitive behavior
* Not optimized for hyperspectral imagery
* High memory footprint (~25GB)
* No explicit geospatial constraints (baseline only)
---
## ๐ฎ Roadmap
* ๐ KAO-DIFFSAT-v2 (KAO-integrated)
* ๐ Prompt-free inference (as proposed in paper)
* ๐ Lightweight and scalable variants
---
## ๐ Citation
### ๐น Base Model
```bibtex
@misc{stabilityai2022sd2,
title = {Stable Diffusion v2},
author = {{Stability AI}},
year = {2022},
howpublished = {\url{https://github.com/Stability-AI/stablediffusion}},
note = {Including inpainting variant}
}
```
### ๐น Our Work (KAO)
```bibtex
@article{panboonyuen2025kao,
title={KAO: Kernel-Adaptive Optimization in Diffusion for Satellite Image},
author={Panboonyuen, Teerapong},
journal={IEEE Transactions on Geoscience and Remote Sensing},
year={2025},
publisher={IEEE}
}
```
---
## ๐ฌ Project Overview
This repository presents **KAO-DIFFSAT-VHR-v1**, a diffusion-based framework for **very high-resolution (VHR) satellite image inpainting**, designed for geospatial restoration and reconstruction tasks.
The model builds upon Stable Diffusion-based inpainting and adapts it for remote sensing imagery.
---
## ๐ Paper
๐ Full paper available on arXiv:
https://arxiv.org/abs/2511.02462
---
## ๐ Project Page
๐ Project website:
https://kaopanboonyuen.github.io/KAO/
---
## ๐ค Acknowledgements
* Stability AI for foundational diffusion models
* Hugging Face for open model hosting
* Remote sensing community for datasets and benchmarks
---
## ๐ Vision
This project aims to advance:
> **Generative AI ร Earth Observation**
toward scalable, reliable, and interpretable satellite intelligence systems.
--- 
