The HF Image Inpainting deep learning package seamlessly integrates pretrained image inpainting models with ArcGIS, allowing you to restore missing or corrupted regions in satellite and aerial imagery directly within your GIS workflows. This deep learning package uses state-of-the-art generative architectures to intelligently inpaint areas affected by occlusions such as clouds, sensor gaps, or intentional redactions.
Before running a model, ensure compliance with its licensing terms, which can be found on the associated Hugging Face model page. Run only trusted models, as they include weights and code that could impact system security. Since model sizes vary, ensure adequate CPU/GPU memory is available for inference.
License requirements
To complete this workflow, the following are the license requirements:
- ArcGIS Desktop—ArcGIS Image Analyst extension for ArcGIS Pro
- ArcGIS Enterprise—ArcGIS Image Server with raster analytics configured
- ArcGIS Online—ArcGIS Pro or Professional Plus user type
Model details
This model has the following characteristics:
- Input—8-bit, 4-band imagery consisting of Red, Green, and Blue (RGB) bands and an additional binary mask band.
- Output—Raster with masked areas filled using spatial and contextual understanding.
- Compute—This workflow can run on CPU or GPU.
- Applicable geographies—This model is expected to work globally.
- Architecture—This deep learning package uses the model from the Hugging Face Object Detection Models page, given the model ID.
Access and download the model
Download the HF Image Inpainting pretrained model from ArcGIS Living Atlas of the World. Alternatively, access the model directly from ArcGIS Pro, or use it in ArcGIS Image for ArcGIS Online.
To download the model, complete the following steps:
- Browse to ArcGIS Living Atlas of the World.
- Sign in with your ArcGIS Online credentials.
- Search for HF Image Inpainting and open the item page from the search results.
- Click the Download button to download the model.
You can use the downloaded .dlpk file directly in ArcGIS Pro.
Release notes
The following are the release notes:
| Date | Description |
|---|---|
June 2025 | First release of HF Image Inpainting |