HATSAT - Super-Resolution for Satellite Images
Upload a satellite image or select a sample to enhance its resolution by 4x.
⚠️ Important: Images must be exactly 130x130 pixels for the model to work properly.
Base Model: HAT (Hybrid Attention Transformer)
This model is a fine tuned version of HAT:
- GitHub Repository: https://github.com/XPixelGroup/HAT
- Paper: Activating More Pixels in Image Super-Resolution Transformer
- Authors: Xiangyu Chen, Xintao Wang, Jiantao Zhou, Yu Qiao, Chao Dong
Training Dataset: SEN2NAIPv2
The model was fine-tuned using the SEN2NAIPv2 dataset:
- HuggingFace Dataset: https://huggingface.co/datasets/tacofoundation/SEN2NAIPv2
- Description: High-resolution satellite imagery dataset for super-resolution tasks
Sample Images (click to select):