mashhoodnnjjjj/masked_autoencoder
0
🎭 Masked Autoencoder — Image Reconstruction
Upload any image and watch a Vision Transformer-based MAE reconstruct it from only a fraction of the visible patches.
Model Architecture
How to Use
- Upload a JPG or PNG image
- Adjust the Mask Ratio slider (default 75%)
- Click Reconstruct
- Compare Original → Masked Input → Reconstruction side by side
