Reconstruct Anything Model Demo

This demo showcases the performance of the Reconstruct Anything Model (RAM) across a variety of inverse problems on both natural and MRI images.
Select a dataset and a physics task below (e.g., inpainting, super-resolution, deblurring...).
Note: The parameters of the selected physics — such as noise levels, blur kernels, or inpainting masks — are randomly generated before reconstruction, leveraging the deepinverse library.

📄 For more details on the method, check out our paper on arXiv.