AboutΒΆ
superres-tomo is a package of useful scripts and models for applying neural networks for tomographic reconstruction of X-ray images. The package also includes models and scripts useful for the analysis of the images generated, allowing tasks such as semantic segmentation of very large images and removing noise from low dose images.
- The tasks possible with superres-tomo are
- Image reconstruction
- Image segmentation
- Image denoising
- Image super-resolution [coming soon]
- Image fusion for super-resolution [coming soon]
superres-tomo is a produced in collaboration between the SciML group from Rutherford Appleton Laboratory and Finden Ltd. The project has been funded by the AI3SD network
The project is also associated with a benchamrk dataset which can be used to test other super-resolution approaches on similar data.