If you have ever taken photos after the sun has gone down, you are probably familiar with the 'noise' that distorts the quality of a picture you have taken.
It is possible to fix your images to some degree with certain software, however, AI developed by Nvidia, MIT and Aalto University can go much further. The Noise2Noise AI was trained using 50,000 pictures – as well as MRI scans and computer-generated images – that had randomised noise added to them.
In their paper, the researchers show that their AI can successfully remove enough noise to make the pictures usable again, with details and clarity that's remarkably close to the source images. The AI could likely find use in software for cleaning up noisy photos captured in low-light conditions on phones and cameras, as well as improving astronomical imagery and MRI scanning.
The Noise2Noise paper will be presented at the Thirty-fifth International Conference on Machine Learning in Sweden this week, but in the meantime, you can read the paper here or watch the video below to see the program in action.