Now you will not surprise anyone with filters that improve the quality of photos. But restoring old portraits still leaves much to be desired. Older photos are usually too blurred, so normal image sharpening methods will not work on them.
The Tantcentarc team has developed a new algorithm for improving old photographic portraits based on a combination of two earlier generative methods – a generative opposing network (GFP -GAN).
The first method is trying to isolate any digital noise and improve the face areas in the photo, while the second method is trying to reject unsuccessful options generated by the first.
According to scientists, this approach allows you to achieve higher quality of face restoration compared to previous methods and algorithms.
Everyone can assess the work of scientists and try to restore old snaps to https://huggingface.co/spaces/akhaliq/gfpgan
More details about the GFP-GAN method can be found in https://github.com/tencentarc/gfpgan
