ProjectsProject Details

In recent years, the use of deep features as an image perceptual descriptor is very popular, mainly for measuring the perceptual similarity between two images. In the field of image restoration, this has proved to be very useful for tasks such as super-resolution and style transfer. In this project, we suggest a different direction: rather than using deep features as a similarity measure, we suggest using them to construct a natural image prior. This can be done by learning the statistics of natural image's deep features. Using this special prior, we can gain from both world: the deep one, and the "classic" one. In this project our goal is to learn images prior using deep features and then probing it is possible to perform a generic Image restoration on corrupted images using the mentioned prior.