Unsupervised perception-based image restoration of semi-transparent degradation using Lie group transformations

This paper presents a generalized model for the removal of semi-transparent defects from images of historical or artistic value. Its main feature is the combination of Lie group transformations with human perception rules that makes restoration more flexible and adaptive to defects having different physical or mechanical causes. Specifically, Lie groups allow to define a redundant set of transformations from which it is possible to automatically select the ones that better invert the physical formation of the defect. Hence, the restoration process consists of an iterative procedure whose main goal is to reduce defect visual perception. The proposed restoration method has been successfully tested on original movies and photographs, affected by line-scratches and semi-transparent blotches.