Blind Facial Image Quality Enhancement using Non-Rigid Semantic Patches

TL;DR

This paper introduces a novel method for facial image enhancement that leverages semantic patches and registration algorithms to improve quality without prior knowledge of degradation, demonstrated on cellular photos.

Contribution

It presents a new technique combining semantic data and adaptive patches for facial image enhancement, overcoming traditional processing limitations.

Findings

Significant visual and quantitative quality improvements in facial images.

Effective enhancement across different identities, expressions, and poses.

Applicable to cellular photography of dark facial images.

Abstract

We propose to combine semantic data and registration algorithms to solve various image processing problems such as denoising, super-resolution and color-correction. It is shown how such new techniques can achieve significant quality enhancement, both visually and quantitatively, in the case of facial image enhancement. Our model assumes prior high quality data of the person to be processed, but no knowledge of the degradation model. We try to overcome the classical processing limits by using semantically-aware patches, with adaptive size and location regions of coherent structure and context, as building blocks. The method is demonstrated on the problem of cellular photography enhancement of dark facial images for different identities, expressions and poses.