Blind Facial Image Quality Enhancement using Non-Rigid Semantic Patches
This addresses the challenge of improving dark facial images for photography applications, but it is incremental as it builds on existing semantic and registration techniques.
The paper tackles the problem of enhancing low-quality facial images from cellular photography without knowing the degradation model, achieving significant visual and quantitative quality improvements.
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.