Deep Face Deblurring

Grigorios G. Chrysos, Stefanos Zafeiriou; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017, pp. 69-78

Blind deblurring consists a long studied task, however the outcomes of generic methods are not effective in real world blurred images. Domain-specific methods for deblurring targeted object categories, frequently outperform their generic counterparts. In this work, we develop such a domain-specific method to tackle deblurring of human faces, henceforth referred to as face deblurring. Studying faces is of tremendous significance in computer vision, however face deblurring has yet to demonstrate some convincing results. This can be partly attributed to the combination of i) poor texture and ii) highly structure shape that yield the contour/gradient priors (that are typically used) sub-optimal. We adopt a learning approach by inserting weak supervision that exploits the well-documented structure of the face. We introduce an efficient framework that allows the generation of a large dataset. We utilised this framework to create 2MF^2, a dataset of over two million frames.