Deep Restoration of Vintage Photographs From Scanned Halftone Prints

A great number of invaluable historical photographs unfortunately only exist in the form of halftone prints in old publications such as newspapers or books. Their original continuous-tone films have long been lost or irreparably damaged. There have been attempts to digitally restore these vintage halftone prints to the original film quality or higher. However, even using powerful deep convolutional neural networks, it is still difficult to obtain satisfactory results. The main challenge is that the degradation process is complex and compounded while almost no paired real data is available for machine learning. In this research, we develop a novel learning strategy, in which the restoration task is divided into two stages: the removal of printing artifacts and the inverse of halftoning. The advantage of our technique is that only the simple first stage, which makes the method adapt to real halftone prints, requires unsupervised training, while the more complex second stage of inverse halftoning only uses synthetic training data. Extensive experiments demonstrate the efficacy of the proposed technique for real halftone prints; the new technique significantly outperforms the existing ones in visual quality.