Deep Restore

Thanks to the Austrian research structure of FFG , our current research project DeepRestore is the first step into the domain of Artificial Intelligence and Neural Networks for our well known DIAMANT-Film Restoration environment.

The main goal is increasing precision and restoration efficiency, based on Deep Learning models for dust/dirt and permanent defects such as scratches and camera hairs.

In the first year of the project, we worked together with our scientific partner TU-Graz on the rapid prototyping of various neuronal networks, based on Tensor Flow techniques.

The development of a dedicated and specific software supported the manual creation of some 500 verified HQ ground-truth samples for dust &dirt defects and their optimal repair. Supported by mathematics and generalisation, the ground-truth forms the basis of a representative 10,000 sample trainings-set.

First training results in our rapid prototyping environment are promising for dust & dirt defects, but there is still some room for improvements, that will be in the focus of our 2019 activities. Beside that, we are going to generate additional and specific ground truth for defects such as Scratches and Camera hairs.

If successful the new AI based methods will strengthen our restoration filters inside DIAMANT-Film Suite from the year 2020 onwards.

About HS-ART

Our DIAMANT-Film Restoration software and DustBuster+ retouching application have become one of the leading high end film restoration solutions on the market.
We are happy to help you integrating restoration services into your workflow or consult you in building up a complete workflow from film scanning via restoration to printing and archiving.

Tel: +43 316 915 998-0 email: office(a)hs-art.com