Training a Deep Remastering Model

 

We present a deep learning solution to bring the NTSC version to the new scan quality levels, which would be otherwise impossible with existing tools.

July 24, 2022
ACM SIGGRAPH 2022

 

Authors

Abdelaziz Djelouah (DisneyResearch|Studios)

Sally Hattori (The Walt Disney Company)

Andrew J. Wahlquist (The Walt Disney Company)

Christopher Schroers (DisneyResearch|Studios)

 

Training a Deep Remastering Model

Download Publication PDF

Abstract

The success of video streaming platforms has pushed studios to make available TV shows from legacy catalog, and there is an increased demand for remastering this content. Ideally, film reels are re-scanned with modern devices directly into high quality digital format. However this is not always possible as parts of the original film reels can be damaged or missing, and the content is then available in its entirety only in the broadcast version, typically NTSC. In this work, we present a deep learning solution to bring the NTSC version to the new scan quality levels, which would be otherwise impossible with existing tools.

Copyright Notice

The documents contained in these directories are included by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a non-commercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, notwithstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author’s copyright. These works may not be reposted without the explicit permission of the copyright holder.

 

 
Research at Disney

 

 

 

 

 

 

 

 

Legal
MORE