Restoration of Analog Videos Using Swin-UNet
This work solves the problem of costly and slow manual restoration for archivists and historians by automating the recovery of degraded analog videos.
The paper tackles the restoration of severely degraded analog videos from historical archives by addressing issues like tape mistracking, and demonstrates the effectiveness of their demo system on real-world videos from a major archive.
In this paper, we present a system to restore analog videos of historical archives. These videos often contain severe visual degradation due to the deterioration of their tape supports that require costly and slow manual interventions to recover the original content. The proposed system uses a multi-frame approach and is able to deal with severe tape mistracking, which results in completely scrambled frames. Tests on real-world videos from a major historical video archive show the effectiveness of our demo system. The code and the pre-trained model are publicly available at https://github.com/miccunifi/analog-video-restoration.