DeepRemaster: Temporal source-reference attention networks for comprehensive video enhancement

Satoshi Iizuka, Edgar Simo-Serra

Research output: Contribution to journalArticle

Abstract

The remastering of vintage film comprises of a diversity of sub-tasks including super-resolution, noise removal, and contrast enhancement which aim to restore the deteriorated film medium to its original state. Additionally, due to the technical limitations of the time, most vintage film is either recorded in black and white, or has low quality colors, for which colorization becomes necessary. In this work, we propose a single framework to tackle the entire remastering task semi-interactively. Our work is based on temporal convolutional neural networks with attention mechanisms trained on videos with data-driven deterioration simulation. Our proposed source-reference attention allows the model to handle an arbitrary number of reference color images to colorize long videos without the need for segmentation while maintaining temporal consistency. Quantitative analysis shows that our framework outperforms existing approaches, and that, in contrast to existing approaches, the performance of our framework increases with longer videos and more reference color images.

Original languageEnglish
Article number176
JournalACM Transactions on Graphics
Volume38
Issue number6
DOIs
Publication statusPublished - 2019 Nov

Keywords

  • Colorization
  • Convolutional network
  • Remastering
  • Restoration
  • Source-reference attention

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design

Fingerprint Dive into the research topics of 'DeepRemaster: Temporal source-reference attention networks for comprehensive video enhancement'. Together they form a unique fingerprint.

  • Cite this