# DeepRemaster: Temporal Source-Reference Attention Networks for Comprehensive Video Enhancement

arXiv: https://arxiv.org/abs/2009.08692 · HTML: https://mlsanity.com/paper/2009.08692/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Sep 2020.

## Built on by (most cited first, 10 of 10)

- [Bringing Old Films Back to Life](https://mlsanity.com/paper/2203.17276/) (2022)
- [Temporally Consistent Video Colorization with Deep Feature Propagation and Self-regularization Learning](https://mlsanity.com/paper/2110.04562/) (2021)
- [Deep Video Prior for Video Consistency and Propagation](https://mlsanity.com/paper/2201.11632/) (2022)
- [ChromaDistill: Colorizing Monochrome Radiance Fields with Knowledge Distillation](https://mlsanity.com/paper/2309.07668/) (2023)
- [Exemplar-based Video Colorization with Long-term Spatiotemporal Dependency](https://mlsanity.com/paper/2303.15081/) (2023)
- [Simulating analogue film damage to analyse and improve artefact restoration on high-resolution scans](https://mlsanity.com/paper/2302.10004/) (2023)
- [Reference-based Restoration of Digitized Analog Videotapes](https://mlsanity.com/paper/2310.14926/) (2023)
- [ReBotNet: Fast Real-time Video Enhancement](https://mlsanity.com/paper/2303.13504/) (2023)
- [Temporal Consistent Automatic Video Colorization via Semantic Correspondence](https://mlsanity.com/paper/2305.07904/) (2023)
- [Restoration of Analog Videos Using Swin-UNet](https://mlsanity.com/paper/2311.04261/) (2023)

## Abstract (arXiv)

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.