DeepRemaster: Temporal Source-Reference Attention Networks for Comprehensive Video Enhancement
This addresses the problem of restoring deteriorated vintage films for archival or entertainment purposes, representing an incremental improvement by integrating multiple sub-tasks into a single semi-interactive framework.
The authors tackled comprehensive video enhancement for vintage film remastering, including super-resolution, noise removal, contrast enhancement, and colorization, and their framework outperformed existing approaches with performance improving for longer videos and more reference images.
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.