Deep Video Color Propagation

TL;DR

This paper introduces a deep learning framework for video color propagation that combines local and global strategies, improving temporal stability and semantic consistency over existing methods.

Contribution

It presents a novel deep learning approach integrating local frame-by-frame and global semantic-based color propagation strategies.

Findings

Outperforms existing video and image color propagation methods

Achieves better temporal stability and semantic consistency

Surpasses neural style transfer approaches in color propagation quality

Abstract

Traditional approaches for color propagation in videos rely on some form of matching between consecutive video frames. Using appearance descriptors, colors are then propagated both spatially and temporally. These methods, however, are computationally expensive and do not take advantage of semantic information of the scene. In this work we propose a deep learning framework for color propagation that combines a local strategy, to propagate colors frame-by-frame ensuring temporal stability, and a global strategy, using semantics for color propagation within a longer range. Our evaluation shows the superiority of our strategy over existing video and image color propagation methods as well as neural photo-realistic style transfer approaches.