Temporally Consistent Video Colorization with Deep Feature Propagation and Self-regularization Learning

TL;DR

This paper introduces a novel deep learning framework for video colorization that enhances temporal consistency and visual quality by propagating deep features bidirectionally and employing self-regularization learning without needing ground-truth videos.

Contribution

The proposed TCVC framework jointly addresses colorization and temporal consistency, introducing bidirectional feature propagation and self-regularization learning for improved video colorization.

Findings

Achieves better temporal consistency than state-of-the-art methods.

Produces visually pleasing and stable colorized videos.

Does not require ground-truth color videos for training.

Abstract

Video colorization is a challenging and highly ill-posed problem. Although recent years have witnessed remarkable progress in single image colorization, there is relatively less research effort on video colorization and existing methods always suffer from severe flickering artifacts (temporal inconsistency) or unsatisfying colorization performance. We address this problem from a new perspective, by jointly considering colorization and temporal consistency in a unified framework. Specifically, we propose a novel temporally consistent video colorization framework (TCVC). TCVC effectively propagates frame-level deep features in a bidirectional way to enhance the temporal consistency of colorization. Furthermore, TCVC introduces a self-regularization learning (SRL) scheme to minimize the prediction difference obtained with different time steps. SRL does not require any ground-truth color videos for training and can further improve temporal consistency. Experiments demonstrate that our method can not only obtain visually pleasing colorized video, but also achieve clearly better temporal consistency than state-of-the-art methods.