Temporally Consistent Video Colorization with Deep Feature Propagation and Self-regularization Learning
This work addresses temporal inconsistency in video colorization, a domain-specific problem for video processing applications, with incremental improvements over existing methods.
The paper tackles the problem of video colorization, which suffers from flickering artifacts and poor temporal consistency, by proposing a unified framework that jointly addresses colorization and consistency. The method achieves visually pleasing results and significantly better temporal consistency than state-of-the-art approaches.
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.