Demo for Temporally Consistent Video Colorization ( TCVC)

Video colorization is a challenging and highly illposed 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 framelevel deep features in a bidirectional way to enhance the temporal consistency of colorization. Furthermore, TCVC introduces a selfregularization learning (SRL) scheme to minimize the prediction difference obtained with different time steps. SRL does not require any groundtruth color videos for training and can further improve temporal consistency. Experiments demonstrate that our method can not only obtain v