We develop an automated video colorization framework that minimizes the flickering of colors across frames. If we apply image colorization techniques to successive frames of a video, they treat each frame as a separate colorization task. Thus, they do not necessarily maintain the colors of a scene consistently across subsequent frames. The proposed solution includes a novel deep recurrent encoder-decoder architecture which is capable of maintaining temporal and contextual coherence between consecutive frames of a video. We use a high-level semantic feature extractor to automatically identify the context of a scenario including objects, with a custom fusion layer that combines the spatial and temporal features of a frame sequence. We demonstrate experimental results, qualitatively showing that recurrent neural networks can be successfully used to improve color consistency in video colorization.
@article{arxiv.2305.13704,
title = {FlowChroma -- A Deep Recurrent Neural Network for Video Colorization},
author = {Thejan Wijesinghe and Chamath Abeysinghe and Chanuka Wijayakoon and Lahiru Jayathilake and Uthayasanker Thayasivam},
journal= {arXiv preprint arXiv:2305.13704},
year = {2023}
}