Dual feature extractor generative adversarial network for colorization

Abstract

The coloring efficiency of most colorization algorithms is suboptimal. Therefore, the dual feature extractor generative adversarial network was designed for colorization. The U-Net-like network was used as the trunk network in the generator. The encoder was used to extract the local features of a grayscale image. The branch extractor used the ResNeXt network that was added to the SE module as a high-level feature extractor to extract the global features of the grayscale image. The two features were fused to predict the chrominance. This strategy prevented color leakage and detail loss in colorization. Moreover, the adversarial loss was added to minimize the tendency toward acquiring an unsaturated tone. The effectiveness of the proposed method was evaluated quantitatively and qualitatively.