BiSTNet: Semantic Image Prior Guided Bidirectional Temporal Feature Fusion for Deep Exemplar-based Video Colorization

no code implementations • 5 Dec 2022 • Yixin Yang, Zhongzheng Peng, Xiaoyu Du, Zhulin Tao, Jinhui Tang, Jinshan Pan

To overcome this problem, we further develop a mixed expert block to extract semantic information for modeling the object boundaries of frames so that the semantic image prior can better guide the colorization process for better performance.

Colorization Semantic correspondence