Take a prior from other tasks for severe blur removal

Pei Wang, Yu Zhu, Danna Xue, Qingsen Yan, Jinqiu Sun, Sung-Eui Yoon, Yanning Zhang

Abstract: Highlights•A severe blur removal framework with learning a comprehensive semantic prior with global contexts and sharp local details in the natural dynamic scene has been proposed.•The semantic prior learning strategy is built relying on the knowledge distillation by the cross-level feature transferring constraints.•A prior embedding layer with feature aggregation and transformation is proposed to utilize the semantic prior effectively.•The plug-and-play semantic priors boost the performance of the several current deblurring methods.