A deep learning model for incorporating temporal information in haze removal

Haze contamination is a very common issue in remote sensing images, which inevitably limits data usability and further applications. Several methods have been developed for haze removal, an ill-posed problem. However, most of these involve various strong assumptions coupled with manually-determined parameters, limit their generalization to different scenarios. Moreover, temporal information amongst time-series images has rarely considered removal. In this paper, the proposed be incorporated more reliable guided by general idea, injection network (TIIN) developed. The TIIN solution removal extracts useful temporally neighboring provided regular revisit satellite sensors. method suitable levels. also applicable neighbors inherent or land cover changes due long-time interval between images. was validated through experiments on both simulated real as well comparison five state-of-the-art benchmark methods. This research provides new paradigm enhancing incorporating