Gta-Net: Gradual Temporal Aggregation Network For Fast Video Deraining

Recently, the development of intelligent technology arouses the requirements of high-quality videos. Rain streak is a frequent and inevitable factor to degrade the video. Many researchers have put their energies into eliminating the adverse effects of rainy video. Unfortunately, how to fully utilize the temporal information from rainy video still be in suspense. In this work, to effectively exploit temporal information, we develop a simple but effective network, Gradual Temporal Aggregation Network (GTA-Net for short). To be specific, by dividing the rainy frames into different groups according to the same distance as the current frame, a multi-stream coarse temporal aggregation module is first performed to aggregate different temporal information with equal status and importance. Then we design a single-stream fine temporal aggregation module to further fuse the integrated frames that maintain the different distances with the target frame. In this way of coarse-to-fine, we not only achieve superior performance, but also gain the surprising execution speed owing to abandon the time-consuming alignment operation. Plenty of experimental results demonstrate that our GTA-Net performs favorably compared to other state-of-the-art approaches. The meticulous ablation study further indicates the effectiveness of our designed GTA-Net.