Towards General and Fast Video Derain via Knowledge Distillation

TL;DR

This paper introduces RRGNet, a fast and general video derain network that uses knowledge distillation and a rain review module to effectively remove various rain streaks from videos, maintaining high performance and speed.

Contribution

The paper presents a novel single pre-trained model capable of handling multiple rain streak types using knowledge distillation and a rain review module for continual learning.

Findings

Achieves state-of-the-art derain performance with high speed.

Effectively handles diverse rain streak types.

Maintains performance without forgetting old tasks.

Abstract

As a common natural weather condition, rain can obscure video frames and thus affect the performance of the visual system, so video derain receives a lot of attention. In natural environments, rain has a wide variety of streak types, which increases the difficulty of the rain removal task. In this paper, we propose a Rain Review-based General video derain Network via knowledge distillation (named RRGNet) that handles different rain streak types with one pre-training weight. Specifically, we design a frame grouping-based encoder-decoder network that makes full use of the temporal information of the video. Further, we use the old task model to guide the current model in learning new rain streak types while avoiding forgetting. To consolidate the network's ability to derain, we design a rain review module to play back data from old tasks for the current model. The experimental results show that our developed general method achieves the best results in terms of running speed and derain effect.