# Removing Rain in Videos: A Large-scale Database and A Two-stream ConvLSTM Approach

## TL;DR

This paper introduces a large-scale rain video database and a novel two-stream ConvLSTM model that leverages temporal correlations for improved rain removal in videos, outperforming existing methods.

## Contribution

The paper provides the first large-scale rain video database and proposes a two-stream ConvLSTM approach utilizing temporal correlations for effective rain removal.

## Key findings

- The proposed method outperforms state-of-the-art approaches on synthetic and real rain videos.
- The large-scale database enables better training of deep learning models for rain removal.
- Temporal correlation of content and rain patterns is effectively exploited by the model.

## Abstract

Rain removal has recently attracted increasing research attention, as it is able to enhance the visibility of rain videos. However, the existing learning based rain removal approaches for videos suffer from insufficient training data, especially when applying deep learning to remove rain. In this paper, we establish a large-scale video database for rain removal (LasVR), which consists of 316 rain videos. Then, we observe from our database that there exist the temporal correlation of clean content and similar patterns of rain across video frames. According to these two observations, we propose a two-stream convolutional long- and short- term memory (ConvLSTM) approach for rain removal in videos. The first stream is composed of the subnet for rain detection, while the second stream is the subnet of rain removal that leverages the features from the rain detection subnet. Finally, the experimental results on both synthetic and real rain videos show the proposed approach performs better than other state-of-the-art approaches.