# Single Image Deraining: A Comprehensive Benchmark Analysis

## TL;DR

This paper provides a comprehensive benchmark and evaluation of single image deraining algorithms using a large-scale dataset with diverse rainy images and multiple evaluation criteria, highlighting current limitations and future directions.

## Contribution

It introduces a new large-scale benchmark dataset with synthetic and real-world rainy images, along with diverse evaluation metrics for assessing deraining algorithms.

## Key findings

- State-of-the-art algorithms show varying performance across different criteria.
- The dataset reveals limitations in current deraining methods, especially in real-world scenarios.
- Future research should focus on improving generalization and evaluation methods.

## Abstract

We present a comprehensive study and evaluation of existing single image deraining algorithms, using a new large-scale benchmark consisting of both synthetic and real-world rainy images.This dataset highlights diverse data sources and image contents, and is divided into three subsets (rain streak, rain drop, rain and mist), each serving different training or evaluation purposes. We further provide a rich variety of criteria for dehazing algorithm evaluation, ranging from full-reference metrics, to no-reference metrics, to subjective evaluation and the novel task-driven evaluation. Experiments on the dataset shed light on the comparisons and limitations of state-of-the-art deraining algorithms, and suggest promising future directions.