Benchmarking Single Image Dehazing and Beyond

TL;DR

This paper introduces RESIDE, a large-scale benchmark for evaluating single image dehazing algorithms using synthetic and real-world images, comprehensive metrics, and analysis of current methods.

Contribution

It provides the first extensive benchmark dataset and evaluation framework for single image dehazing, including diverse data, multiple evaluation criteria, and insights into algorithm performance.

Findings

Current algorithms have notable limitations on real-world images.

The benchmark reveals the strengths and weaknesses of state-of-the-art methods.

Future research directions are suggested based on evaluation results.

Abstract

We present a comprehensive study and evaluation of existing single image dehazing algorithms, using a new large-scale benchmark consisting of both synthetic and real-world hazy images, called REalistic Single Image DEhazing (RESIDE). RESIDE highlights diverse data sources and image contents, and is divided into five subsets, 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 RESIDE shed light on the comparisons and limitations of state-of-the-art dehazing algorithms, and suggest promising future directions.