Nighttime Dehazing with a Synthetic Benchmark

TL;DR

This paper introduces a synthetic benchmark dataset for nighttime dehazing, a novel method for generating realistic hazy images, and effective algorithms that outperform existing methods in quality and speed.

Contribution

It presents a new synthetic data generation method called 3R and a novel dehazing approach with an optimal-scale prior, advancing nighttime haze removal research.

Findings

The synthetic benchmark enables better evaluation of dehazing methods.

The proposed methods outperform state-of-the-art in image quality and runtime.

The dataset and code are publicly available for research use.

Abstract

Increasing the visibility of nighttime hazy images is challenging because of uneven illumination from active artificial light sources and haze absorbing/scattering. The absence of large-scale benchmark datasets hampers progress in this area. To address this issue, we propose a novel synthetic method called 3R to simulate nighttime hazy images from daytime clear images, which first reconstructs the scene geometry, then simulates the light rays and object reflectance, and finally renders the haze effects. Based on it, we generate realistic nighttime hazy images by sampling real-world light colors from a prior empirical distribution. Experiments on the synthetic benchmark show that the degrading factors jointly reduce the image quality. To address this issue, we propose an optimal-scale maximum reflectance prior to disentangle the color correction from haze removal and address them sequentially. Besides, we also devise a simple but effective learning-based baseline which has an encoder-decoder structure based on the MobileNet-v2 backbone. Experiment results demonstrate their superiority over state-of-the-art methods in terms of both image quality and runtime. Both the dataset and source code will be available at https://github.com/chaimi2013/3R.