Realistic Large-Scale Fine-Depth Dehazing Dataset from 3D Videos

TL;DR

This paper introduces a large, realistic outdoor dehazing dataset created from HD 3D movies using stereo depth, significantly improving dehazing performance on real scenes and providing a new benchmark for the field.

Contribution

The paper presents a novel large-scale outdoor dehazing dataset from 3D videos, enhancing realism and diversity over existing datasets, and demonstrates its effectiveness in improving dehazing methods.

Findings

The new dataset is more realistic and diverse than existing ones.

Using the dataset improves dehazing performance on real outdoor scenes.

Evaluation of state-of-the-art methods on the dataset provides benchmarking insights.

Abstract

Image dehazing is one of the important and popular topics in computer vision and machine learning. A reliable real-time dehazing method with reliable performance is highly desired for many applications such as autonomous driving, security surveillance, etc. While recent learning-based methods require datasets containing pairs of hazy images and clean ground truth, it is impossible to capture them in real scenes. Many existing works compromise this difficulty to generate hazy images by rendering the haze from depth on common RGBD datasets using the haze imaging model. However, there is still a gap between the synthetic datasets and real hazy images as large datasets with high-quality depth are mostly indoor and depth maps for outdoor are imprecise. In this paper, we complement the existing datasets with a new, large, and diverse dehazing dataset containing real outdoor scenes from High-Definition (HD) 3D movies. We select a large number of high-quality frames of real outdoor scenes and render haze on them using depth from stereo. Our dataset is clearly more realistic and more diversified with better visual quality than existing ones. More importantly, we demonstrate that using this dataset greatly improves the dehazing performance on real scenes. In addition to the dataset, we also evaluate a series state of the art methods on the proposed benchmarking datasets.