HazeSpace2M: A Dataset for Haze Aware Single Image Dehazing

TL;DR

HazeSpace2M is a large, diverse dataset for haze type classification and dehazing, enabling improved haze removal by classifying haze types before applying specialized dehazing algorithms.

Contribution

This work introduces HazeSpace2M, a novel large-scale dataset with diverse haze types, and proposes a haze classification-based dehazing framework that enhances image clarity.

Findings

State-of-the-art models achieve high accuracy on synthetic datasets but lower on real haze.

Haze type classification followed by specialized dehazing improves PSNR, SSIM, and MSE metrics.

Framework enhances performance of existing dehazing models on real-world hazy images.

Abstract

Reducing the atmospheric haze and enhancing image clarity is crucial for computer vision applications. The lack of real-life hazy ground truth images necessitates synthetic datasets, which often lack diverse haze types, impeding effective haze type classification and dehazing algorithm selection. This research introduces the HazeSpace2M dataset, a collection of over 2 million images designed to enhance dehazing through haze type classification. HazeSpace2M includes diverse scenes with 10 haze intensity levels, featuring Fog, Cloud, and Environmental Haze (EH). Using the dataset, we introduce a technique of haze type classification followed by specialized dehazers to clear hazy images. Unlike conventional methods, our approach classifies haze types before applying type-specific dehazing, improving clarity in real-life hazy images. Benchmarking with state-of-the-art (SOTA) models, ResNet50 and AlexNet achieve 92.75\% and 92.50\% accuracy, respectively, against existing synthetic datasets. However, these models achieve only 80% and 70% accuracy, respectively, against our Real Hazy Testset (RHT), highlighting the challenging nature of our HazeSpace2M dataset. Additional experiments show that haze type classification followed by specialized dehazing improves results by 2.41% in PSNR, 17.14% in SSIM, and 10.2\% in MSE over general dehazers. Moreover, when testing with SOTA dehazing models, we found that applying our proposed framework significantly improves their performance. These results underscore the significance of HazeSpace2M and our proposed framework in addressing atmospheric haze in multimedia processing. Complete code and dataset is available on \href{https://github.com/tanvirnwu/HazeSpace2M} {\textcolor{blue}{\textbf{GitHub}}}.