HazeSpace2M: A Dataset for Haze Aware Single Image Dehazing

Md Tanvir Islam, Nasir Rahim, Saeed Anwar, Muhammad Saqib, Sambit Bakshi, Khan Muhammad

Abstract: Reducing atmospheric hazes and enhancing image clarity is crucial for a range of applications related to computer vision. The lack of real-life hazy ground truth images necessitates synthetic datasets, which often need more diverse haze types, impeding effective haze type classification and dehazing algorithm selection. This research introduces the HazeSpace2M dataset, a comprehensive collection of over 2 million images designed to enhance the performance of dehazing through haze-type classification. HazeSpace2M includes diverse scenes with 10 haze intensity levels, featuring Fog, Cloud, and a novel category, Environmental Haze (EH). Leveraging the dataset, we introduce a novel technique of haze-type classification followed by specialized dehazers to dehaze hazy images. Unlike the conventional methods, our approach classifies haze types before applying type-specific dehazing, improving clarity and functionality across applications lacking real-life hazy images. We benchmark the state-of-the-art classification models against different combinations of the hazy benchmarking datasets (HBDs) and the Real Hazy Testset (RHT) from the HazeSapce2M dataset. For instance, ResNet50 and AlexNet, on average, achieve 92.75% and 92.50% accuracy, respectively, against the existing synthetic HBDs. However, the same models furnish 80% and 70% accuracy, respectively, against our RHT, proving the challenging nature of our dataset. Additional experiments utilizing our proposed framework verify that haze-type classification followed by specialized dehazing enhances dehazing results by 2.41% in PSNR, 17.14% in SSIM, and 10.2% in MSE over general dehazers. These results highlight the significance of HazeSapce2M and the proposed framework in addressing the pervasive challenge of atmospheric haze in multimedia processing. The codes and dataset will be available on GitHub soon.

Primary Subject Area: [Content] Vision and Language

Secondary Subject Area: [Experience] Multimedia Applications

Relevance To Conference: The paper "HazeSpace2M: A Dataset for Haze Aware Single Image Dehazing" makes a notable contribution to multimedia and multimodal processing, particularly within the context of the ACM Multimedia conference. Addressing the prevalent issue of haze in outdoor images, the creation of the HazeSpace2M dataset fills a critical gap in the availability of high-quality datasets tailored specifically for haze-aware single image dehazing tasks. By providing a comprehensive dataset that includes diverse scenes affected by varying degrees of haze, along with corresponding ground truth dehazed images, the research facilitates the development and evaluation of more robust and accurate dehazing algorithms. In the realm of Multimedia, where the advancement of image and video processing techniques is paramount, the availability of such a dataset enables researchers to explore innovative approaches for mitigating the effects of haze in multimedia content. Through the utilization of HazeSpace2M, researchers can benchmark their dehazing algorithms, fostering collaboration and innovation within the multimedia community. Ultimately, the study significantly contributes to advancing the state-of-the-art in multimedia processing by providing researchers with valuable resources to address the challenges posed by haze in visual media.

Submission Number: 3668