I-HAZE: a dehazing benchmark with real hazy and haze-free indoor images

TL;DR

The paper introduces I-HAZE, a new indoor dehazing dataset with real haze and ground-truth images, enabling objective evaluation of dehazing algorithms using standard metrics.

Contribution

It provides the first indoor dehazing dataset with real haze generated by a professional machine and paired ground-truth images for accurate benchmarking.

Findings

Allows objective comparison of dehazing methods using PSNR and SSIM.

Includes color calibration tools for better assessment.

Uses real haze for more realistic evaluation.

Abstract

Image dehazing has become an important computational imaging topic in the recent years. However, due to the lack of ground truth images, the comparison of dehazing methods is not straightforward, nor objective. To overcome this issue we introduce a new dataset -named I-HAZE- that contains 35 image pairs of hazy and corresponding haze-free (ground-truth) indoor images. Different from most of the existing dehazing databases, hazy images have been generated using real haze produced by a professional haze machine. For easy color calibration and improved assessment of dehazing algorithms, each scene include a MacBeth color checker. Moreover, since the images are captured in a controlled environment, both haze-free and hazy images are captured under the same illumination conditions. This represents an important advantage of the I-HAZE dataset that allows us to objectively compare the existing image dehazing techniques using traditional image quality metrics such as PSNR and SSIM.