I-HAZE: a dehazing benchmark with real hazy and haze-free indoor images
This provides a benchmark for researchers in computational imaging to test dehazing algorithms, but it is incremental as it adds a new dataset to existing ones.
The authors tackled the lack of ground truth for comparing image dehazing methods by introducing I-HAZE, a dataset with 35 pairs of real hazy and haze-free indoor images, enabling objective evaluation using metrics like PSNR and SSIM.
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.