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

By Codruta Orniana Ancuti, Cosmin Ancuți, Radu Timofte, C. De Vleeschouwer. Advanced Concepts for Intelligent Vision Systems Conference, 2018

465 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/013a74b9c78e292a8ea9e7dcbce6615f20b34276

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

NH-HAZE: An Image Dehazing Benchmark with Non-Homogeneous Hazy and Haze-Free Images (2020, methodology): “I-HAZE and O-HAZE were employed by the ﬁrst image dehazing challenge [2] organized in conjunction with the 2018 IEEE CVPR NTIRE work-shop 4 .”
Vision Transformers for Single Image Dehazing (2022, methodology): “These dehazing datasets are divided into two main categories: real datasets [47], [50],”
Multi-Scale Boosted Dehazing Network With Dense Feature Fusion (2020, background): “I-HAZE [2] PSNR↑ 14.”
Cycle-Dehaze: Enhanced CycleGAN for Single Image Dehazing (2018, methodology): “During data augmentation, we have obtained 200 images per original image in the training set of the I-HAZE [6] and O-HAZE [7] datasets, since this dataset contains too few images.”
Advancing Image Understanding in Poor Visibility Environments: A Collective Benchmark Study (2019, methodology): “video restoration, such as DIV2K [108] and MANGA109 [29] for image super-resolution, PolyU [123] and Darmstadt [89] for denoising, RawInDark [13] and LOL dataset [120] for low light enhancement, HazeRD [141], OHAZE [3] and IHAZE [2] for dehazing, Rain100L/H [127] and Rain800 [134] for rain streak re”