D-HAZY: A dataset to evaluate quantitatively dehazing algorithms

Ancuti, Cosmin; Vleeschouwer, Christophe De

doi:10.1109/icip.2016.7532754

Cited by 255 publications

(132 citation statements)

References 28 publications

Supporting

Mentioning

120

Contrasting

Order By: Relevance

“…The work [40] presents the FRIDA dataset designed for Advanced Driver Assistance Systems (ADAS) that is a synthetic image database with 66 computer graphics generated roads scenes. In [4], a dataset of 1400+ images of real complex scenes has been derived from the Middleburry 1 and the NYU-Depth V2 2 datasets. It contains high quality real scenes, and the depth map associated to each image has been used to yield synthesized hazy im-1 http://vision.middlebury.edu/stereo/data/scenes2014/ 2 http://cs.nyu.edu/˜silberman/datasets/nyu_depth_v2.…”

Section: Dehazing Assessmentmentioning

confidence: 99%

O-HAZE: A Dehazing Benchmark with Real Hazy and Haze-Free Outdoor Images

Ancuti

Timofte

Vleeschouwer

2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

Self Cite

524

226

View full text Add to dashboard Cite

Haze removal or dehazing is a challenging ill-posed problem that has drawn a significant attention in the last few years. Despite this growing interest, the scientific community is still lacking a reference dataset to evaluate objectively and quantitatively the performance of proposed dehazing methods. The few datasets that are currently considered, both for assessment and training of learning-based dehazing techniques, exclusively rely on synthetic hazy images. To address this limitation, we introduce the first outdoor scenes database (named O-HAZE) composed of pairs of real hazy and corresponding haze-free images. In practice, hazy images have been captured in presence of real haze, generated by professional haze machines, and O-HAZE contains 45 different outdoor scenes depicting the same visual content recorded in haze-free and hazy conditions, under the same illumination parameters. To illustrate its usefulness, O-HAZE is used to compare a representative set of state-of-the-art dehazing techniques, using traditional image quality metrics such as PSNR, SSIM and CIEDE2000. This reveals the limitations of current techniques, and questions some of their underlying assumptions.

show abstract

Section: Dehazing Assessmentmentioning

confidence: 99%

O-HAZE: A Dehazing Benchmark with Real Hazy and Haze-Free Outdoor Images

Ancuti

Timofte

Vleeschouwer

2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

Self Cite

524

226

View full text Add to dashboard Cite

show abstract

“…The work [31] presents the FRIDA dataset designed for Advanced Driver Assistance Systems (ADAS) that is a synthetic image database (computer graphics generated scenes) with 66 roads synthesized scenes. In [32], a dataset of 1400+ images of real complex scenes has been derived from the Middleburry 1 and the NYU-Depth V2 2 datasets. It contains high quality real scenes, and the depth map associated to each image has been used to yield synthesized hazy images based on Koschmieder's light propagation model [33].…”

Section: Introductionmentioning

confidence: 99%

I-HAZE: A Dehazing Benchmark with Real Hazy and Haze-Free Indoor Images

Ancuti

Timofte

Vleeschouwer

2018

Lecture Notes in Computer Science

Self Cite

243

119

View full text Add to dashboard Cite

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 I-HAZE, a new dataset 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. To ease color calibration and improve the 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.

show abstract

“…We choose 6 pairs of stereo images from the Middlebury Stereo Dataset (2005) [48], [49] and D-HAZY Dataset [50].…”

Section: Qualitative Comparison On Synthetic Imagesmentioning

confidence: 99%