D-HAZY: A dataset to evaluate quantitatively dehazing algorithms

By Cosmin Ancuți, Codruta Orniana Ancuti, C. De Vleeschouwer. International Conference on Information Photonics, 2016

338 citations recorded by the source corpus.

How researchers see this paper

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

I-HAZE: a dehazing benchmark with real hazy and haze-free indoor images (2018, methodology): “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.”
O-HAZE: A Dehazing Benchmark with Real Hazy and Haze-Free Outdoor Images (2018, methodology): “In [4], a dataset of 1400+ images of real complex scenes has been derived from the Middleburry(2) and the NYU-Depth V2(3) datasets.”
Vision Transformers for Single Image Dehazing (2022, neutral): “[51], [52] and synthetic datasets [53], [54], [55].”
NH-HAZE: An Image Dehazing Benchmark with Non-Homogeneous Hazy and Haze-Free Images (2020, methodology): “D-Hazy [6] dataset uses the images and the depth maps of the Middleburry(2) and the NYU-Depth V2(3) datasets.”
Cycle-Dehaze: Enhanced CycleGAN for Single Image Dehazing (2018, methodology): “The proliferation of deep neural networks increases the use of large-scale datasets, therefore, researchers tend to create synthetic dehazing datasets like FRIDA [33] and D-HAZY [2] , which have a more practical creation process than real dehazing datasets.”
Fast and memory efficient de-hazing technique for real-time computer vision applications (2020, methodology): “To verify the validity of our proposed algorithm, we choose a well-known standard database Middlebury [13].”