The O-Haze dataset contains 35 hazy images (size 2833×4657 pixels) for training. It has 5 hazy images for validation along with their corresponding ground truth images.
45 PAPERS • 1 BENCHMARK
A new large-scale benchmark consisting of both synthetic and real-world hazy images, called REalistic Single Image DEhazing (RESIDE). RESIDE highlights diverse data sources and image contents, and is divided into five subsets, each serving different training or evaluation purposes.
23 PAPERS • 5 BENCHMARKS
Includes 950 real-world underwater images, 890 of which have the corresponding reference images.
23 PAPERS • 1 BENCHMARK
The I-Haze dataset contains 25 indoor hazy images (size 2833×4657 pixels) training. It has 5 hazy images for validation along with their corresponding ground truth images.
22 PAPERS • 1 BENCHMARK
NN-HAZE is an image dehazing dataset. Since in many real cases haze is not uniformly distributed NH-HAZE, a non-homogeneous realistic dataset with pairs of real hazy and corresponding haze-free images. This is the first non-homogeneous image dehazing dataset and contains 55 outdoor scenes. The non-homogeneous haze has been introduced in the scene using a professional haze generator that imitates the real conditions of hazy scenes.
16 PAPERS • 2 BENCHMARKS
The D-HAZY dataset is generated from NYU depth indoor image collection. D-HAZY contains depth map for each indoor hazy image. It contains 1400+ real images and corresponding depth maps used to synthesize hazy scenes based on Koschmieder’s light propagation mode
13 PAPERS • NO BENCHMARKS YET
A dataset of images taken in different locations with varying water properties, showing color charts in the scenes. Moreover, to obtain ground truth, the 3D structure of the scene was calculated based on stereo imaging. This dataset enables a quantitative evaluation of restoration algorithms on natural images.
11 PAPERS • NO BENCHMARKS YET