Image Dehazing

KITTI (Karlsruhe Institute of Technology and Toyota Technological Institute) is one of the most popular datasets for use in mobile robotics and autonomous driving. It consists of hours of traffic scenarios recorded with a variety of sensor modalities, including high-resolution RGB, grayscale stereo cameras, and a 3D laser scanner. Despite its popularity, the dataset itself does not contain ground truth for semantic segmentation. However, various researchers have manually annotated parts of the dataset to fit their necessities. Álvarez et al. generated ground truth for 323 images from the road detection challenge with three classes: road, vertical, and sky. Zhang et al. annotated 252 (140 for training and 112 for testing) acquisitions – RGB and Velodyne scans – from the tracking challenge for ten object categories: building, sky, road, vegetation, sidewalk, car, pedestrian, cyclist, sign/pole, and fence. Ros et al. labeled 170 training images and 46 testing images (from the visual odometry challenge) with 11 classes: building, tree, sky, car, sign, road, pedestrian, fence, pole, sidewalk, and bicyclist. Source: A Review on Deep Learning Techniques Applied to Semantic Segmentation Image Source: http://www.cvlibs.net/datasets/kitti/eval_object.php?obj_benchmark=3d

DENSE (Depth Estimation oN Synthetic Events) is a new dataset with synthetic events and perfect ground truth. Source: Learning Monocular Dense Depth from Events

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. Source: RESIDE

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. Source: Single image dehazing for a variety of haze scenarios using back projected pyramid network Image Source: https://data.vision.ee.ethz.ch/cvl/ntire18//i-haze/

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. Source: NH-HAZE: An Image Dehazing Benchmark with Non-Homogeneous Hazy and Haze-Free Images

Haze4k is a synthesized dataset with 4,000 hazy images, in which each hazy image has the associate ground truths of a latent clean image, a transmission map, and an atmospheric light ma

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. Source: Underwater Single Image Color Restoration Using Haze-Lines and a New Quantitative Dataset

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 Source: C2MSNet: A Novel approach for single image haze removal Image Source: https://www.semanticscholar.org/paper/D-HAZY%3A-A-dataset-to-evaluate-quantitatively-Ancuti-Ancuti/9451d0b1bfbba5f3e19c083866f1394aabf7d06c

A large-scale non-homogeneous remote sensing image dehazing dataset

Consists of 2,864 videos each with a label from 25 different classes corresponding to an event unfolding 5 seconds. The ERA dataset is designed to have a significant intra-class variation and inter-class similarity and captures dynamic events in various circumstances and at dramatically various scales. Source: ERA: A Dataset and Deep Learning Benchmark for Event Recognition in Aerial Videos

A dataset of over 65,000 pairs of incorrectly white-balanced images and their corresponding correctly white-balanced images. Source: When Color Constancy Goes Wrong: Correcting Improperly White-Balanced Images

SEN12MS-CR-TS is a multi-modal and multi-temporal data set for cloud removal. It contains time-series of paired and co-registered Sentinel-1 and cloudy as well as cloud-free Sentinel-2 data from European Space Agency's Copernicus mission. Each time series contains 30 cloudy and clear observations regularly sampled throughout the year 2018. Our multi-temporal data set is readily pre-processed and backward-compatible with SEN12MS-CR.

A large-scale video dataset for MOR in aerial videos. Source: MOR-UAV: A Benchmark Dataset and Baselines for Moving Object Recognition in UAV Videos

The SMOKE dataset is a dataset for fog/smoke removal. There are 110 self-collected fog/smoke images and their clean pairs. There are 12 other pairs of fog data for evaluation.

The existing multi-modality image fusion dataset lacks comprehensive coverage of adverse weather scenarios. To address this, we introduce AWMM-100k, a benchmark dataset constructed by selecting samples from RoadScene, MSRS, M3FD, and LLVIP, followed by controlled degradation processing to simulate adverse weather conditions. Combined with real-world data captured using a DJI M30T drone equipped with high-resolution visible and thermal cameras, AWMM-100k comprises 187,699 images covering rain, haze, and snow, each categorized into heavy, medium, and light intensities. This dataset supports research on multi-modality image fusion under challenging weather conditions and is also applicable to image restoration tasks such as dehazing, deraining, and desnowing. We thank the original dataset for its contribution. In addition, we believe this dataset significantly expands the scope of multimodal image processing and computer vision research, facilitating advancements in both image fusion and restoration tasks under adverse conditions.

The laparoscopic surgery dataset is associated with our International Journal of Computer Assisted Radiology and Surgery (IJCARS) publication titled “DeSmoke-LAP: Improved Unpaired Image-to-Image Translation for Desmoking in Laparoscopic Surgery”. The training model of the proposed method is available as an open source on Github. We propose DeSmoke-LAP, a new method for removing smoke from real robotic laparoscopic hysterectomy videos. The proposed method is based on the unpaired image-to-image cycle-consistent generative adversarial network in which two novel loss functions, namely, inter-channel discrepancies and dark channel prior. The dataset contains frames and video clips from 10 robot-assisted laparoscopic hysterectomy procedure videos. The original videos were decomposed into frames at 1 fps. From each video, 300 hazy images and 300 clear images were manually selected by observing the electrocauterisation. A short video clip of 50 frames from each procedure was also selected that was utilised for testing. 5-fold cross-validation was performed for all methods under comparison. Quantitative evaluation was done using referenceless metrics and qualitative evaluation was performed through a survey filled out by end-users (surgeons).

A small-scale real-world dataset containing hazy/dusty industrial images and their clean ground truth counterparts. Designed for evaluating deep learning models for dust removal and image dehazing in industrial environments. Collected and fine-tuned by Moshtaghioun et al., 2025.