O-HAZE: A Dehazing Benchmark with Real Hazy and Haze-Free Outdoor Images
Codruta O. Ancuti,Cosmin Ancuti,Radu Timofte,Christophe De Vleeschouwer +3 more
- pp 754-762
TLDR
The O-HAZE dataset as mentioned in this paper contains 45 different outdoor scenes depicting the same visual content recorded in haze-free and hazy conditions, under the same illumination parameters, using traditional image quality metrics such as PSNR, SSIM and CIEDE2000.Abstract:
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.read more
Citations
More filters
Proceedings ArticleDOI
Multi-Scale Boosted Dehazing Network With Dense Feature Fusion
TL;DR: Wang et al. as mentioned in this paper proposed a Multi-Scale Boosted Dehazing Network with Dense Feature Fusion based on the U-Net architecture, which can simultaneously remedy the missing spatial information from high-resolution features and exploit the nonadjacent features.
Proceedings ArticleDOI
Cycle-Dehaze: Enhanced CycleGAN for Single Image Dehazing
TL;DR: In this article, an end-to-end network called Cycle-Dehaze, which does not require pairs of hazy and corresponding ground truth images for training, is presented.
Proceedings ArticleDOI
Seeing Through Fog Without Seeing Fog: Deep Multimodal Sensor Fusion in Unseen Adverse Weather
Mario Bijelic,Tobias Gruber,Fahim Mannan,Florian Kraus,Werner Ritter,Klaus Dietmayer,Felix Heide +6 more
TL;DR: In this paper, a multimodal dataset acquired in over 10,000~km of driving in northern Europe is presented, with 100k labels for lidar, camera, radar, and gated NIR sensors.
Proceedings ArticleDOI
“Double-DIP”: Unsupervised Image Decomposition via Coupled Deep-Image-Priors
TL;DR: In this paper, a unified framework for unsupervised layer decomposition of a single image, based on coupled "Deep-image-Prior" (DIP) networks, is proposed.
Proceedings ArticleDOI
Multi-scale Single Image Dehazing Using Perceptual Pyramid Deep Network
TL;DR: This work presents a multi-scale image dehazing method using Perceptual Pyramid Deep Network based on the recently popular dense blocks and residual blocks and is ranked among top-3 methods in terms of quantitative performance in the recently conducted NTIRE2018-Dehazing challenge.
References
More filters
Journal ArticleDOI
Image quality assessment: from error visibility to structural similarity
TL;DR: In this article, a structural similarity index is proposed for image quality assessment based on the degradation of structural information, which can be applied to both subjective ratings and objective methods on a database of images compressed with JPEG and JPEG2000.
Journal ArticleDOI
Guided Image Filtering
Kaiming He,Jian Sun,Xiaoou Tang +2 more
TL;DR: The guided filter is a novel explicit image filter derived from a local linear model that can be used as an edge-preserving smoothing operator like the popular bilateral filter, but it has better behaviors near edges.
Journal ArticleDOI
No-Reference Image Quality Assessment in the Spatial Domain
TL;DR: Despite its simplicity, it is able to show that BRISQUE is statistically better than the full-reference peak signal-to-noise ratio and the structural similarity index, and is highly competitive with respect to all present-day distortion-generic NR IQA algorithms.
Journal ArticleDOI
Making a “Completely Blind” Image Quality Analyzer
TL;DR: This work has recently derived a blind IQA model that only makes use of measurable deviations from statistical regularities observed in natural images, without training on human-rated distorted images, and, indeed, without any exposure to distorted images.
Journal ArticleDOI
Single Image Haze Removal Using Dark Channel Prior
Kaiming He,Jian Sun,Xiaoou Tang +2 more
TL;DR: A simple but effective image prior - dark channel prior to remove haze from a single input image is proposed, based on a key observation - most local patches in haze-free outdoor images contain some pixels which have very low intensities in at least one color channel.